$ bun run src/index.ts --doi "10.48550/arXiv.2509.18480" --url "https://arxiv.org/pdf/2509.18480" --recipe-fixture "../fixtures/phase1a/simplefold3b_phase1a_9k9ya_v1.json" --model "simplefold-3b" --run-id "phase1a-repeat-2026-05-18-simplefold-3b-9k9ya-r3" --benchmark
[pipeline] start 10.48550/arXiv.2509.18480
[pipeline] healthchecks
[pipeline] cite-verify
[pipeline] cite-verify ok via cache
[pipeline] fetch_pdf
[pipeline] pdf at https://eigen-reprod-atlas-pdf-parse.raul-chio-leon.workers.dev/pdf/papers/10.48550_arXiv.2509.18480.pdf
[pipeline] reader fixture ../fixtures/phase1a/simplefold3b_phase1a_9k9ya_v1.json
[pipeline] recipe extracted; headline phase1a_frozen_benchmark_no_published_headline = 0
[pipeline] verify all citations in recipe quotes
[pipeline] executor: deterministic loop over evaluation_set
[pipeline] model simplefold-3b
[pipeline] target 9K9Y:A
[pipeline] simplefold_cli pid=72522 elapsed=60s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=120s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=180s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=240s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=300s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=360s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=420s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=480s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=540s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=600s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=660s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=720s peak_rss_gb=34.35
[pipeline] simplefold_cli pid=72522 elapsed=780s peak_rss_gb=34.35
[pipeline] validator benchmark mode
[pipeline] verdict successful_with_caveat diagnosis: Benchmark slice mode: 1/1 targets scored. No published headline metric is being reproduced; interpret per-target scores 
[pipeline] wrote /Users/raulzhou/Projects/eigen-reprod-atlas/pilot/local-runner/results-phase1a-repeats/phase1a-repeat-2026-05-18-simplefold-3b-9k9ya-r3

Pipeline complete. Status: successful_with_caveat