docs: relevance-and-veto-synthesis-for-dav1d.md — single decision brief synthesizing #000049 + #000052 §3.1 + §3.2 for forward review
Synthesizes the bench-maxing work across: #000049 NLI recombination veto (bart-large-mnli/k=12/margin/θ=0.999 → 48% real-haystack recall at 0/808 STRICT FP — partial closure, Phase-3 semantic candidate selector for full closure) #000052 §3.1 diagnose_coherence (lexical sidecar, advisory-only, 1.1% real-STRICT FP after round-2 patch) #000052 §3.2 relevance reranker (bge-reranker-large + cleaned + θ ≤ -2.42 → 100% mis-cite / 55% deflection / 0% STRICT FP — motivating Zionist-shape failure fully covered) The three are architecturally orthogonal (§3.2.2 step 3C verified: combining lexical sidecars with the relevance reranker gives no lift; each owns its own failure-shape slice). Three structurally distinct demote-only signals layered on the binary verifier. Three runtime-promotion decisions for fox+dav1d: - §3.1: keep advisory or wire policy hook? (probably advisory) - §3.2: promote at the fp=0 operating point? (sign-off folds relevance_policy_hash into governance_policy_hash) - #000049: promote at 48% partial closure, or wait for Phase 3 semantic candidate selector? Bench-maxing methodology codified in CLAUDE.md is the transferable artifact: 'clean candidate-bench can mis-predict in BOTH directions — real-data fixtures on both precision AND recall axes are the only load-bearing measurement'. Eight instances across the two arcs; the discipline applies to any future model-based addition. Indexed in docs/TICKETS.md 'Distinction from other docs' section as a non-ticket reference doc. Production verifier unchanged; nothing in audit_mode; all work SHADOW pending sign-off.
This commit is contained in:
parent
7910440e50
commit
90d5c54c0a
2 changed files with 226 additions and 0 deletions
|
|
@ -91,6 +91,16 @@ proposing change. Examples that stay un-numbered:
|
|||
between "ingest + search runs on a phone" and an NPU hand-warmer.
|
||||
Generalizes the "soft hash vs hard hash" discipline; the numbers
|
||||
come from #000039 §14.6. Written 2026-05-12.)
|
||||
- `relevance-and-veto-synthesis-for-dav1d.md` (2026-05-13 dav1d
|
||||
handoff: synthesis of #000049 [NLI recombination veto] + #000052
|
||||
§3.1 [coherence sidecar] + §3.2 [relevance reranker] into one
|
||||
decision-ready brief. Three orthogonal sidecars / vetoes
|
||||
covering non-overlapping failure shapes; recommended runtime
|
||||
operating points; per-step bench-maxing receipts; the
|
||||
eight-instance meta-lesson "clean candidate-bench mis-predicts in
|
||||
both directions, real-data on both axes is the only load-bearing
|
||||
measurement". Awaiting fox+dav1d sign-off on the three runtime-
|
||||
promotion decisions.)
|
||||
|
||||
If a doc proposes change AND awaits a decision AND has scoped
|
||||
implementation cost, it's a ticket. Otherwise it's reference.
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue