12/12 Putnam 2025 verified — complete sweep, $1.13 total 759bac6 Vilin97 Claude Opus 4.6 (1M context) commited on 4 days ago
9/9 Putnam 2025 problems verified! Full test log update a6cab41 Vilin97 Claude Opus 4.6 (1M context) commited on 4 days ago
Update LOG with pq-group 20min active-proving result d95748d Vilin97 Claude Opus 4.6 (1M context) commited on 5 days ago
Active proving: Kimi + Qwen race against Aristotle 81ad344 Vilin97 Claude Opus 4.6 (1M context) commited on 6 days ago
Update LOG: pq-group fast path verified but agent didn't finalize 6da83ba Vilin97 Claude Opus 4.6 (1M context) commited on 6 days ago
Update LOG.md with UW analysis prelim results and new tool tests ab10662 Vilin97 Claude Opus 4.6 (1M context) commited on 6 days ago
Update LOG.md with FATE-X #10 test, update README lean version to v4.28 7247599 Vilin97 Claude Opus 4.6 (1M context) commited on 6 days ago
Improve false-statement handling, increase Aristotle timeout to 2h, better visibility 4093e2c Vilin97 Claude Opus 4.6 (1M context) commited on 6 days ago
Update LOG.md with comprehensive test results (20 queries) 5dc7261 Vilin97 Claude Opus 4.6 (1M context) commited on 6 days ago
Add VeriDeepResearch: verified math research chatbot 925bbe2 Vilin97 Claude Opus 4.6 (1M context) commited on 6 days ago
Vilin97 Claude Opus 4.6 (1M context) commited on 