results(imo-2026): archive audit trails for 8 more runs + extraction script#348
Merged
Conversation
…script Adds full audit artifacts (current.md, approaches/, lemmas/ from the run branch; logs.jsonl from the DB; scratch/ from the rounds volume) for: - Fable 5 — p6 (effort: medium) - GPT-5.6 Sol — p5, p6 (effort: high) - Opus 4.5 — p1, p2 (effort: high) [new model folder] - Opus 4.8 — p1, p2 (effort: high) [new model folder] All 7 runs verified: status completed, run_starting/run_ended balanced, full subagent-role pipeline present, zero credential matches. Also saves the reproducible extraction script under scripts/ (fixes the relative-DEST bug and documents the benign trailing-grep exit code). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds full audit artifacts (current.md, approaches/, lemmas/, logs.jsonl, scratch/) for GPT-5.6 Sol problem 4 (effort: high). Completes GPT-5.6 Sol's coverage of all six IMO 2026 problems. Verified: status completed, run_starting/run_ended balanced, full subagent-role pipeline present, zero credential matches. Co-Authored-By: Claude Opus 4.8 (1M context) <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Archives full audit artifacts for 8 more completed IMO 2026 runs, proving each was AI-generated with no human intervention. Same schema as prior batches (PR #344 etc.):
current.md+approaches/+lemmas/from the run branch,logs.jsonl(verbatim run + audit_log + tool_calls) from the DB,scratch/from the rounds volume.Adds two new model folders (
claude-opus-4-5/,claude-opus-4-8/). GPT-5.6 Sol now covers all six problems.Also saves the reproducible extraction script at
results/imo-2026/scripts/extract_run.sh(relative-DEST bug fixed; benign trailing-grep exit documented).Verification (all 8 runs): status
completed, balancedrun_starting/run_ended, full subagent-role pipeline present (math-explorer/proof-outliner/proof-builder/proof-reviewer/outline-reviewer + orchestrator), and 0 credential matches across every committed byte.🤖 Generated with Claude Code