Skip to content

Actions: securityCFS/EBench-Astra-Tech-Report

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
125 workflow runs
125 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
Take the Pages base path from Pages, so renames cannot break the site Cross-platform frontend checks #8: Commit 86aadcd pushed by securityCFS
14m 46s main
main
14m 46s
Take the Pages base path from Pages, so renames cannot break the site Deploy report to GitHub Pages #117: Commit 86aadcd pushed by securityCFS
1m 40s clean
clean
1m 40s
Deploy only from clean Cross-platform frontend checks #7: Commit d64ef25 pushed by securityCFS
15m 55s main
main
15m 55s
Deploy only from clean Deploy report to GitHub Pages #116: Commit d64ef25 pushed by securityCFS
1m 5s clean
clean
1m 5s
Rename compositional task execution heading Deploy report to GitHub Pages #115: Commit 8208ffc pushed by YudeZou
1m 15s clean
clean
1m 15s
Lead the task-level examples with the ranking, in one paragraph Deploy report to GitHub Pages #114: Commit ae00b35 pushed by securityCFS
1m 18s clean
clean
1m 18s
Say the per-task ranking in one line Deploy report to GitHub Pages #113: Commit d92a6ad pushed by securityCFS
1m 18s clean
clean
1m 18s
Give the capability section its evidence, and name π₀.₅ as the example Deploy report to GitHub Pages #112: Commit 7856bb9 pushed by securityCFS
1m 18s clean
clean
1m 18s
Fold the perturbation finding into the opening paragraph Deploy report to GitHub Pages #111: Commit c836770 pushed by securityCFS
1m 18s clean
clean
1m 18s
Soften the perturbation finding to what the table shows Deploy report to GitHub Pages #110: Commit 76363c7 pushed by securityCFS
1m 31s clean
clean
1m 31s
State the perturbation finding without repeating the table Deploy report to GitHub Pages #109: Commit c437a0b pushed by securityCFS
1m 20s clean
clean
1m 20s
Use a clearly failed cup-flipping run, at full frame rate Deploy report to GitHub Pages #108: Commit 20b72b8 pushed by securityCFS
1m 16s clean
clean
1m 16s
Remove the capability table that no text relied on Deploy report to GitHub Pages #107: Commit 4e7133a pushed by securityCFS
1m 8s clean
clean
1m 8s
Rank the outcome bars by success rate, then Score, across all 26 tasks Deploy report to GitHub Pages #106: Commit b5bd0b4 pushed by securityCFS
1m 26s clean
clean
1m 26s
Drop the tabletop precision rows from the capability table Deploy report to GitHub Pages #105: Commit d369f5c pushed by securityCFS
1m 8s clean
clean
1m 8s
Report SR to one decimal and Score to three, and tighten three passages Deploy report to GitHub Pages #104: Commit 67ab6ef pushed by securityCFS
1m 7s clean
clean
1m 7s
Say when a demonstration helps: instructive experience, not precise a… Deploy report to GitHub Pages #103: Commit 5af18c2 pushed by securityCFS
1m 9s clean
clean
1m 9s
Reduce the paired ICL appendix to its per-task outcome Deploy report to GitHub Pages #102: Commit 6ee28d7 pushed by securityCFS
1m 19s clean
clean
1m 19s
Replace the four-seed ICL pairs with all 20 seeds of frame and gear Deploy report to GitHub Pages #101: Commit 9eb5e3b pushed by securityCFS
1m 6s clean
clean
1m 6s
Keep the two mobile evidence videos under their own play control Deploy report to GitHub Pages #100: Commit 05c225e pushed by securityCFS
1m 49s clean
clean
1m 49s
Account for all 26 tasks in the per-task ranking sentence Deploy report to GitHub Pages #99: Commit 5e2e9a3 pushed by securityCFS
2m 40s clean
clean
2m 40s
Resolve the report audit: contradictions, overclaims, names and spelling Deploy report to GitHub Pages #98: Commit 3005792 pushed by securityCFS
1m 15s clean
clean
1m 15s
Make the title singular: one frontier agent was evaluated Deploy report to GitHub Pages #97: Commit 67ddfca pushed by securityCFS
1m 52s clean
clean
1m 52s
Credit the lead to short horizon, not to mobile short-horizon tasks Deploy report to GitHub Pages #96: Commit ba4fce7 pushed by securityCFS
1m 7s clean
clean
1m 7s
Number references by first citation in reading order Deploy report to GitHub Pages #95: Commit be51d7b pushed by securityCFS
1m 41s clean
clean
1m 41s