{"paper":{"title":"CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An LLM agent autonomously discovers algorithms for scientific image tasks that outperform baselines.","cross_cats":["physics.data-an"],"primary_cat":"cs.AI","authors_text":"Dishant Beniwal, Hemant Sharma, Mathew J. Cherukara, Ming Du, Songyuan Tang, Xiangyu Yin, Yanqi Luo","submitted_at":"2026-05-12T00:24:30Z","abstract_excerpt":"Scientific data processing often requires task-specific algorithms or AI models, creating a barrier for domain scientists who need to analyze their data but may not have extensive computing or image-processing expertise. This barrier is especially pronounced when data are noisy, have a high dynamic range, are sparsely labeled, or are only loosely specified. We introduce CVEvolve, an autonomous agentic harness with a zero-code interface for scientific data-processing algorithm discovery. CVEvolve combines a multi-round search strategy with tools for code execution, evaluation implementation, hi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across these tasks, CVEvolve discovers algorithms that improve over baseline methods, while holdout test tracking helps identify candidates that generalize better than later over-optimized alternatives.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the LLM-powered multi-round search with lineage-aware sampling and holdout evaluation can reliably produce generalizable algorithms for unstructured scientific data without extensive human guidance or post-hoc tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CVEvolve uses LLM agents with lineage-aware search to autonomously discover algorithms that outperform baselines on scientific image tasks including registration, peak detection, and segmentation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An LLM agent autonomously discovers algorithms for scientific image tasks that outperform baselines.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d272aaafe08f2abfee89a2775448d71a876b44a036ecd8e74553775de0e7d855"},"source":{"id":"2605.11359","kind":"arxiv","version":2},"verdict":{"id":"4b50180b-6f61-42b7-a7cd-ed16762f2992","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T02:38:44.681800Z","strongest_claim":"Across these tasks, CVEvolve discovers algorithms that improve over baseline methods, while holdout test tracking helps identify candidates that generalize better than later over-optimized alternatives.","one_line_summary":"CVEvolve uses LLM agents with lineage-aware search to autonomously discover algorithms that outperform baselines on scientific image tasks including registration, peak detection, and segmentation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the LLM-powered multi-round search with lineage-aware sampling and holdout evaluation can reliably produce generalizable algorithms for unstructured scientific data without extensive human guidance or post-hoc tuning.","pith_extraction_headline":"An LLM agent autonomously discovers algorithms for scientific image tasks that outperform baselines."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11359/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T04:22:00.586493Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T12:37:23.079996Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T10:01:16.850656Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T08:30:59.176553Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9943b0e94bb21bac7267f3d932f07288c10b27998e3d34942aece40df1825557"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}