pj/messageboardbench
1
0 Fork 0
mirror of https://github.com/priyanshujain/messageboardbench.git synced 2026-10-02 11:07:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • e94b75c6f5 archive historical results and add token budget logs main pj 2026-09-25 22:07:26 +05:30
  • 638e978227 archive old experiments and publish swe series pj 2026-09-25 12:34:44 +05:30
  • 480100587e remove all tests pj 2026-09-17 18:24:29 +05:30
  • 9a80c0cf96 exp v4 and v5 pj 2026-09-17 04:32:02 +05:30
  • 62a9a35537 add v3 board activation experiment analysis pj 2026-09-16 11:22:27 +05:30
  • bce10b34ac analyze swe board activation v2 pj 2026-09-16 02:48:53 +05:30
  • 9101e62f3a analyze swe board activation pj 2026-09-16 01:52:41 +05:30
  • 1428c2b08e Support immutable local SWE image IDs pj 2026-09-15 23:24:09 +05:30
  • 69c5793562 Grade SWE submissions in fresh containers pj 2026-09-15 23:17:49 +05:30
  • 13d62ae7fc fix swe pilot v3 offline verification pj 2026-09-15 22:27:50 +05:30
  • 08c8de15c2 Analyze SWE population pilot v3 pj 2026-09-15 22:22:13 +05:30
  • 175c9d48f4 Add deterministic SWE candidate screening pj 2026-09-15 17:54:57 +05:30
  • aeaae4291f Fail fast on invalid SWE prerequisite tasks pj 2026-09-15 17:16:54 +05:30
  • b3c935fbfa Add independent-agent SWE prompt-ablation pilot pj 2026-09-15 16:25:27 +05:30
  • b896955d3e Keep communication diagnostics coding-relevant pj 2026-09-15 15:59:10 +05:30
  • 72d77018d8 Checkpoint experiments through SWE pilot v2 pj 2026-09-15 15:46:10 +05:30
  • abacd5c5e1 Bound sample wall clock; a request timeout does not stop a hang pj 2026-09-01 00:01:26 +05:30
  • f933ce6d15 Record working files written outside the scratch directory pj 2026-08-31 22:38:48 +05:30
  • d604370d96 A file called scratch.py is not the scratch directory pj 2026-08-31 22:02:56 +05:30
  • bcce9d9e90 Calibration artifact: the checks and the raw commands side by side pj 2026-08-31 21:44:04 +05:30
  • 0a053c114c Do not attribute the harness's own filesystem actions to the agent pj 2026-08-31 21:43:22 +05:30
  • fc43b691a7 Guard that the fork presents the same task text as the stock benchmark pj 2026-08-31 21:40:09 +05:30
  • 863c6bd7d8 Analysis rows, pilot and report scripts pj 2026-08-31 21:38:52 +05:30
  • 099563a830 Scratch directory task, event adapter, per-run checks pj 2026-08-31 21:36:13 +05:30
  • bf3bb0d144 Repo skeleton, pinned environment, free smoke test pj 2026-08-31 21:14:58 +05:30