diff --git a/docs/TICKETS.md b/docs/TICKETS.md
index 00940f8..87e87b5 100644
--- a/docs/TICKETS.md
+++ b/docs/TICKETS.md
@@ -101,7 +101,7 @@ Newest first. Update on every open/close.
 
 | ID       | Title                                          | Status                | Opened     | Directive |
 |----------|------------------------------------------------|-----------------------|------------|-----------|
-| #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"). The mechanism behind whitepaper §1's "the embedding pass runs off the device". #000039 / #000050 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 · awaiting go/no-go · 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). First decision = the discipline question: may a small fixed purpose-built NLI/entailment *model* influence `audit_mode`? (vs the "no LLM-as-judge" rule). Recommends Option 2.3 (do nothing — the 2 fixtures are a boundary marker) until real-traffic recombination-over-grounds show up, then Option 2.2 (`[nli]` extra, policy-gated, off-by-default, bench-gated) *if* fox rules a fixed NLI model is acceptable. #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 | —         |
diff --git a/docs/tickets/ticket-000051-federated-vecpack-distribution.md b/docs/tickets/ticket-000051-federated-vecpack-distribution.md
index e5698ad..2e84e3c 100644
--- a/docs/tickets/ticket-000051-federated-vecpack-distribution.md
+++ b/docs/tickets/ticket-000051-federated-vecpack-distribution.md
@@ -155,6 +155,29 @@ Prometheus-Σ unconscious-sweep task (#000037 §3.1) is the natural
 producer — it backfills `chunk_vecs` off-peak *and* exports the pack
 *and* answers pull requests, all as one low-priority background role.
 
+**GPU producer (the fast path).** `bge-small-en-v1.5` is a 33M-param
+model; on a CUDA box (a 4090 or similar) with batched inference (batch
+256–512) embedding throughput is ~10³–10⁴ chunks/s — tokenization /
+data-feeding bound, not matmul bound — so the full 6.24M-chunk wiki
+set is **minutes of GPU time, not days of CPU**. The producer is just
+`arborist embed --quant int8` run with a CUDA `Embedder`: `fastembed`'s
+`TextEmbedding(..., providers=["CUDAExecutionProvider"])`, or
+`sentence-transformers` `.encode(..., device="cuda", batch_size=512)`
+— both drop into `default_embedder()`'s pluggable callable (#000039
+§14.6). int8 quantization stays on the CPU side in `_to_blob` (cheap,
+post-embed) so the GPU only produces float32 vectors; the rest of the
+pipeline is byte-for-byte the same. The CUDA stack (`torch` /
+`onnxruntime-gpu`) lives **only on the producer box** — an optional
+toolchain in a sibling repo / extra, never in arborist's
+`python3.12 + sqlite3` core; a fresh laptop checkout needs only the
+`[vec]` extra to *import* a pack. Determinism note: a GPU backfill is
+**not** byte-identical to a CPU one (matmul order differs) — irrelevant
+here, embeddings are soft data (`UNGROUNDED`, never proof path) and two
+independent backfills are interchangeable; pin the model revision +
+quant recipe in `vec_backend_version`, not the output bytes (the same
+"don't byte-KAT the embedder" call the #000050 review made — contrast
+#000035's φ_PRG, which *is* byte-KAT'd because it's hard-channel).
+
 ## 5. Out of scope
 
 - The local embed backend + `arborist embed` itself (#000039 — done).