Skip to content

Actions: ASSERT-KTH/program-probes

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
97 workflow runs
97 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Use real turns in persistence baseline after-edit filter and trajecto… CI #97: Commit 37bdf12 pushed by andre15silva
1m 16s main
main
1m 16s
Add naive-persistence baseline for lookahead probes (#19) CI #96: Commit 1399ffa pushed by andre15silva
1m 2s main
main
1m 2s
Add naive-persistence baseline for lookahead probes CI #95: Pull request #19 opened by andre15silva
1m 15s persistence-baseline
persistence-baseline
1m 15s
Use real agent turns for lookahead labels; add trajectory-level shuff… CI #94: Commit d64c02f pushed by andre15silva
1m 19s main
main
1m 19s
Use real agent turns for lookahead labels; add trajectory-level shuffle CI #93: Pull request #18 opened by andre15silva
1m 14s fix/real-turn-labels
fix/real-turn-labels
1m 14s
add license update readme CI #92: Commit bee2b06 pushed by andre15silva
1m 22s main
main
1m 22s
paper: rename probes, add median stats, fix figure labels CI #91: Commit 26a1868 pushed by andre15silva
1m 56s main
main
1m 56s
update style.py CI #90: Commit be72cea pushed by andre15silva
1m 29s main
main
1m 29s
conf: add qwen36 pro labelling config CI #89: Commit 2bd0d62 pushed by andre15silva
1m 25s main
main
1m 25s
fix(paper): use 1-indexed layer labels consistently in figures CI #88: Commit 04a1e1d pushed by andre15silva
1m 24s main
main
1m 24s
add qwen-pro figures CI #87: Commit 5bc50dd pushed by andre15silva
1m 30s main
main
1m 30s
fix(paper): update dataset stats table caption CI #86: Commit 61c343b pushed by andre15silva
1m 37s main
main
1m 37s
fix(paper): wrap model and dataset names in \texttt in dataset stats … CI #85: Commit a07df38 pushed by andre15silva
1m 37s main
main
1m 37s
fix(paper): correct default shuffled run IDs to include _pooled suffix CI #84: Commit 7a64caf pushed by andre15silva
1m 59s main
main
1m 59s
feat(paper): add dataset statistics figures and table CI #83: Commit 62b0c89 pushed by andre15silva
1m 18s main
main
1m 18s
fix(paper): add dataset and model labels to heatmap and lookahead titles CI #82: Commit 97a0bd5 pushed by andre15silva
1m 24s main
main
1m 24s
fix(paper): remove n annotation from lookahead x-axis label CI #81: Commit 885b4f8 pushed by andre15silva
1m 59s main
main
1m 59s
update tables CI #80: Commit f06925d pushed by andre15silva
1m 27s main
main
1m 27s
fix(paper): remove shuffled series from combined layer AUC plots CI #79: Commit 6068c63 pushed by andre15silva
1m 32s main
main
1m 32s
feat(probe): per-probe per-layer sweep pipeline with parallel coordin… CI #78: Commit bd9e18c pushed by andre15silva
1m 20s main
main
1m 20s
fix(paper): clean up heatmaps — pcolormesh, no grid lines, 0.5–1.0 scale CI #77: Commit 7807d09 pushed by andre15silva
1m 29s main
main
1m 29s
feat(paper): overhaul figures pipeline — PDF output, hparam table, Pr… CI #76: Commit bf0d905 pushed by andre15silva
1m 20s main
main
1m 20s
fix(paper): use math-mode ASCII minus in transfer table to avoid Unic… CI #75: Commit a5b7d62 pushed by andre15silva
1m 23s main
main
1m 23s
fix(labeler-pro): detect compile failures from stdout.log/stderr.log … CI #74: Commit a274c78 pushed by andre15silva
1m 21s main
main
1m 21s
conf: add qwen3.6 sweb-pro CI #73: Commit fa669d9 pushed by andre15silva
1m 19s main
main
1m 19s