{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DEJZZCM4MQ5OTC3P4B5MXPR74F","short_pith_number":"pith:DEJZZCM4","schema_version":"1.0","canonical_sha256":"19139c899c643ae98b6fe07acbbe3fe14516eec33f4ec70e1547545e149171e5","source":{"kind":"arxiv","id":"2605.11359","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.11359","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T00:24:30Z","cross_cats_sorted":["physics.data-an"],"title_canon_sha256":"522411d31630d3afca3cfc91f5bdd5ea8f6e3f6a56a60c7cc47369a1eeb6dae6","abstract_canon_sha256":"bcc0f03d852f427bb8da06409a815175062778e985672f4547b332d21f06b8dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:35.640477Z","signature_b64":"QtjIhpKcWvIOlgd5V0R/7A11L/CD6rgxnz6sdCrstYiecrd4kEVGA/YWo3XPgTyAlOfih1mgdS/uHpfixlXiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19139c899c643ae98b6fe07acbbe3fe14516eec33f4ec70e1547545e149171e5","last_reissued_at":"2026-05-26T01:02:35.639768Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:35.639768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.11359","created_at":"2026-05-26T01:02:35.639865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11359v2","created_at":"2026-05-26T01:02:35.639865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11359","created_at":"2026-05-26T01:02:35.639865+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEJZZCM4MQ5O","created_at":"2026-05-26T01:02:35.639865+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEJZZCM4MQ5OTC3P","created_at":"2026-05-26T01:02:35.639865+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEJZZCM4","created_at":"2026-05-26T01:02:35.639865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEJZZCM4MQ5OTC3P4B5MXPR74F","json":"https://pith.science/pith/DEJZZCM4MQ5OTC3P4B5MXPR74F.json","graph_json":"https://pith.science/api/pith-number/DEJZZCM4MQ5OTC3P4B5MXPR74F/graph.json","events_json":"https://pith.science/api/pith-number/DEJZZCM4MQ5OTC3P4B5MXPR74F/events.json","paper":"https://pith.science/paper/DEJZZCM4"},"agent_actions":{"view_html":"https://pith.science/pith/DEJZZCM4MQ5OTC3P4B5MXPR74F","download_json":"https://pith.science/pith/DEJZZCM4MQ5OTC3P4B5MXPR74F.json","view_paper":"https://pith.science/paper/DEJZZCM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11359&json=true","fetch_graph":"https://pith.science/api/pith-number/DEJZZCM4MQ5OTC3P4B5MXPR74F/graph.json","fetch_events":"https://pith.science/api/pith-number/DEJZZCM4MQ5OTC3P4B5MXPR74F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEJZZCM4MQ5OTC3P4B5MXPR74F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEJZZCM4MQ5OTC3P4B5MXPR74F/action/storage_attestation","attest_author":"https://pith.science/pith/DEJZZCM4MQ5OTC3P4B5MXPR74F/action/author_attestation","sign_citation":"https://pith.science/pith/DEJZZCM4MQ5OTC3P4B5MXPR74F/action/citation_signature","submit_replication":"https://pith.science/pith/DEJZZCM4MQ5OTC3P4B5MXPR74F/action/replication_record"}},"created_at":"2026-05-26T01:02:35.639865+00:00","updated_at":"2026-05-26T01:02:35.639865+00:00"}