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_10",
"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-p1_Aq6HVepgji5rjYVzLSkqPd.eval",
"source_log_sha256": "cbce6b1e153e4fb428b7fcccef907dafcf665b1498c0ab9f10011bc3dd19b42f",
"source_sha256": "5ae6aeb6ca920cf6c498110d6963c08f708aebeb29d8f059a2f1601ae155f4eb",
"probe_sha256": "012b8130ccf28621b9e7694231ae8a5b3b598b6bbb0a714855bef9f58e8717e2",
"command": [
"docker",
"run",
"--rm",
"--name",
"board-v2-probe-0defea635213",
"--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-task10-probe,dst=/workspace,readonly",
"--workdir",
"/workspace",
"sha256:fb045da8203aea656785c758f7147b003cfe21f213e9048a38be0a33242a5b3d",
"python3",
"-B",
"/workspace/probe.py"
],
"image_id": "sha256:fb045da8203aea656785c758f7147b003cfe21f213e9048a38be0a33242a5b3d",
"exit_code": 0,
"result": {
"identical_input_returns": [
117169852,
999999999,
999999999
],
"control_zero_caps_returns": [
0,
0,
0
],
"second_return_outside_required_modular_range": true
}
}