feat(competition): provenance-rank engine-lane submission - #567
Merged
Conversation
ranks first-hand statements over hearsay (reported speech about a named third party is demoted, hardest when the query is first-person), pushes stored instructions to the tail (a memory that tells the reader what to answer is an injection, not a fact), and boosts change-of-state phrasing so the newest value survives a tight budget. blended with the backend score and plain lexical overlap for everything else. verified locally with the ci-exact loop over generic seeds 1-12: challenger 0.5750 vs baseline 0.5250, diff +0.0500, band 0.0381 - dethroned.
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. 🗂️ Base branches to auto review (2)
Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
github-actions
Bot
added
size: S
plind-junior
enabled auto-merge
July 28, 2026 03:55
plind-junior
disabled auto-merge
July 28, 2026 03:55
plind-junior
added a commit
that referenced
this pull request
Jul 28, 2026
the engine-lane winner (pr #567) moves in-package as vouch.strategies.provenance and becomes what challengers must beat: contrib/strategies/baseline.py now delegates to it instead of returning identity order. new KBs get it as the final reorder stage via the starter config (retrieval.strategy); existing KBs keep byte-identical ordering until they add the key, and strategy: null opts out. the bench is unaffected - its throwaway KBs write their own config, so kits and strategies keep being measured explicitly. rerank-isolation tests opt out of the strategy stage, since the champion is final-say and would re-sort the asserted window.
plind-junior
added a commit
that referenced
this pull request
Jul 28, 2026
the engine-lane winner (pr #567) moves in-package as vouch.strategies.provenance and becomes what challengers must beat: contrib/strategies/baseline.py now delegates to it instead of returning identity order. new KBs get it as the final reorder stage via the starter config (retrieval.strategy); existing KBs keep byte-identical ordering until they add the key, and strategy: null opts out. the bench is unaffected - its throwaway KBs write their own config, so kits and strategies keep being measured explicitly. rerank-isolation tests opt out of the strategy stage, since the champion is final-say and would re-sort the asserted window.
This was referenced Jul 28, 2026
plind-junior
added a commit
to Steve-too/vouch
that referenced
this pull request
Jul 29, 2026
pull_request_target workflows only trigger when the workflow file exists on the default branch. the engine gate lived only on the ladder and feature branches, so engine-lane pr vouchdev#567 got no scoring run at all while the kit gate (registered from main) ran fine. the file is byte-identical to the ladder copy; the run itself still checks out and executes base-branch code per its security model.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
engine-lane submission: provenance-aware ranking. three general principles, no benchmark-keyed logic:
everything else defers to the backend's fused score blended with lexical overlap.
local verification with the ci-exact loop (
vouch bench run --seeds 1,2,3,4,5,6,7,8,9,10,11,12 --strategy contrib/strategies/provenance_rank.py --against contrib/strategies/baseline.py): challenger 0.5750, baseline 0.5250, diff +0.0500, band 0.0381 — dethroned.per the lane rules this pr is scored by the gate in a sandbox and never auto-merges: a human reviews the code for benchmark-keyed logic and merges the highest verified score.