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 deterministic SWE candidate screening

Browse Source
This commit is contained in:
pj committed 2026-09-15 17:54:57 +05:30
1 parent aeaae4291f
commit 175c9d48f4
13 files changed
+1292 -50
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

experiments/swe-population-pilot-10-v3/justfile
+3 -2
View File
@@ -1,9 +1,10 @@
root := "../.."
start:
cd {{root}} && .venv/bin/python scripts/run_experiment_bundle.py --bundle experiments/swe-population-pilot-10-v3 --validate-only
cd {{root}} && .venv/bin/python scripts/remote_docker.py -- .venv/bin/python scripts/validate_swe_population_prerequisites.py --plan experiments/swe-population-pilot-10-v3/plan.json --out work/swe-population-pilot-10-v3-validation
cd {{root}} && .venv/bin/python scripts/prepare_swe_population_v3.py --pool experiments/swe-population-pilot-10-v3/candidate-pool.json --template experiments/swe-population-pilot-10-v3/plan.json --screen-root work/swe-population-pilot-10-v3-validation --derived-plan work/swe-population-pilot-10-v3-validation/execution-plan.json --validate-only
cd {{root}} && .venv/bin/python scripts/remote_docker.py -- .venv/bin/python scripts/prepare_swe_population_v3.py --pool experiments/swe-population-pilot-10-v3/candidate-pool.json --template experiments/swe-population-pilot-10-v3/plan.json --screen-root work/swe-population-pilot-10-v3-validation --derived-plan work/swe-population-pilot-10-v3-validation/execution-plan.json
cd {{root}} && .venv/bin/python scripts/run_experiment_bundle.py --bundle experiments/swe-population-pilot-10-v3
validate:
cd {{root}} && .venv/bin/python scripts/prepare_swe_population_v3.py --pool experiments/swe-population-pilot-10-v3/candidate-pool.json --template experiments/swe-population-pilot-10-v3/plan.json --screen-root work/swe-population-pilot-10-v3-validation --derived-plan work/swe-population-pilot-10-v3-validation/execution-plan.json --validate-only
cd {{root}} && .venv/bin/python scripts/run_experiment_bundle.py --bundle experiments/swe-population-pilot-10-v3 --validate-only