mirror of
https://github.com/priyanshujain/messageboardbench.git
synced 2026-10-05 04:27:06 +00:00
Add deterministic SWE candidate screening
This commit is contained in:
1 parent
aeaae4291f
commit
175c9d48f4
13 files changed
+1292
-50
No files matched your search
@@ -1,12 +1,10 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"status": "blocked",
|
||||
"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": [
|
||||
"The reused django__django-15315 conflicting evaluator crashes during import and records every target as MISSING. Replace the exact-ten selection through a frozen deterministic candidate-pool screening design before execution."
|
||||
],
|
||||
"blockers": [],
|
||||
"outputs": {
|
||||
"run_dir": "logs/swe-population-pilot-10-v3/run",
|
||||
"report_dir": "logs/swe-population-pilot-10-v3/report",
|
||||
@@ -15,7 +13,7 @@
|
||||
"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"],
|
||||
"argv": [".venv/bin/python", "scripts/swe_board_experiment.py", "--plan", "work/swe-population-pilot-10-v3-validation/execution-plan.json", "--out", "logs/swe-population-pilot-10-v3/run", "--execute"],
|
||||
"resume": true
|
||||
},
|
||||
"postprocess": [
|
||||
@@ -35,5 +33,5 @@
|
||||
"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": "e648799bad82182e46c15dccc6f14280d565e17fe7d19d2ce1bf4d7bacd7e28e"
|
||||
"manifest_sha256": "448c4078f71c673c8142f71a19b78cd88605fbaaee650f050923ddcfc12bf0d9"
|
||||
}
|
||||
Reference in new issue
Block a user