docs(plans): enrich synthetic-validation plan for v1.8.0 survey #1060 - #1792
Conversation
|
Strix is installed on this repository, but we couldn't run this PR security review because this workspace's trial has ended. Add a card to resume code reviews here. So far, Strix has reviewed 36 pull requests, surfaced 5 security issues (1 critical/high) and blocked 1 risky merge across this workspace. |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
FabioLeitao has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.
There was a problem hiding this comment.
FabioLeitao has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.
Specify composite eval as four separate axes (F1, latency, throughput, re-id privacy risk) with a citation tuple; no fused score and no new numbers. Sync hub and PLANS_TODO. Docs-first; no harness change. Closes #1060
Script output only: pt_BR row now links VALIDATION.md via ../VALIDATION.md to match plans_hub_sync.py.
Keep packaging-extras and composite-eval survey rows; dashboard counts include both slices.
0e08cce to
7e46ce6
Compare
There was a problem hiding this comment.
FabioLeitao has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.
1 participant
Summary
PLAN_SYNTHETIC_DATA_AND_CONFIDENCE_VALIDATION(EN + new equivalent pt-BR): composite eval as four separate axes — F1, latency, throughput, and re-id risk as privacy (not quality). Ranking changes if you measure F1 only; no fused score.F1_BASELINE_METHODOLOGY— no file with that name) + synthetic lab plan / ADR-0007. Citation tuple required for any later number: scope, pinned artifact,benchmarkid,git_sha, date. No new published figures in this PR.PLANS_HUB.md+PLANS_TODO.md. Does not depend on open PR docs(plans): enrich packaging-extras plan for v1.8.0 survey #1059 #1791 ([1.8.x][packaging] Enriquecer PLAN_PACKAGING_EXTRAS: perfil [noavx] (wheelhouse #929) + [nlp]/[ocr]/[dl] capability-profiles #1059).Test plan
./scripts/check-all.sh(local, this session)Closes #1060