Checkpoint experiments through SWE pilot v2

This commit is contained in:
pj committed 2026-09-15 15:46:10 +05:30
1 parent abacd5c5e1
commit 72d77018d8
845 files changed
+431756 -41

No files matched your search

@@ -0,0 +1,50 @@
{
"task_id": "lcbhard_12",
"source_log": "/Users/pj/Workspace/projects/python/research/messageboardbench/logs/board-pilot-glm-interface-v2-sept8/evals/2026-09-07T20-31-49-00-00_board-pilot-board-c2-p3_FkHpQjLvcVaP2g9aynmEKe.eval",
"source_log_sha256": "6605eed2cece65dc1638661d08410b78900b218fedf8077b7d0e1cdcbee2f5fd",
"source_sha256": "a3ede3690c8a19f0b9b24cbf1bb3be36a000aa591c82814450a3a4776e8df016",
"probe_sha256": "859e73605b66a8838f30ecf5ae402d162ef93f57dfc3d7c981616772aeb7c357",
"command": [
"docker",
"run",
"--rm",
"--name",
"board-v2-probe-996f1424a8f5",
"--network",
"none",
"--memory",
"256m",
"--pids-limit",
"64",
"--read-only",
"--cap-drop",
"ALL",
"--security-opt",
"no-new-privileges",
"--user",
"65534:65534",
"--mount",
"type=bind,src=/Users/pj/Workspace/projects/python/research/messageboard/scratchpad/board-interface-v2-sept8/reviews/board-c2-task12-probe,dst=/workspace,readonly",
"--workdir",
"/workspace",
"sha256:fb045da8203aea656785c758f7147b003cfe21f213e9048a38be0a33242a5b3d",
"python3",
"-B",
"/workspace/probe.py"
],
"image_id": "sha256:fb045da8203aea656785c758f7147b003cfe21f213e9048a38be0a33242a5b3d",
"exit_code": 0,
"result": {
"independent_reference": 3,
"identical_input_returns": [
7,
3,
3
],
"control_identical_start_goal_returns": [
0,
0,
0
]
}
}