pj/messageboardbench
1
0 Fork 0
mirror of https://github.com/priyanshujain/messageboardbench.git synced 2026-10-04 20:17:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add independent-agent SWE prompt-ablation pilot

Browse Source
This commit is contained in:
pj committed 2026-09-15 16:25:27 +05:30
1 parent b896955d3e
commit b3c935fbfa
13 files changed
+673 -12
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

experiments/swe-population-pilot-10-v3/experiment.json
+37
View File
@@ -0,0 +1,37 @@
{
"schema_version": 1,
"status": "ready",
"experiment_id": "swe-population-pilot-10-v3",
"purpose": "Developmental matched prompt comparison with independent SWE agents and a board-only cross-agent pathway.",
"remote_docker_host": "ssh://[email protected]",
"blockers": [],
"outputs": {
"run_dir": "logs/swe-population-pilot-10-v3/run",
"report_dir": "logs/swe-population-pilot-10-v3/report",
"verification_file": "logs/swe-population-pilot-10-v3/verification.json",
"resource_file": "logs/swe-population-pilot-10-v3/resources.json",
"state_file": "logs/swe-population-pilot-10-v3-status.json"
},
"execution": {
"argv": [".venv/bin/python", "scripts/swe_board_experiment.py", "--plan", "experiments/swe-population-pilot-10-v3/plan.json", "--out", "logs/swe-population-pilot-10-v3/run", "--execute"],
"resume": true
},
"postprocess": [
{
"name": "report",
"requires": ["logs/swe-population-pilot-10-v3/run/status.json", "logs/swe-population-pilot-10-v3/run/board-final.json", "logs/swe-population-pilot-10-v3/run/feedback-final.json"],
"argv": [".venv/bin/python", "scripts/swe_population_report.py", "--run", "logs/swe-population-pilot-10-v3/run", "--out", "logs/swe-population-pilot-10-v3/report"]
},
{
"name": "verify",
"requires": ["logs/swe-population-pilot-10-v3/report/report.json"],
"argv": [".venv/bin/python", "scripts/analysis/verify_swe_population.py", "--run", "logs/swe-population-pilot-10-v3/run", "--export", "logs/swe-population-pilot-10-v3/report", "--out", "logs/swe-population-pilot-10-v3/verification.json"]
},
{
"name": "resources",
"requires": ["logs/swe-population-pilot-10-v3/report/report.json", "logs/swe-population-pilot-10-v3/verification.json"],
"argv": [".venv/bin/python", "scripts/analysis/board_resources.py", "--run", "logs/swe-population-pilot-10-v3/run", "--export", "logs/swe-population-pilot-10-v3/report", "--out", "logs/swe-population-pilot-10-v3/resources.json"]
}
],
"manifest_sha256": "5e7201286c193c87d01f308a7d65615c6f99c2b10412091cd983ebae3dd33aef"
}