docs: record leaderboard publishing pitfalls in CLAUDE.md - #43
Open
haolin-chen-actava wants to merge 1 commit into
Open
haolin-chen-actava wants to merge 1 commit into
haolin-chen-actava wants to merge 1 commit into
Conversation
Three notes from auditing why merged results were not appearing publicly: - The site's leaderboard is a hand-maintained array in actava-official-website/lib/benchmarks-data.ts, not generated from the leaderboard repo, so merging a submission PR publishes nothing. - Publishing is four independent manual steps (run -> leaderboard PR -> website PR -> infographic) that drift apart; generated post assets under ~/.codex/visualizations are where broadcast-but-unsubmitted results surface first. - Never cite a chi_bench_git_sha that is unreachable from main, with the concrete 4f39c1e case that motivated it. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Three notes from auditing why merged results were not appearing on the public leaderboard.
actava-ai/leaderboard— it is a hand-maintained array inactava-official-website/lib/benchmarks-data.ts. Merging a submission PR publishes nothing on its own, which is how both merged-but-unlisted entries and packet-vs-site number drift happened. Includes the commands to audit it.~/.codex/visualizations/are where broadcast-but-unsubmitted results surface first.chi_bench_git_shaunreachable frommain, with the concrete4f39c1ecase that motivated it (now resolved by Land frontier model evaluations (GPT-5.6 family, Kimi K3, Inkling, Nemotron 3 Ultra) #42).🤖 Generated with Claude Code