Skip to content

Actions: ParsaVictor/code-context-engine

Actions

Continuous Empirical Benchmarking

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
benchmark.yml
320 workflow runs
320 workflow runs

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
Continuous Empirical Benchmarking Continuous Empirical Benchmarking #320: Scheduled
1m 34s main
main
1m 34s
Measured: v1.4.0 once on Lite/Verified (function Acc@5 Lite-274 0.394… Continuous Empirical Benchmarking #319: Commit 17a7195 pushed by ParsaVictor
1m 49s main
main
1m 49s
Measured: v1.4.0 once on Lite/Verified (function Acc@5 0.394 → 0.460 / 0.346 → 0.429); paper draft; session 19 brief Continuous Empirical Benchmarking #318: Pull request #145 opened by ParsaVictor
1m 49s s18/paper-v140
s18/paper-v140
1m 49s
1.4.0: traceback functions vote, function list for every prompt; phas… Continuous Empirical Benchmarking #317: Commit ee6cc27 pushed by ParsaVictor
1m 25s main
main
1m 25s
1.4.0: traceback functions vote, function list for every prompt; phase-1 priors measured; fresh jsoup holdout confirms S1 Continuous Empirical Benchmarking #316: Pull request #144 opened by ParsaVictor
1m 39s s18/phase1-priors
s18/phase1-priors
1m 39s
Measured: v1.3.0 run once on Lite and Verified; function-level denomi… Continuous Empirical Benchmarking #315: Commit e7a7819 pushed by ParsaVictor
1m 49s main
main
1m 49s
Measured: v1.3.0 once on Lite/Verified; function-level denominator fix Continuous Empirical Benchmarking #314: Pull request #143 opened by ParsaVictor
1m 22s s18/phase0-tables
s18/phase0-tables
1m 22s
docs: session 18 brief (state, rules, phases, competitor-inspired pri… Continuous Empirical Benchmarking #313: Commit 6562779 pushed by ParsaVictor
1m 28s main
main
1m 28s
docs: session 18 brief Continuous Empirical Benchmarking #312: Pull request #142 opened by ParsaVictor
1m 53s phase-o/session18-brief
phase-o/session18-brief
1m 53s
1.3.0: named files and functions_to_look for reports; short-question … Continuous Empirical Benchmarking #311: Commit 6e94b91 pushed by ParsaVictor
1m 48s main
main
1m 48s
1.3.0 Continuous Empirical Benchmarking #310: Pull request #141 opened by ParsaVictor
1m 26s phase-o/release-1.3.0
phase-o/release-1.3.0
1m 26s
Function level: classes out + file prior (dev func Acc@5 0.268 → 0.32… Continuous Empirical Benchmarking #309: Commit 7106fd7 pushed by ParsaVictor
1m 49s main
main
1m 49s
Function level: classes out + file prior (dev func Acc@5 0.268 → 0.323); functions_to_look; Verified & ablation Continuous Empirical Benchmarking #308: Pull request #140 opened by ParsaVictor
2m 8s phase-o/function-level-2
phase-o/function-level-2
2m 8s
mcp: exit when the client closes stdin; no dashboard tab for a worksp… Continuous Empirical Benchmarking #307: Commit ee1c4b9 pushed by ParsaVictor
1m 54s main
main
1m 54s
MCP: exit on stdin close (no orphan servers); no empty dashboard for an unindexed workspace Continuous Empirical Benchmarking #306: Pull request #139 opened by ParsaVictor
1m 54s phase-o/no-empty-dashboard
phase-o/no-empty-dashboard
1m 54s
function-level: definitions in packet --json for reports; local-LLM… Continuous Empirical Benchmarking #305: Commit 6cb01a4 pushed by ParsaVictor
1m 43s main
main
1m 43s
Function-level definitions for reports; local-LLM stage verdict Continuous Empirical Benchmarking #304: Pull request #138 opened by ParsaVictor
1m 48s phase-o/function-level
phase-o/function-level
1m 48s
reports: files the report names vote in the localisation list (dev Ac… Continuous Empirical Benchmarking #303: Commit 272fad0 pushed by ParsaVictor
1m 14s main
main
1m 14s
Reports: named files vote in where_to_look (dev Acc@1 0.249 → 0.298); LocAgent head-to-head; paper draft Continuous Empirical Benchmarking #302: Pull request #137 opened by ParsaVictor
1m 41s phase-o/named-files
phase-o/named-files
1m 41s
Plain-language list fusion; two fresh holdouts (cobra, axios); baseli… Continuous Empirical Benchmarking #301: Commit 2feca12 pushed by ParsaVictor
2m 4s main
main
2m 4s
Plain-language list fusion; two fresh holdouts (cobra, axios); baseline path-match fix Continuous Empirical Benchmarking #300: Pull request #136 opened by ParsaVictor
1m 23s phase-o/concept-holdout3
phase-o/concept-holdout3
1m 23s
1.2.0: issue localisation (SWE-bench Lite holdout Acc@5 0.587 → 0.750… Continuous Empirical Benchmarking #299: Commit c50d555 pushed by ParsaVictor
2m 1s main
main
2m 1s
1.2.0: issue localisation (SWE-bench Lite holdout Acc@5 0.587 → 0.750 vs BM25), where_to_look, 8× faster cold index Continuous Empirical Benchmarking #298: Pull request #135 opened by ParsaVictor
1m 13s phase-o/release-1.2.0
phase-o/release-1.2.0
1m 13s
Issue mode: definition-level ranking + report hygiene (SWE dev Acc@5 … Continuous Empirical Benchmarking #297: Commit d6854b6 pushed by ParsaVictor
1m 25s main
main
1m 25s
Issue mode: definition-level ranking + report hygiene (SWE dev Acc@5 0.456 → 0.596) Continuous Empirical Benchmarking #296: Pull request #134 synchronize by ParsaVictor
1m 43s phase-o/issue-hygiene
phase-o/issue-hygiene
1m 43s