Repository navigation
Record where each shown claim sat; score ratings against that slot - #83
Merged
Merged
Conversation
Every shown claim_usages row now keeps {position, section, rank} in the order the reply renders,
so a used rating can be read against what that slot gets anyway. scripts/usefulness.py reports
each claim's lift over its slots' used rate (read-only, one SELECT on D1).
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Requested by Vu · project thread
A
usedrating on the top claim of every briefing means less than one on position 9 of a recall. This change records the slot when a claim is shown and scores ratings against it (the "score centering" idea from Applied Compute's production-RL post).recordUsagenow takes the reply's sections in render order. Every shown row storesmetadata: {position, section, rank}, with no migration because the column already exists. The localrecord_usagedoes the same.scripts/usefulness.pyis read-only, one SELECT. It reports the used rate per slot and each claim'slift, meaning its used rate minus the rate its slots get anyway.Verification: worker
npm testpasses 376 tests, including a new one for slot metadata across recall, briefing and expand.tsc --noEmitis clean. Pythonunittest discover -s testspasses 351 tests.kypp.verifyand thekypp.storeself-test pass, and so doesfeaturemap.py check. The hosted-worker map now lists the script and its test.Generated by Claude Code