Files
messageboardbench/experiments/swe-population-pilot-10-v1/experiment.json
T

42 lines
2.0 KiB
JSON

{
"schema_version": 1,
"status": "ready",
"experiment_id": "swe-population-pilot-10-v1",
"purpose": "Run a 10-task matched control/board SWE pilot before the full population experiment.",
"remote_docker_host": "ssh://[email protected]",
"blockers": [],
"outputs": {
"run_dir": "logs/swe-population-pilot-10-v1/run",
"report_dir": "logs/swe-population-pilot-10-v1/report",
"verification_file": "logs/swe-population-pilot-10-v1/verification.json",
"resource_file": "logs/swe-population-pilot-10-v1/resources.json",
"state_file": "logs/swe-population-pilot-10-v1-status.json"
},
"execution": {
"argv": [
".venv/bin/python", "scripts/swe_board_experiment.py",
"--plan", "experiments/swe-population-pilot-10-v1/plan.json",
"--out", "logs/swe-population-pilot-10-v1/run", "--execute"
],
"resume": true
},
"postprocess": [
{
"name": "report",
"requires": ["logs/swe-population-pilot-10-v1/run/status.json", "logs/swe-population-pilot-10-v1/run/board-final.json"],
"argv": [".venv/bin/python", "scripts/swe_population_report.py", "--run", "logs/swe-population-pilot-10-v1/run", "--out", "logs/swe-population-pilot-10-v1/report"]
},
{
"name": "verify",
"requires": ["logs/swe-population-pilot-10-v1/report/report.json"],
"argv": [".venv/bin/python", "scripts/analysis/verify_swe_population.py", "--run", "logs/swe-population-pilot-10-v1/run", "--export", "logs/swe-population-pilot-10-v1/report", "--out", "logs/swe-population-pilot-10-v1/verification.json"]
},
{
"name": "resources",
"requires": ["logs/swe-population-pilot-10-v1/report/episodes.json"],
"argv": [".venv/bin/python", "scripts/analysis/board_resources.py", "--run", "logs/swe-population-pilot-10-v1/run", "--export", "logs/swe-population-pilot-10-v1/report", "--out", "logs/swe-population-pilot-10-v1/resources.json"]
}
],
"manifest_sha256": "eef7fc99bd9189126ff9b84e36591116a1d191394c1eb04c69cc5a8fbfff22d1"
}