Cross-link leaderboard <-> dataset on HF + GitHub README d05b5bd Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 15 days ago
Restore /admin/insert for maintainer leaderboard corrections 53c64b6 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 15 days ago
Single-repo dataset hosting on HF (GLUE-style subdirs) bd3e9ac Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 15 days ago
Overall: only complete agents get an average; rest sink to bottom ab28b31 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Landing table: fix per-column sort + drop tasks col + move avg to last bf48fd7 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Fix kaggle status parse + add /admin/repoll for stuck rows f819f00 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Fix kaggle async: use sentinel -1.0 for pending (NOT NULL) + correct col names 1a157a1 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Async Kaggle scoring: submit + insert pending row + background poll 9cb903d Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Pin kaggle==1.7.4.5 (newer versions reject KAGGLE_API_TOKEN env auth) 00bf799 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Surface kaggle submit stdout + rc in error msg b226034 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Add POST /admin/insert for direct leaderboard writes 209df55 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Add POST /admin/delete for bypass-keyed leaderboard cleanup 18fe8a0 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
binary check: keep float dtype during validation, reject non-{0,1} 769f2a4 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
ibm-aml → binary submission for minority F1 (server: no threshold) b3dbec5 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
push_to_space.sh: auto-inject HF_TOKEN into push URL when set 640f1df Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Landing: stack panel header (description above pills); style schema pill green; drop GT loaded badge cf612db Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Add Overall tab + /leaderboard JSON; stage ibm-aml + arxiv data 5955024 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Redesign landing as a leaderboard-first single page 6741538 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Add Kaggle scoring backend + load all 4 task GTs 17942c5 Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Add Flask + Jinja2 landing page at GET / 464248e Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Add GT_BYPASS_KEY for unlimited submissions + dry mode 5ead61d Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 16 days ago
Add agents/ harness integrations and HF Space scoring deployment d094faf Zhu Jiajun (jz28583) Claude Opus 4.7 (1M context) commited on 17 days ago
Initial commit: GraphTestbed v0.1.0 ad6901d zhuconv Claude Opus 4.7 (1M context) commited on 18 days ago