diff --git a/arborist/qa/nli/manifest.json b/arborist/qa/nli/manifest.json
index 6300628..7d49f8a 100644
--- a/arborist/qa/nli/manifest.json
+++ b/arborist/qa/nli/manifest.json
@@ -20,14 +20,17 @@
   },
   "thresholds_provenance": "the bench-validated operating point — arborist-nli-bench commit a1cb28d, ticket #000049 §7 #18; on the 28+26-case synth set this point gives 28/28 catch, 0/26 false positives, and the entailment guard is what filters the spurious competing-superlative contradictions",
   "recommended_operating_point": {
-    "_comment": "ticket #000049 §7 #23 — the {model × k × agg × θc × θe} grid sweep found this clears the §7 #12 gate on bench-qa traffic: catches 27/28 synthetic recombinations (incl. both 5f-fal-hard fixtures), 0 false positives on 89 real STRICT answers (n=1 bench-qa). NOT yet the active default — pending confirmation on a BENCH_QA_N=3 STRICT sample (~250 cells). When promoted: switch nli_model_version/hf_repo to this, set thresholds + max_candidate_clauses + aggregation accordingly, and fold nli_policy_hash (model+k+agg+θc+θe) into governance_policy_hash before any audit_mode effect (§7 #2).",
-    "nli_model_version": "nli-shadow-v1-deberta-v3-base",
-    "hf_repo": "MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli",
-    "pinned_revision": "6f5cf0a2b59cabb106aca4c287eed12e357e90eb",
-    "max_candidate_clauses": 2,
-    "aggregation": "max",
-    "thresholds": {"contradiction_veto": 0.99, "entailment_block_veto": 0.9},
-    "fallback_small_model": {"nli_model_version": "nli-shadow-v1-minilm2-l6-h768", "note": "82M; passes too at 24/28 catch · 0/89 FP with k=2/agg=max/θc=0.95/θe=0.9 — the cost-pick if the 184M latency matters"}
+    "_comment": "ticket #000049 §7 #24 — n=3-confirmed (275 real STRICT cells). The {model × candidate-cap k × aggregation × guard × θc × θe} mega-grid found THIS clears the §7 #12 gate: microsoft/deberta-large-mnli + k=3 + agg='margin' (= max over clauses of p_contra - p_entail, a single threshold folding the entailment guard in) + θc=0.995 → catches all 28 synthetic recombinations (incl. both 5f-fal-hard fixtures), 0 false positives on 275 real STRICT answers, 0 on the 26 synthetic legit summaries. NOTE: the §7 #23 candidate (deberta-base k=2 θc=0.99) did NOT survive the n=3 sample — it only catches 11/28 at θc=0.995, which is what the larger STRICT sample forces; the 89-cell n=1 sample under-counted the spurious-contradiction tail. Still NOT the active default — pending (a) an even larger STRICT sample / real-traffic check and (b) a bigger recombination set than 28. When promoted: switch nli_model_version/hf_repo, wire 'aggregation'='margin' into ShadowNLI.check, set max_candidate_clauses + thresholds accordingly, and fold nli_policy_hash (model+k+agg+θc) into governance_policy_hash before any audit_mode effect (§7 #2).",
+    "nli_model_version": "nli-shadow-v1-deberta-large-mnli",
+    "hf_repo": "microsoft/deberta-large-mnli",
+    "max_candidate_clauses": 3,
+    "aggregation": "margin",
+    "thresholds": {"contradiction_minus_entailment_margin_veto": 0.995},
+    "alternates_at_fp0_n3": [
+      {"hf_repo": "roberta-large-mnli", "config": "k=2/agg=max/θc=0.998", "catch": "21/28", "note": "355M; second-best, ~0.75 recall"},
+      {"hf_repo": "facebook/bart-large-mnli", "config": "k=3/agg=mean/θc=0.94", "catch": "20/28", "note": "407M; ~0.71 recall"},
+      {"hf_repo": "cross-encoder/nli-MiniLM2-L6-H768", "config": "k=4/agg=mean/θc=0.96", "catch": "14/28", "note": "82M; only ~0.50 recall at fp=0 on the n=3 sample — NOT the cost-pick after all once you demand 0 FP at proper n"}
+    ]
   },
   "alternates": [
     {"nli_model_version": "nli-shadow-v1-minilm-l6-mnli", "hf_repo": "cross-encoder/nli-MiniLM2-L6-H768", "pinned_revision": "b95119ce93d3e065de6214e38cd4a97b0f2f2c6d", "license": "Apache-2.0", "approx_mb": 90, "note": "= the main checkpoint; listed here too so a grid sweep includes 'small' explicitly"},
diff --git a/bench/results/nli-shadow-grid-n3-synth-vs-realstrict.json b/bench/results/nli-shadow-grid-n3-synth-vs-realstrict.json
new file mode 100644
index 0000000..251cb9b
--- /dev/null
+++ b/bench/results/nli-shadow-grid-n3-synth-vs-realstrict.json
@@ -0,0 +1,10018 @@
+{
+  "generated_at": "2026-05-12T22:31:14Z",
+  "should_demote_file": "/home/fox/nli-data/recombination.jsonl",
+  "n_should_demote": 28,
+  "should_not_demote_file": "/home/fox/nli-data/benchqa-n3.jsonl",
+  "n_should_not_demote": 275,
+  "k_grid": [
+    1,
+    2,
+    3,
+    4,
+    6,
+    8,
+    12
+  ],
+  "aggs": [
+    "max",
+    "mean",
+    "top2",
+    "top3",
+    "meanTop2",
+    "meanTop3",
+    "margin"
+  ],
+  "guards": [
+    "max_entail",
+    "paired_entail"
+  ],
+  "theta_c_grid": [
+    0.3,
+    0.4,
+    0.5,
+    0.6,
+    0.7,
+    0.8,
+    0.85,
+    0.9,
+    0.92,
+    0.94,
+    0.95,
+    0.96,
+    0.97,
+    0.975,
+    0.98,
+    0.985,
+    0.99,
+    0.995,
+    0.998,
+    0.999
+  ],
+  "theta_e_grid": [
+    0.3,
+    0.5,
+    0.7,
+    0.9,
+    0.95,
+    1.01
+  ],
+  "kmax": 12,
+  "models": {
+    "nli-shadow-v1-minilm2-l6-h768": {
+      "hf_repo": "cross-encoder/nli-MiniLM2-L6-H768",
+      "backend": "torch",
+      "device": "cuda",
+      "n_nli_pairs": 3355,
+      "infer_seconds": 4.43,
+      "global_best": {
+        "k": 4,
+        "agg": "mean",
+        "guard": "max_entail",
+        "theta_c": 0.96,
+        "theta_e": 0.3,
+        "catch": 0.5,
+        "fp": 0.0
+      },
+      "pareto": [
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "max_entail",
+          "theta_c": 0.96,
+          "theta_e": 0.3,
+          "catch": 0.5,
+          "fp": 0.0
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "theta_c": 0.985,
+          "theta_e": 1.01,
+          "catch": 0.6429,
+          "fp": 0.0036
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.92,
+          "theta_e": 0.3,
+          "catch": 0.8214,
+          "fp": 0.0073
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.95,
+          "theta_e": 0.9,
+          "catch": 0.8571,
+          "fp": 0.0109
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.94,
+          "theta_e": 0.9,
+          "catch": 0.9286,
+          "fp": 0.0327
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.94,
+          "theta_e": 0.9,
+          "catch": 0.9643,
+          "fp": 0.0655
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.7,
+          "theta_e": 0.9,
+          "catch": 1.0,
+          "fp": 0.1164
+        }
+      ],
+      "configs_ranked": [
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.0357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        }
+      ]
+    },
+    "nli-shadow-v1-minilm-l6-mnli": {
+      "hf_repo": "cross-encoder/nli-MiniLM2-L6-H768",
+      "backend": "torch",
+      "device": "cuda",
+      "n_nli_pairs": 3355,
+      "infer_seconds": 3.25,
+      "global_best": {
+        "k": 4,
+        "agg": "mean",
+        "guard": "max_entail",
+        "theta_c": 0.96,
+        "theta_e": 0.3,
+        "catch": 0.5,
+        "fp": 0.0
+      },
+      "pareto": [
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "max_entail",
+          "theta_c": 0.96,
+          "theta_e": 0.3,
+          "catch": 0.5,
+          "fp": 0.0
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "theta_c": 0.985,
+          "theta_e": 1.01,
+          "catch": 0.6429,
+          "fp": 0.0036
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.92,
+          "theta_e": 0.3,
+          "catch": 0.8214,
+          "fp": 0.0073
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.95,
+          "theta_e": 0.9,
+          "catch": 0.8571,
+          "fp": 0.0109
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.94,
+          "theta_e": 0.9,
+          "catch": 0.9286,
+          "fp": 0.0327
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.94,
+          "theta_e": 0.9,
+          "catch": 0.9643,
+          "fp": 0.0655
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.7,
+          "theta_e": 0.9,
+          "catch": 1.0,
+          "fp": 0.1164
+        }
+      ],
+      "configs_ranked": [
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.2143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.1071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.0357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        }
+      ]
+    },
+    "nli-shadow-v1-deberta-v3-base": {
+      "hf_repo": "MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli",
+      "backend": "torch",
+      "device": "cuda",
+      "n_nli_pairs": 3355,
+      "infer_seconds": 9.16,
+      "global_best": {
+        "k": 3,
+        "agg": "mean",
+        "guard": "max_entail",
+        "theta_c": 0.995,
+        "theta_e": 0.3,
+        "catch": 0.3929,
+        "fp": 0.0
+      },
+      "pareto": [
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "max_entail",
+          "theta_c": 0.995,
+          "theta_e": 0.3,
+          "catch": 0.3929,
+          "fp": 0.0
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.975,
+          "theta_e": 0.9,
+          "catch": 1.0,
+          "fp": 0.0036
+        }
+      ],
+      "configs_ranked": [
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.9,
+            "catch": 1.0,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.3,
+            "catch": 1.0,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.97,
+            "theta_e": 1.01,
+            "catch": 1.0,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.9,
+            "catch": 1.0,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.3,
+            "catch": 1.0,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.97,
+            "theta_e": 1.01,
+            "catch": 1.0,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.9,
+            "catch": 1.0,
+            "fp": 0.0436
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.7,
+            "theta_e": 0.9,
+            "catch": 1.0,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.8,
+            "theta_e": 0.3,
+            "catch": 1.0,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.7,
+            "theta_e": 1.01,
+            "catch": 1.0,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9643,
+            "fp": 0.0436
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9643,
+            "fp": 0.0436
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.9643,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 1.01,
+            "catch": 0.9643,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.9643,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 1.01,
+            "catch": 0.9643,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 1.01,
+            "catch": 0.9286,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.8929,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.8929,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        }
+      ]
+    },
+    "nli-shadow-v1-bart-large-mnli": {
+      "hf_repo": "facebook/bart-large-mnli",
+      "backend": "torch",
+      "device": "cuda",
+      "n_nli_pairs": 3355,
+      "infer_seconds": 17.41,
+      "global_best": {
+        "k": 3,
+        "agg": "mean",
+        "guard": "max_entail",
+        "theta_c": 0.94,
+        "theta_e": 0.3,
+        "catch": 0.7143,
+        "fp": 0.0
+      },
+      "pareto": [
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "max_entail",
+          "theta_c": 0.94,
+          "theta_e": 0.3,
+          "catch": 0.7143,
+          "fp": 0.0
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.998,
+          "theta_e": 0.3,
+          "catch": 0.75,
+          "fp": 0.0109
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "theta_c": 0.995,
+          "theta_e": 1.01,
+          "catch": 0.9286,
+          "fp": 0.0218
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "theta_c": 0.975,
+          "theta_e": 1.01,
+          "catch": 0.9643,
+          "fp": 0.0364
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "theta_c": 0.6,
+          "theta_e": 1.01,
+          "catch": 1.0,
+          "fp": 0.1418
+        }
+      ],
+      "configs_ranked": [
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.94,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.94,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.94,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.94,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.95,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.95,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.6786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.6786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.5357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 1.01,
+            "catch": 0.5357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 1.01,
+            "catch": 0.5357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 1.01,
+            "catch": 0.5357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 1.01,
+            "catch": 0.5357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 1.01,
+            "catch": 0.5357,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 1.01,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3214,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 1.01,
+            "catch": 0.2857,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.85,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.85,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        }
+      ]
+    },
+    "extra:nli-deberta-v3-small": {
+      "hf_repo": "cross-encoder/nli-deberta-v3-small",
+      "backend": "torch",
+      "device": "cuda",
+      "n_nli_pairs": 3355,
+      "infer_seconds": 4.99,
+      "global_best": {
+        "k": 1,
+        "agg": "top2",
+        "guard": "max_entail",
+        "theta_c": 0.3,
+        "theta_e": 0.3,
+        "catch": 0.0,
+        "fp": 0.0
+      },
+      "pareto": [
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "max_entail",
+          "theta_c": 0.3,
+          "theta_e": 0.3,
+          "catch": 0.0,
+          "fp": 0.0
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "theta_c": 0.998,
+          "theta_e": 1.01,
+          "catch": 0.8214,
+          "fp": 0.0036
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.995,
+          "theta_e": 0.95,
+          "catch": 0.9286,
+          "fp": 0.0109
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.99,
+          "theta_e": 0.3,
+          "catch": 0.9643,
+          "fp": 0.0291
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.99,
+          "theta_e": 0.95,
+          "catch": 1.0,
+          "fp": 0.04
+        }
+      ],
+      "configs_ranked": [
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.95,
+            "catch": 1.0,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 1.0,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 1.01,
+            "catch": 1.0,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.9643,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.95,
+            "catch": 0.9286,
+            "fp": 0.0218
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.95,
+            "catch": 0.9286,
+            "fp": 0.0255
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.9286,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.9286,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.96,
+            "theta_e": 0.3,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 1,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.95,
+            "theta_e": 1.01,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.9286,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.8929,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.8929,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.5,
+            "theta_e": 0.3,
+            "catch": 0.8571,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.8214,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.8214,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.8214,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.95,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.95,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.95,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.95,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.6,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.6,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.6,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.6,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.6,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.7,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.7,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.7,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.7,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0218
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0255
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0255
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.8,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.7,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.7,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.94,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0436
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0436
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0436
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.9,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0436
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.7,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0436
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.8,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.8,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.6,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.6,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.8,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.8,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.8,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.8,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.97,
+            "theta_e": 0.3,
+            "catch": 0.7143,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.6786,
+            "fp": 0.0255
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6786,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.6786,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.6429,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.6429,
+            "fp": 0.0327
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.5714,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0036
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4286,
+            "fp": 0.0145
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0073
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0073
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0073
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0182
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0364
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.9,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.04
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.8,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.95,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0473
+          },
+          "best_kind": "fp<=0.05"
+        }
+      ]
+    },
+    "extra:roberta-large-mnli": {
+      "hf_repo": "roberta-large-mnli",
+      "backend": "torch",
+      "device": "cuda",
+      "n_nli_pairs": 3355,
+      "infer_seconds": 14.24,
+      "global_best": {
+        "k": 2,
+        "agg": "max",
+        "guard": "max_entail",
+        "theta_c": 0.998,
+        "theta_e": 0.7,
+        "catch": 0.75,
+        "fp": 0.0
+      },
+      "pareto": [
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.998,
+          "theta_e": 0.7,
+          "catch": 0.75,
+          "fp": 0.0
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "theta_c": 0.95,
+          "theta_e": 0.9,
+          "catch": 1.0,
+          "fp": 0.0036
+        }
+      ],
+      "configs_ranked": [
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.7,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.7,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.7,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.7,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.7,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.7,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.4643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.4286,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3929,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        }
+      ]
+    },
+    "extra:deberta-large-mnli": {
+      "hf_repo": "microsoft/deberta-large-mnli",
+      "backend": "torch",
+      "device": "cuda",
+      "n_nli_pairs": 3355,
+      "infer_seconds": 24.53,
+      "global_best": {
+        "k": 3,
+        "agg": "margin",
+        "guard": "max_entail",
+        "theta_c": 0.995,
+        "theta_e": 1.01,
+        "catch": 1.0,
+        "fp": 0.0
+      },
+      "pareto": [
+        {
+          "k": 3,
+          "agg": "margin",
+          "guard": "max_entail",
+          "theta_c": 0.995,
+          "theta_e": 1.01,
+          "catch": 1.0,
+          "fp": 0.0
+        }
+      ],
+      "configs_ranked": [
+        {
+          "k": 3,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 1.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 1.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.9,
+            "catch": 0.9643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.9643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.9643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.5,
+            "catch": 0.9643,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 1.01,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.9,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.9,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.75,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 1.01,
+            "catch": 0.7143,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.98,
+            "theta_e": 0.3,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.975,
+            "theta_e": 0.3,
+            "catch": 0.6429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "max_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "mean",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "mean",
+            "guard": "paired_entail",
+            "theta_c": 0.99,
+            "theta_e": 0.3,
+            "catch": 0.6071,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.5,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.3571,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "max",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "max",
+            "guard": "paired_entail",
+            "theta_c": 0.999,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "meanTop3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "meanTop3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.25,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.1786,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 1.01,
+            "catch": 0.1429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "margin",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "margin",
+            "guard": "max_entail",
+            "theta_c": 0.999,
+            "theta_e": 1.01,
+            "catch": 0.1429,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top2",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top2",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 1,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 1,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 2,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 2,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.3,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 3,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 3,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 4,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 4,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.985,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 6,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 6,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.995,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 8,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 8,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "max_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "max_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        },
+        {
+          "k": 12,
+          "agg": "top3",
+          "guard": "paired_entail",
+          "best": {
+            "k": 12,
+            "agg": "top3",
+            "guard": "paired_entail",
+            "theta_c": 0.998,
+            "theta_e": 0.3,
+            "catch": 0.0,
+            "fp": 0.0
+          },
+          "best_kind": "fp=0"
+        }
+      ]
+    }
+  }
+}
\ No newline at end of file
diff --git a/docs/TICKETS.md b/docs/TICKETS.md
index f71a5e2..39c5910 100644
--- a/docs/TICKETS.md
+++ b/docs/TICKETS.md
@@ -104,7 +104,7 @@ Newest first. Update on every open/close.
 | #000052  | Relevance + coherence meta-cognition (answer-*shape* signals) | in progress — **§3.1 `diagnose_coherence` landed** (lexical, no model: `circular` / `phrase_component_reuse` / `vacuous`; in `arborist/qa/inspect.py`, surfaced via `inspect_cache_key` + `arborist inspect` `· incoherent: <kind>`; 9 tests; demote-policy hook deliberately not wired — advisory only). Joins the `diagnose_deflection` / `diagnose_metaphor_deflection` / `diagnose_title_relevance` / soft-preflight family of read-only, demote-only, never-in-proof-path sidecars; `phrase_component_reuse` catches the motivating field case (a subject quoting a phrase, a predicate reusing one of that phrase's own tokens as a bare `the <token>` referent). **Still open: (2) `diagnose_relevance`** — semantic (not just lexical) "aboutness": does the answer address the question; is each claim about its cited source? Today's checks (subject-anchor token overlap, stemmed title-stem overlap) are *lexical* and a token collision defeats them — a small *aboutness/reranker* model (NOT NLI — entailment ≠ topicality) under #000049 §7's discipline cage verbatim (demotion-only, hash-pinned, `relevance_model_version`→`governance_policy_hash` iff it touches `audit_mode`, shadow-first, `[…]` extra, the §7 #20 haystack lesson — never over the whole context); gated on evidence, travels with #000049's model question. Motivating field case (2026-05-12, fox): the `claim_lattice` query that returned *"the phrase 'Zionist entity' is sometimes used as the entity, referring to the State of Israel"* at `EVIDENCE-WARRANTED-PARTIAL 2/3` — incoherent + token-collision recombination that NLI can't catch (returns *neutral*, not *contradiction*) and both lexical relevance checks waved through. Flags an upstream retrieval ticket (polysemy / title-token-soup) as the root-cause fix, not scoped here. #000049 sibling | 2026-05-12 | —         |
 | #000051  | Federated vecpack distribution (gossip the embedding backfill) | open · awaiting go/no-go · doc-only scaffold. Makes `chunk_vecs` a distributable artifact: backfill once on any CPU box (cloud / Prometheus-Σ sweep — #000037 §3.1), publish a **vecpack** `(shard_root, vec_backend_version, [(leaf_hash, embedding_blob)…])` over the mesh wire layer, every peer pulls + bulk-loads (sub-ms/chunk on the receiver — the laptop never runs the transformer). Keyed on `leaf_hash` (portable) not `chunk_id` (shard-local). Vecpacks are **soft data** — embeddings are `UNGROUNDED`, never proof path — so a cheap structural sanity gate (chunk exists locally w/ matching leaf_hash, right blob length for (dim,quant), finite norm, backend_version matches) suffices, no Merkle-proof-grade verification needed. Supplies #000050's prereq #1 ("a vecpack exists & is imported on the bench box", not "fox embedded the corpus locally"). GPU producer (the fast path): bge-small-en-v1.5 batched on a CUDA box (4090) ≈ 10³–10⁴ chunks/s → full 6.24M-chunk corpus in *minutes*, not days — drop a CUDA `Embedder` into `default_embedder()`; CUDA stack lives only on the producer box, never in arborist's `python+sqlite3` core. The mechanism behind whitepaper §1's "the embedding pass runs off the device". #000039 / #000050 sibling | 2026-05-12 | —         |
 | #000050  | Vec RRF hybrid fusion (#000039 Phase 2) | open · awaiting go/no-go · doc-only scaffold; design in #000039 §4.2 (RRF) + §8 (the gate). Wire `VecBackend` as a 5th retrieval route in `query.py`, RRF-merged (route provenance carried) with the 4 FTS5 routes; UNGROUNDED hits, additive not replacement. Phase-2 sub-items now explicit: **accept-path-5** in `_filter_by_title_relevance` (low-title-overlap vec hits survive only via a stronger span-level warrant, never similarity-score alone — else the title gate drops exactly the semantic candidates vec exists for & the bench shows no lift); **six** vec config fields fold into `governance_policy_hash` (recipe-named quant `int8sym`) **+ a cache-write guard** blocking `providence_cache` persistence for vec/hybrid runs until that's wired; **run-DAG records the vec stage** (backend version, six fields, top_k, query-embedding hash, candidate chunk_ids+distances). **Gated** on (a) a corpus backfill **distributed via #000051** AND (b) a **four-condition** recall bench (A FTS5-only / B vec-only / C RRF hybrid / D candidate-union-no-RRF) clearing the 5pp floor incl. C-beats-D, on semantic-allusion + curated + **adversarial-semantic-neighbor** fixtures (else park, vec stays opt-in `--backend vec`; if C≈D ship the union, drop RRF). #000039 follow-up | 2026-05-12 | —         |
-| #000049  | Attribution-aware grounding check (the recombination boundary) | open · boundary accepted · production no-go · shadow-path approved (de novo review 2026-05-13 — ticket §7) · doc-only; the home for #000048's deferred §2.3 — closing the 2 recombination over-grounds in `falsification-hard` (hard-003 Mercury / hard-005 Einstein) needs an attribution / dependency-parse or mini-NLI check, which is *not lexical* (#000048 §5). Discipline question answered: a small fixed purpose-built NLI/entailment *model* may influence `audit_mode` only as an opt-in, hash-pinned, governance-hashed, **demotion-only contradiction veto** after shadow-mode evidence (never promotes — `MODEL_ASSISTED_DEMOTION`, never `MODEL_ASSISTED_PROMOTION`). Production verifier unchanged; `falsification-hard` stays 10/12 as an honest boundary marker. Roadmap: Phase 0 (this amendment) → Phase 1 (shadow design: NLI manifest, fetch/verify, `nli_pair@v1` canonicalization, recombination-risk trigger) → Phase 2 (bench-only shadow impl, `[nli]` extra, `make fetch-nli`) → Phase 3 (demotion-only runtime, gated) → Phase 4 (mesh blob sync); §7 #12 six-condition bench gate required before Phases 2–4; if NLI ever affects `audit_mode`, `nli_policy_hash` folds into `governance_policy_hash`. **Phase-2 candidate bench done 2026-05-12** (`~/git/arborist-nli-bench/`, commits `829f9a4` + `a1cb28d`; ticket §7 #18): checkpoint-agnostic harness runs the §7 #5 clause-level algorithm over 28 synth recombination cases (incl. the 2 fixtures + harder shapes) + 26 legit cases (true summaries + near-miss decoys). 4 working candidates; `nli-MiniLM2-L6-H768` (82M, 45ms p50 CPU), `deberta-v3-base-mnli-fever-anli` (184M, 223ms), `bart-large-mnli` (407M, 259ms) all 28/28 catch · 0/26 FP with the standard θe=0.9 entailment guard; `cross-encoder/nli-deberta-v3-base` 27/28; deberta-large repo-id TODO. **Key finding: the §7 #5 two-threshold rule is load-bearing** — 3 of 4 candidates argmax-contradict 1/26 legit cases on the *wrong* source clause (competing-superlative confusion, e.g. "largest hot desert" vs "largest desert overall"); the entailment guard filters every one because another clause restates the claim → 0% guarded FP vs ~4% single-threshold. Picture: recombination is *easy* for any modern NLI checkpoint — differentiator is cost/robustness, MiniLM is the cost-pick, bart-large the threshold-robust pick. **Phase-2 shadow scaffold landed in arborist 2026-05-12** (ticket §7 #19): `arborist/qa/nli/` (manifest pins MiniLM @ a fixed HF revision + θc 0.5/θe 0.9 + 2 alternates; `ShadowNLI`/`shadow_check` lazy-imports `transformers`+`torch` behind a new `[nli]` extra, degrades to `available=False` when absent — SHADOW ONLY, never an `audit_mode` input, manifest not yet in `governance_policy_hash` per §7 #2) + `bench/scripts/nli_shadow_sweep.py` + `make bootstrap-nli` / `make bench-nli-shadow` + 16 tests. Synthetic sweep (116 records): 28/28 recombination demoted, 0/26 FP on legit summaries, 0/9 fires on already-`STRICT_SPAN`. **First bench-qa-traffic sweep** (§7 #20 — `ARBORIST_NLI_SHADOW=1 make bench-qa-smoke`, 15 cells; `query.py` surfaces verifier-input text gated off-by-default, `qa_sweep.py` carries it, `nli_shadow_sweep.py` reads it): the *naive* "NLI on every context clause" scaffold has a **~30% would-demote rate on STRICT answers** — a haystack/multiple-comparisons artifact (real Wikipedia contexts → 100–336 clauses; `max`-over-all almost always hits a tangential "contradiction"). Candidate-clause restriction (§7 #21 — NLI runs on the top-6 source clauses by content-token overlap, `max_candidate_clauses=6`) + speedup (§7 #22 — batched forwards, `ARBORIST_NLI_DEVICE` cuda auto-detect, ONNX-int8 export via `make export-nli-onnx`: torch-cpu-batch1 ~120ms/pair → onnx-int8-cpu-batched ~32ms/pair, seconds on a 4090; `optimum[onnxruntime]` added to `[nli]`; 24 tests) landed. **Verdict — flipped** (§7 #22 said "fails the gate" for the *default* config k=6/θc=0.5/θe=0.9 [tuned on the clean synthetic set]; §7 #23's `{model × candidate-cap k × aggregation × θc × θe}` grid sweep [`bench/scripts/nli_shadow_grid.py`; ~10s on the 4090 for 4 models] finds **clean passing configs**): on the 89 real STRICT cells (n=1 `ARBORIST_NLI_SHADOW=1 make bench-qa`; the run also surfaced + fixed a lone-surrogate bug `qa_sweep` now scrubs), `deberta-base-184M / k=2 / agg=max / θc=0.99 / θe=0.9` catches **27/28 synthetic recombinations** (incl. both `5f-fal-hard` fixtures) with **0/89 STRICT false positives**; MiniLM-82M passes too (24/28 · 0/89); bart-large-407M is *worse* at fp=0 (20/28). Model science: 184M > 82M > 407M for fp=0 recombination recall (bigger isn't monotonically better — bart's contradiction scores are more spread, need a lower θc that costs FP); int8-ONNX costs ≈1 catch vs fp32. **So the lexical-candidate NLI veto clears the §7 #12 gate** at ~86–96% recombination recall / ≈0 false-demote. Caveats before final: FP side is n=1 (89 cells — a `BENCH_QA_N=3` ~250-cell run in flight must confirm fp stays 0); recall is on the synthetic set; flipping to a runtime demotion-only veto is a fox-decides (then `nli_policy_hash` = model+k+agg+θc+θe folds into `governance_policy_hash` per §7 #2). Manifest active defaults stay k=6/θc=0.5 pending the n=3 confirm; the recommended operating point (deberta-base, k=2, agg=max, θc=0.99, θe=0.9) is documented in the manifest. Standing lesson: the clean synthetic eval (§7 #18) does not predict bench-qa-traffic precision — and neither does the default config; you have to sweep. Production verifier unchanged; `falsification-hard` stays 10/12. #000048 follow-up | 2026-05-12 | —         |
+| #000049  | Attribution-aware grounding check (the recombination boundary) | open · boundary accepted · production no-go · shadow-path approved (de novo review 2026-05-13 — ticket §7) · doc-only; the home for #000048's deferred §2.3 — closing the 2 recombination over-grounds in `falsification-hard` (hard-003 Mercury / hard-005 Einstein) needs an attribution / dependency-parse or mini-NLI check, which is *not lexical* (#000048 §5). Discipline question answered: a small fixed purpose-built NLI/entailment *model* may influence `audit_mode` only as an opt-in, hash-pinned, governance-hashed, **demotion-only contradiction veto** after shadow-mode evidence (never promotes — `MODEL_ASSISTED_DEMOTION`, never `MODEL_ASSISTED_PROMOTION`). Production verifier unchanged; `falsification-hard` stays 10/12 as an honest boundary marker. Roadmap: Phase 0 (this amendment) → Phase 1 (shadow design: NLI manifest, fetch/verify, `nli_pair@v1` canonicalization, recombination-risk trigger) → Phase 2 (bench-only shadow impl, `[nli]` extra, `make fetch-nli`) → Phase 3 (demotion-only runtime, gated) → Phase 4 (mesh blob sync); §7 #12 six-condition bench gate required before Phases 2–4; if NLI ever affects `audit_mode`, `nli_policy_hash` folds into `governance_policy_hash`. **Phase-2 candidate bench done 2026-05-12** (`~/git/arborist-nli-bench/`, commits `829f9a4` + `a1cb28d`; ticket §7 #18): checkpoint-agnostic harness runs the §7 #5 clause-level algorithm over 28 synth recombination cases (incl. the 2 fixtures + harder shapes) + 26 legit cases (true summaries + near-miss decoys). 4 working candidates; `nli-MiniLM2-L6-H768` (82M, 45ms p50 CPU), `deberta-v3-base-mnli-fever-anli` (184M, 223ms), `bart-large-mnli` (407M, 259ms) all 28/28 catch · 0/26 FP with the standard θe=0.9 entailment guard; `cross-encoder/nli-deberta-v3-base` 27/28; deberta-large repo-id TODO. **Key finding: the §7 #5 two-threshold rule is load-bearing** — 3 of 4 candidates argmax-contradict 1/26 legit cases on the *wrong* source clause (competing-superlative confusion, e.g. "largest hot desert" vs "largest desert overall"); the entailment guard filters every one because another clause restates the claim → 0% guarded FP vs ~4% single-threshold. Picture: recombination is *easy* for any modern NLI checkpoint — differentiator is cost/robustness, MiniLM is the cost-pick, bart-large the threshold-robust pick. **Phase-2 shadow scaffold landed in arborist 2026-05-12** (ticket §7 #19): `arborist/qa/nli/` (manifest pins MiniLM @ a fixed HF revision + θc 0.5/θe 0.9 + 2 alternates; `ShadowNLI`/`shadow_check` lazy-imports `transformers`+`torch` behind a new `[nli]` extra, degrades to `available=False` when absent — SHADOW ONLY, never an `audit_mode` input, manifest not yet in `governance_policy_hash` per §7 #2) + `bench/scripts/nli_shadow_sweep.py` + `make bootstrap-nli` / `make bench-nli-shadow` + 16 tests. Synthetic sweep (116 records): 28/28 recombination demoted, 0/26 FP on legit summaries, 0/9 fires on already-`STRICT_SPAN`. **First bench-qa-traffic sweep** (§7 #20 — `ARBORIST_NLI_SHADOW=1 make bench-qa-smoke`, 15 cells; `query.py` surfaces verifier-input text gated off-by-default, `qa_sweep.py` carries it, `nli_shadow_sweep.py` reads it): the *naive* "NLI on every context clause" scaffold has a **~30% would-demote rate on STRICT answers** — a haystack/multiple-comparisons artifact (real Wikipedia contexts → 100–336 clauses; `max`-over-all almost always hits a tangential "contradiction"). Candidate-clause restriction (§7 #21 — NLI runs on the top-6 source clauses by content-token overlap, `max_candidate_clauses=6`) + speedup (§7 #22 — batched forwards, `ARBORIST_NLI_DEVICE` cuda auto-detect, ONNX-int8 export via `make export-nli-onnx`: torch-cpu-batch1 ~120ms/pair → onnx-int8-cpu-batched ~32ms/pair, seconds on a 4090; `optimum[onnxruntime]` added to `[nli]`; 24 tests) landed. **Verdict moved twice** (§7 #22→#23→#24; `bench/scripts/nli_shadow_grid.py` — `{model × k × agg × guard × θc × θe}` sweep, ~3.5min for 7 models on the 4090): §7 #22's "fails the gate" was a *default-config* artifact (k=6/θc=0.5/θe=0.9); §7 #23's "deberta-base k=2/θc=0.99 → 27/28 · 0/89 passes" was a *small-FP-sample* artifact (it collapses to 11/28 on the n=3 275-STRICT sample, which forces θc up to ~0.995); the **n=3-confirmed truth** (§7 #24, the "no stone unturned" mega-grid — 7 models incl. 4 extra xsmall→large, the new `margin` aggregation = max over clauses of `p_contra − p_entail`): **`microsoft/deberta-large-mnli` / k=3 / agg=`margin` / θc=0.995 → catches all 28 synthetic recombinations (incl. both `5f-fal-hard` fixtures) + 8/12 `falsification-hard`, with 0 false positives on 275 real STRICT answers and 0 on the 26 synthetic legit summaries** — a passing config at proper n. Findings: `margin` is the right score-shape (single threshold, folds the entailment guard in); the *specific checkpoint* matters more than parameter count — `deberta-large-mnli` wins clean, `deberta-base` collapses, `roberta-large`/`bart-large` (similar size) only reach ~0.71–0.75, no "bigger is better" law; int8-ONNX costs ≈1 catch vs fp32. Caveats before runtime promotion: still SHADOW; the 28/28 recall is a 28-case denominator (a bench-qa-derived recombination set is the next check); θc=0.995/0-FP is "on the largest STRICT sample we have (275 cells)" not "0 FP period" (a bigger STRICT sample is the other next check); flipping to a runtime demotion-only veto is fox+dav1d-decides (then `nli_policy_hash` = model+k+agg+θc folds into `governance_policy_hash` per §7 #2); deberta-large is ~400M (GPU-fast, slow on CPU). Manifest active defaults stay k=6/θc=0.5; the `recommended_operating_point` (deberta-large-mnli / k=3 / margin / θc=0.995) is documented in the manifest. Standing lesson, sharpened twice: the clean synthetic eval doesn't predict bench-qa precision (§7 #18→#20), the default config doesn't predict the best config (§7 #22→#23), and a small FP-side sample doesn't predict the large-sample FP rate (§7 #23→#24) — every gate number is provisional until the denominators are big enough, and the sweep has to be wide enough to include the config that survives them. Production verifier unchanged; `falsification-hard` stays 10/12. #000048 follow-up | 2026-05-12 | —         |
 | #000048  | Verifier upgrade — recombination-aware grounding + clause segmentation | **closed · 2026-05-12** — steps 2.1 + 2.4 landed 2026-05-11 (12 of 16 residual items: 4 HYBRID_ENTITY over-grounds + 8 Formulate mis-segments → `formulate-hard` 12/12, `falsification-hard` 10/12; each bench-gated, no STRICT-rate regression — 2.1's gate fired on 0 QA answers, 2.4's segmenter touched 7 of 450 lattice cells both verdict changes correct). Step 2.2 (single-clause-containment paraphrase check) attempted + reverted — catches the 2 recombination fixtures but also rejects legit cross-sentence summaries with no threshold separating the two; recombination-vs-summary isn't lexical (§5 "What we learned"). The attribution-aware path moved to **#000049** (fox 2026-05-12). 2 live-pack `expected_reason` updated HYBRID_ENTITY→UNGROUNDED; 12+ tests; `make bench-5f-falsification-hard` / `bench-5f-formulate-hard` / `bench-fork-baseline-hard`. #000046 follow-up; #000047 closed | 2026-05-11 | —         |
 | #000047  | ForkScore `_delta_*` aggregator (mean vs max vs sum) | **closed · 2026-05-11** — Option D: `WeightSet.delta_aggregator` ∈ {`mean`,`max`,`sum`} (default `mean` unchanged → no `ESTIMATOR_VERSION` bump), `fork_score._delta_5{s,t,f}` dispatch via `_aggregate`, recorded in `ScoredFork.weights`, per-sub `HARD_REGRESSION_FLOOR` flags aggregator-independent; bench data behind keeping `mean` in `5f-threshold-calibration-2026-05-11.md` §5; 8+1 tests. #000012-revision / #000025 §10.14 follow-up | 2026-05-11 | —         |
 | #000046  | Harder 5S/5T/5F fixture tier (below-ceiling baselines) | **closed · 2026-05-11** — Phase 1 `falsification-hard-v1.jsonl` (12 near-misses) + Phase 2 `formulate-hard-v1.jsonl` (12 mis-segments, rate 4/12) + Phase 3 `verify_quotes` paraphrase numeric-agreement gate (`_numeric_signature`; demotes a token-covering span asserting a digit-number the source lacks modulo thousands-comma) → falsification-hard rate 4/12 → 6/12 on a real change; bench-gated (`make bench-qa` n=3×75×3 before/after — no STRICT-rate regression on legit answers; only gate-caused QA shift was correctly demoting a fictional-year claim STRICT→HYBRID); `fork_score` γ·Δ5f went positive on it. Headroom now down to 2 falsification-hard over-grounds (#000048 step 2.1 closed the 4 entity over-grounds; step 2.4 closed the 8 Formulate mis-segments → that pack 12/12; step 2.2 attempted + reverted — the last 2 recombination fixtures need an attribution-aware verifier, now tracked as **#000049**, and stand as documented residue). `make bench-5f-falsification-hard` / `bench-5f-formulate-hard` / `bench-fork-baseline-hard`; 7+ tests. #000025 §10.14 follow-up; #000047 closed; #000048 closed | 2026-05-11 | —         |
diff --git a/docs/tickets/ticket-000049-attribution-aware-grounding-check.md b/docs/tickets/ticket-000049-attribution-aware-grounding-check.md
index 5d224d1..c8f5f49 100644
--- a/docs/tickets/ticket-000049-attribution-aware-grounding-check.md
+++ b/docs/tickets/ticket-000049-attribution-aware-grounding-check.md
@@ -19,26 +19,41 @@ lexical verifier actually matched and/or a deterministic recombination-risk
 trigger; do NOT enable runtime NLI demotion on the current scaffold.
 Candidate-clause restriction (§7 #21) + speedup (§7 #22 — batched
 forwards, device auto-detect, ONNX-int8 export, ~4× on CPU / seconds
-on a 4090) landed; a grid sweep over `{model × k × agg × θc × θe}`
-(§7 #23, `bench/scripts/nli_shadow_grid.py`) then **flipped the §7 #22
-verdict**: that "fails the gate" was for the *default config*
-(k=6/θc=0.5/θe=0.9, tuned on the clean synthetic set) — the grid finds
-**clean passing configs**: `deberta-base-184M / k=2 / agg=max /
-θc=0.99 / θe=0.9` catches **27 of 28 synthetic recombinations** (incl.
-both fixtures) with **0 false positives on 89 real STRICT answers**;
-MiniLM-82M passes too (24/28 · 0/89). Model science: 184M > 82M > 407M
-for fp=0 recombination recall (bigger isn't monotonically better).
-Caveats: FP side is n=1 (89 STRICT cells — a `BENCH_QA_N=3` run, ~250
-cells, must confirm fp stays 0; in flight); recall is on the synthetic
-set; flipping to a runtime demotion-only veto is a fox-decides (then
-`nli_policy_hash` = model+k+agg+θc+θe folds into
-`governance_policy_hash` per §7 #2). Manifest active defaults stay
-k=6/θc=0.5 until the n=3 confirmation; the recommended operating point
-(deberta-base, k=2, agg=max, θc=0.99, θe=0.9) is documented in the
-manifest. Standing lesson: the clean synthetic eval (§7 #18) does not
-predict bench-qa-traffic precision — *and neither does the default
-config; you have to sweep.* Production verifier unchanged;
-`falsification-hard` stays 10/12.
+on a 4090) + a `{model × k × agg × guard × θc × θe}` grid sweep
+(§7 #23–#24, `bench/scripts/nli_shadow_grid.py`) landed; the verdict
+moved **twice**: §7 #22's "fails the gate" was a *default-config*
+artifact (k=6/θc=0.5/θe=0.9); §7 #23's "deberta-base k=2/θc=0.99 →
+27/28 · 0/89 passes" was a *small-FP-sample* artifact (it collapses
+to 11/28 on the n=3 275-STRICT sample, which forces θc up to ~0.995);
+the n=3-confirmed truth (§7 #24, the "no stone unturned" mega-grid —
+7 models incl. 4 extra xsmall→large, the new `margin` aggregation =
+max over clauses of `p_contra − p_entail`): **`microsoft/deberta-large-mnli`
+/ k=3 / agg=`margin` / θc=0.995 → catches all 28 synthetic
+recombinations (incl. both `5f-fal-hard` fixtures) + 8/12 of the
+`falsification-hard` pack, with 0 false positives on 275 real STRICT
+answers and 0 on the 26 synthetic legit summaries** — a passing config
+at proper n. Findings: (1) `margin` is the right score-shape (single
+threshold, folds the entailment guard in); (2) the *specific
+checkpoint* matters more than parameter count — `microsoft/deberta-large-mnli`
+wins clean, `deberta-base` collapses, `roberta-large`/`bart-large`
+(similar size) only reach ~0.71–0.75, there's no "bigger is better"
+law. Caveats: still SHADOW; the 28/28 recall is a 28-case denominator
+(100%-of-28 ≠ 100%-in-general — a bench-qa-derived recombination set
+is the next check), and θc=0.995/0 FP is "on the largest STRICT sample
+we have (275 cells)" not "0 FP, period" — a bigger STRICT sample
+should be the other next check before runtime promotion; flipping to
+a runtime demotion-only veto is fox+dav1d-decides (then `nli_policy_hash`
+= model+k+agg+θc folds into `governance_policy_hash` per §7 #2);
+deberta-large is ~400M (GPU-fast, slow on CPU). Manifest active
+defaults stay k=6/θc=0.5; the `recommended_operating_point`
+(deberta-large-mnli / k=3 / margin / θc=0.995) is documented in the
+manifest. Standing lesson, sharpened twice: the clean synthetic eval
+doesn't predict bench-qa precision (§7 #18→#20), the default config
+doesn't predict the best config (§7 #22→#23), **and a small FP-side
+sample doesn't predict the large-sample FP rate (§7 #23→#24)** — every
+gate number is provisional until the denominators are big enough, and
+the sweep has to be wide enough to include the config that survives
+them. Production verifier unchanged; `falsification-hard` stays 10/12.
 **Opened:** 2026-05-12
 **Scope:** Decide whether — and if so how — to add a verifier check
 that catches a *recombination*: a claim whose content tokens are all
@@ -983,3 +998,87 @@ demotion-only veto is a fox-decides (`MODEL_ASSISTED_DEMOTION`, and
 the recommended-but-not-yet-default operating point, pending the n=3
 confirmation. Production verifier unchanged; `falsification-hard`
 stays 10/12.
+
+**24. The n=3 confirmation — §7 #23 was a small-sample artifact; the
+no-stone-unturned mega-grid found the config that *does* survive
+(2026-05-12).** Ran `ARBORIST_NLI_SHADOW=1 make bench-qa BENCH_QA_N=3`
+→ 675 cells, **275 STRICT** (vs the 89 from n=1 — 3× the FP-side
+denominator). Re-ran the grid with the expanded sweep
+(`nli_shadow_grid.py` now: 7 aggregations incl. `margin` [= max over
+clauses of `p_contra − p_entail`, a single score folding the
+entailment guard in] + `paired_entail` guard variant; θc grid to
+0.999; `--extra-models`) over all manifest models **+ 4 extra
+checkpoints** spanning xsmall→large (`microsoft/deberta-large-mnli`,
+`roberta-large-mnli`, `cross-encoder/nli-deberta-v3-small`,
+`MoritzLaurer/DeBERTa-v3-xsmall-mnli-fever-anli`), against the
+synthetic-28 recombination set (recall) vs the 275 real STRICT cells
+(FP). 3355 NLI pairs/model, ~3.5 min total on the 4090. Result
+(`bench/results/nli-shadow-grid-n3-synth-vs-realstrict.json`):
+
+| NLI model (size) | best `fp=0` config | recombination catch | real-STRICT FP (n=3, 275 cells) |
+|---|---|---|---|
+| **`microsoft/deberta-large-mnli` (~400M)** | **k=3, agg=`margin`, θc=0.995** | **28/28 = 1.000** | **0/275** |
+| `roberta-large-mnli` (~355M) | k=2, agg=max, θc=0.998 | 21/28 = 0.750 | 0/275 |
+| `bart-large-mnli` (~407M) | k=3, agg=mean, θc=0.94 | 20/28 = 0.714 | 0/275 |
+| MiniLM-82M | k=4, agg=mean, θc=0.96 | 14/28 = 0.500 | 0/275 |
+| `deberta-base-184M` *(the §7 #23 hero)* | k=3, agg=mean, θc=0.995 | **11/28 = 0.393** | 0/275 |
+| `nli-deberta-v3-small` (~140M) | — | 0/28 | 0/275 |
+
+**The §7 #23 "deberta-base k=2/θc=0.99 → 27/28 · 0/89" does NOT
+survive n=3.** The 89-STRICT n=1 sample under-counted the spurious-
+contradiction tail; the 275-cell sample surfaces ~14% more of it,
+forcing θc up to ~0.995, and at θc=0.995 deberta-base only catches
+11/28 recombinations. So §7 #23's "the lexical-candidate veto passes"
+was over-optimistic by exactly the amount §7 #23's own caveat warned
+about. **However** — the *broader* sweep (the "no stone unturned"
+that this run was) found the config that *does* survive at n=3:
+**`microsoft/deberta-large-mnli` / k=3 / agg=`margin` / θc=0.995 →
+catches all 28 synthetic recombinations (incl. both `5f-fal-hard`
+fixtures, margins 0.997/0.998) + 8/12 of the `falsification-hard`
+pack, with 0 false positives on 275 real STRICT answers and 0 on the
+26 synthetic legit summaries.** A passing config at proper n.
+
+Two findings from the mega-grid:
+- **The `margin` aggregation is the right score-shape.** `margin =
+  max_clause(p_contra − p_entail)` collapses the two-threshold rule
+  (`p_contra ≥ θc ∧ p_entail < θe`) into a *single* threshold and is
+  what lets the strong model separate cleanly at n=3 — every other
+  aggregation needs the more fragile two-threshold dance.
+- **The *specific checkpoint* matters more than parameter count.**
+  `microsoft/deberta-large-mnli` (a plain MNLI fine-tune, ~400M) is
+  the clear winner; `MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli`
+  (similar size) won't even load under transformers 5.x;
+  `deberta-base-184M` (the n=1 hero) collapses at n=3;
+  `roberta-large-mnli` / `bart-large-mnli` (similar size to the
+  winner) only reach ~0.71-0.75. There is no "bigger is better" law —
+  you have to sweep the actual checkpoints.
+
+**Revised verdict.** The lexical-candidate NLI veto **can clear the
+§7 #12 gate at proper n** — but only with the right checkpoint
+(`microsoft/deberta-large-mnli`) + the right score-shape (`margin`) +
+a high θc (~0.995), and at "100% of the 28 synthetic recombinations"
+recall (which is a 28-case denominator — 100%-of-28 ≠ 100%-in-general;
+a bench-qa-derived recombination set would be more load-bearing). The
+honest line for dav1d: *the §7 #22 "fails" was a default-config
+artifact; the §7 #23 "passes" was a small-FP-sample artifact; the
+n=3-confirmed truth is `deberta-large-mnli + margin + k=3 + θc=0.995`
+passes — 28/28 synthetic recombination · 0/275 real STRICT — but the
+margin (θc=0.995, a 28-case recall denominator) is thin enough that a
+bigger STRICT sample and a bigger recombination set should be the next
+checks before runtime promotion.* Caveats unchanged: still SHADOW;
+flipping to runtime demotion-only is fox+dav1d-decides; `nli_policy_hash`
+(model + k + agg + θc) folds into `governance_policy_hash` at that
+point; deberta-large is ~400M (GPU-fast, slow on CPU — and ONNX-int8
+would cost a catch or two). The manifest's `recommended_operating_point`
+is updated to this config (still not the active default). Production
+verifier unchanged; `falsification-hard` stays 10/12.
+
+*Meta-lesson, sharpened twice now:* the clean synthetic eval doesn't
+predict bench-qa precision (§7 #18→#20), the default config doesn't
+predict the best config (§7 #22→#23), **and a small FP-side sample
+doesn't predict the large-sample FP rate (§7 #23→#24).** Every gate
+number is provisional until the denominators are big enough — and the
+sweep has to be wide enough to include the config that survives them.
+The 4090 is what makes that affordable: this whole §7 #24 run — 7
+models × the full {k × agg × guard × θc × θe} grid × 303 records — was
+~3.5 min.