feat(#000057): stronger code judge — resolve HYBRID with verified quote + on-topic

The code judge bailed to JUDGE_ERROR on 40% of in-corpus answers: HYBRID
(partial grounding) with low NLI entail, where the entity-grounding
rescue needs ZERO unsourced specifics. A single extra proper noun
('Emperor Honorius', 'Alexander Molossus' — an alias/paraphrase) blocked
rescue even with verbatim quotes verified and the answer correct.

New HYBRID resolution tier: rescue to CORRECT_GROUNDED when the verifier
confirmed >=1 verbatim quote, the subject anchor is in gold (on-topic),
there is NO unsourced NUMERIC specific (wrong dates/counts stay residue),
and NLI isn't strongly contradicting. Unsourced proper nouns are treated
as aliases/paraphrase; unsourced numerics (the real factual-error class)
keep the answer as JUDGE_ERROR. Validated on the 12 real residue cases:
9 -> CORRECT (all genuinely right), 3 stay residue (unsourced numerics).
JUDGE_ERROR 40% -> ~10%. self-test 4/4; 2 new tier tests; suite 2549.

bench/judge_code.py

@@ -653,6 +653,35 @@ def judge(question: str, answer: str, gold_source: str) -> Verdict:
                       f"specifics in gold + subject anchor "
                       f"{subj_anchor!r} in gold",
                       trace)
+        # Relaxed entity-grounding rescue (2026-05-21). Requiring ZERO
+        # unsourced specifics is too brittle: a single extra proper noun
+        # ("Emperor Honorius", "Alexander Molossus" — an alias or a
+        # paraphrased adjacent fact) blocks rescue even when the verifier
+        # confirmed verbatim quotes and the answer is correct. The risky
+        # unsourced class is NUMERIC (a wrong date/count is a real factual
+        # error); unsourced proper nouns are usually aliases/paraphrase.
+        # So rescue a HYBRID to CG when: (a) the verifier confirmed >=1
+        # verbatim quote in gold (real grounding), (b) subject anchor in
+        # gold (on-topic), (c) NO unsourced NUMERIC specific (dates/counts
+        # all grounded), and (d) NLI is not strongly contradicting. Wrong-
+        # number answers (unsourced numeric) and contradicted answers stay
+        # as JUDGE_ERROR residue.
+        n_verified = v.get("n_verified", 0)
+        unsourced_numeric = [s for s in unsourced
+                             if _NUMERIC_SPECIFIC_RE.search(s)]
+        not_contra = (not nli_avail) or nli.max_contradiction < theta_contra
+        trace["hybrid_n_verified"] = n_verified
+        trace["hybrid_unsourced_numeric"] = unsourced_numeric[:10]
+        if (subj_in_gold and n_verified >= 1 and all_specs
+                and not unsourced_numeric and not_contra):
+            trace["rules_fired"].append("hybrid+verified_quote_on_topic")
+            return _v("CORRECT_GROUNDED",
+                      f"verifier HYBRID via {method} + {n_verified} "
+                      f"verbatim quote(s) verified + subject anchor "
+                      f"{subj_anchor!r} in gold + no unsourced numeric "
+                      f"specific + not NLI-contradicted "
+                      f"(unsourced proper-nouns treated as aliases)",
+                      trace)
         return _v("JUDGE_ERROR",
                   f"code judge ambiguous: HYBRID via {method} without "
                   f"NLI entailment corroboration or entity-grounding — "

tests/test_judge_code.py

@@ -237,3 +237,39 @@ def test_judge_handles_nli_unavailable(monkeypatch):
         "This article is about thermodynamics.",
     )
     assert v.label == "FABRICATED"
+
+
+# --- relaxed HYBRID rescue (2026-05-21): tolerate unsourced proper nouns
+# (aliases/paraphrase) but still block unsourced numerics (date/count
+# errors), gated on a verified quote + on-topic + no contradiction. -----
+
+_EPIRUS_GOLD = ("Alexander I of Epirus was a king of Epirus from 350 to "
+                "331 BC, belonging to the Aeacid dynasty. He was the son "
+                "of Neoptolemus I and brother of Olympias.")
+
+
+def test_hybrid_rescued_when_only_unsourced_specific_is_proper_noun(monkeypatch):
+    # NLI off so the lexical tier is isolated (not the NLI corroboration
+    # path). One verbatim quote (verified) + one quote NOT in gold
+    # (-> HYBRID); the only unsourced specifics are proper nouns.
+    import bench.judge_code as jc
+    monkeypatch.setattr(jc, "_nli_check", lambda a, g: None)
+    answer = ('Alexander I of Epirus "was a king of Epirus from 350 to '
+              '331 BC". Also called Alexander Molossus, he "led famed '
+              'campaigns in southern Italy against the Romans".')
+    v = jc.judge("who was Alexander the first of epirus?", answer, _EPIRUS_GOLD)
+    assert v.label == "CORRECT_GROUNDED", (v.label, v.rationale)
+    assert v.decision.get("audit_mode") == "HYBRID"
+    assert "hybrid+verified_quote_on_topic" in v.decision["rules_fired"]
+
+
+def test_hybrid_stays_residue_when_unsourced_specific_is_numeric(monkeypatch):
+    # NLI off. One verified quote + an unverified quote with a WRONG date
+    # -> unsourced numeric -> NOT rescued (date/count errors stay residue).
+    import bench.judge_code as jc
+    monkeypatch.setattr(jc, "_nli_check", lambda a, g: None)
+    answer = ('Alexander I of Epirus "was a king of Epirus". He '
+              '"reigned from 999 to 888 BC".')
+    v = jc.judge("who was Alexander the first of epirus?", answer, _EPIRUS_GOLD)
+    assert v.label == "JUDGE_ERROR", (v.label, v.rationale)
+    assert "hybrid+verified_quote_on_topic" not in v.decision["rules_fired"]