Workflow runs · wlu03/pattern-driven-optimization-benchmark · GitHub

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows

9 workflow runs

9 workflow runs

fix(modal+scoring): chat template + <think> fallback for reasoning mo… Multi-Architecture Benchmark #9: Commit 958e21c pushed by wlu03

30m 21s main

main

30m 21s

feat(modal): add Pareto sweep driver scripts + smoke profile Multi-Architecture Benchmark #8: Commit 7067c2b pushed by wlu03

30m 21s main

main

30m 21s

feat(modal): wire CoT (reasoning_content) capture for reasoning models Multi-Architecture Benchmark #7: Commit 27d4e4a pushed by wlu03

30m 24s main

main

30m 24s

audit P1 #9-14: BENCH hooks + per-regime table + bib + LaTeX + setup-… Multi-Architecture Benchmark #6: Commit d3ba3e9 pushed by wlu03

30m 25s main

main

30m 25s

audit: P0 + P1 fixes from pre-submission scientific-validity review Multi-Architecture Benchmark #5: Commit b7f4a28 pushed by wlu03

30m 23s main

main

30m 23s

fix: 3 readiness bugs found during pre-evaluation verification Multi-Architecture Benchmark #4: Commit cb9a68b pushed by wlu03

30m 23s main

main

30m 23s

fix: zero non-resistant variants in active dataset (1110/1110 ✓) Multi-Architecture Benchmark #3: Commit 742dec4 pushed by wlu03

30m 21s main

main

30m 21s

fix(compiler-resistance): tighten HR-2 + per-pattern threshold + main… Multi-Architecture Benchmark #2: Commit a358ec5 pushed by wlu03

30m 20s main

main

30m 20s

feat: CF+HR held-out wave 4 (8 patterns) + COMP regen to 700/23-combo… Multi-Architecture Benchmark #1: Commit 51dc9b9 pushed by wlu03

30m 18s main

main

30m 18s