{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M7NF5ZRKRVPCRXLCTDNIVSJKBQ","short_pith_number":"pith:M7NF5ZRK","schema_version":"1.0","canonical_sha256":"67da5ee62a8d5e28dd6298da8ac92a0c3ace5e92d435dde5948213a691ecf5b5","source":{"kind":"arxiv","id":"2605.21528","version":1},"attestation_state":"computed","paper":{"title":"A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lican Huang, Rui Huang","submitted_at":"2026-05-19T16:57:56Z","abstract_excerpt":"Accurate and reproducible disease risk prediction remains challenging due to heterogeneous features, limited samples, and severe class imbalance. This study introduces yvsoucom-iterkit, a deterministic and log-driven automated machine learning framework that formulates pipeline optimization as a fully reproducible, configuration-level system. Each pipeline is encoded as a traceable log entity, enabling analysis of component attribution, interactions, similarity, and cross-seed robustness. Experiments on the Pima Indians Diabetes and Stroke datasets across more than 18,000 pipeline configuratio"},"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":"2605.21528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T16:57:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c64dd2b484a7a83e5e1d323ab4bcf759935c423fc7a59a5fa8f3f0daf0ce987d","abstract_canon_sha256":"cf06a0442edfd5bc5b49f0ae4cd9bcd53aadd73881498bfcd851409f85735625"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T00:02:27.717064Z","signature_b64":"y8wjZ6+xdQgdLCgXK9WZw5xGPrWaLMlDF4LxIJr23D7GcyOW2ApbCRNN8PcPdu5x9bqCaFQfqjHPNV7gNGy2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67da5ee62a8d5e28dd6298da8ac92a0c3ace5e92d435dde5948213a691ecf5b5","last_reissued_at":"2026-05-22T00:02:27.716670Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T00:02:27.716670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lican Huang, Rui Huang","submitted_at":"2026-05-19T16:57:56Z","abstract_excerpt":"Accurate and reproducible disease risk prediction remains challenging due to heterogeneous features, limited samples, and severe class imbalance. This study introduces yvsoucom-iterkit, a deterministic and log-driven automated machine learning framework that formulates pipeline optimization as a fully reproducible, configuration-level system. Each pipeline is encoded as a traceable log entity, enabling analysis of component attribution, interactions, similarity, and cross-seed robustness. Experiments on the Pima Indians Diabetes and Stroke datasets across more than 18,000 pipeline configuratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21528","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.21528/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2605.21528","created_at":"2026-05-22T00:02:27.716726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21528v1","created_at":"2026-05-22T00:02:27.716726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21528","created_at":"2026-05-22T00:02:27.716726+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7NF5ZRKRVPC","created_at":"2026-05-22T00:02:27.716726+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7NF5ZRKRVPCRXLC","created_at":"2026-05-22T00:02:27.716726+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7NF5ZRK","created_at":"2026-05-22T00:02:27.716726+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/M7NF5ZRKRVPCRXLCTDNIVSJKBQ","json":"https://pith.science/pith/M7NF5ZRKRVPCRXLCTDNIVSJKBQ.json","graph_json":"https://pith.science/api/pith-number/M7NF5ZRKRVPCRXLCTDNIVSJKBQ/graph.json","events_json":"https://pith.science/api/pith-number/M7NF5ZRKRVPCRXLCTDNIVSJKBQ/events.json","paper":"https://pith.science/paper/M7NF5ZRK"},"agent_actions":{"view_html":"https://pith.science/pith/M7NF5ZRKRVPCRXLCTDNIVSJKBQ","download_json":"https://pith.science/pith/M7NF5ZRKRVPCRXLCTDNIVSJKBQ.json","view_paper":"https://pith.science/paper/M7NF5ZRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21528&json=true","fetch_graph":"https://pith.science/api/pith-number/M7NF5ZRKRVPCRXLCTDNIVSJKBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/M7NF5ZRKRVPCRXLCTDNIVSJKBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7NF5ZRKRVPCRXLCTDNIVSJKBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7NF5ZRKRVPCRXLCTDNIVSJKBQ/action/storage_attestation","attest_author":"https://pith.science/pith/M7NF5ZRKRVPCRXLCTDNIVSJKBQ/action/author_attestation","sign_citation":"https://pith.science/pith/M7NF5ZRKRVPCRXLCTDNIVSJKBQ/action/citation_signature","submit_replication":"https://pith.science/pith/M7NF5ZRKRVPCRXLCTDNIVSJKBQ/action/replication_record"}},"created_at":"2026-05-22T00:02:27.716726+00:00","updated_at":"2026-05-22T00:02:27.716726+00:00"}