{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TFTKQMJ5HBP3O2SEKN6F6AKQMO","short_pith_number":"pith:TFTKQMJ5","schema_version":"1.0","canonical_sha256":"9966a8313d385fb76a44537c5f0150638b170c5315c128730a987f9eac3019fa","source":{"kind":"arxiv","id":"2505.22746","version":1},"attestation_state":"computed","paper":{"title":"StarBASE-GP: Biologically-Guided Automated Machine Learning for Genotype-to-Phenotype Association Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Attri Ghosh, Jason H. Moore, Jose Guadalupe Hernandez, Nicholas Matsumoto, Philip J. Freda, Yufei Meng","submitted_at":"2025-05-28T18:05:15Z","abstract_excerpt":"We present the Star-Based Automated Single-locus and Epistasis analysis tool - Genetic Programming (StarBASE-GP), an automated framework for discovering meaningful genetic variants associated with phenotypic variation in large-scale genomic datasets. StarBASE-GP uses a genetic programming-based multi-objective optimization strategy to evolve machine learning pipelines that simultaneously maximize explanatory power (r2) and minimize pipeline complexity. Biological domain knowledge is integrated at multiple stages, including the use of nine inheritance encoding strategies to model deviations fro"},"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":"2505.22746","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-05-28T18:05:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6f4c4a90b038d64553dcf9c8a26fadd4e826f963cb08e361aadd666f693b257f","abstract_canon_sha256":"99a2ef903de697c03ff56930223fb74c354de8ab84013b649bcbed4f96e016b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:49.472493Z","signature_b64":"Jzi9S13IzprpwPAz3ff8BAJ+UCrzRusb6CDVmUKg6o8Wqi/Z1miyMe/ITpSzZJFbaoPOYO8fhwruA+SI4R8rCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9966a8313d385fb76a44537c5f0150638b170c5315c128730a987f9eac3019fa","last_reissued_at":"2026-07-05T11:11:49.471982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:49.471982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StarBASE-GP: Biologically-Guided Automated Machine Learning for Genotype-to-Phenotype Association Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Attri Ghosh, Jason H. Moore, Jose Guadalupe Hernandez, Nicholas Matsumoto, Philip J. Freda, Yufei Meng","submitted_at":"2025-05-28T18:05:15Z","abstract_excerpt":"We present the Star-Based Automated Single-locus and Epistasis analysis tool - Genetic Programming (StarBASE-GP), an automated framework for discovering meaningful genetic variants associated with phenotypic variation in large-scale genomic datasets. StarBASE-GP uses a genetic programming-based multi-objective optimization strategy to evolve machine learning pipelines that simultaneously maximize explanatory power (r2) and minimize pipeline complexity. Biological domain knowledge is integrated at multiple stages, including the use of nine inheritance encoding strategies to model deviations fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22746","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/2505.22746/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":"2505.22746","created_at":"2026-07-05T11:11:49.472043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22746v1","created_at":"2026-07-05T11:11:49.472043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22746","created_at":"2026-07-05T11:11:49.472043+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFTKQMJ5HBP3","created_at":"2026-07-05T11:11:49.472043+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFTKQMJ5HBP3O2SE","created_at":"2026-07-05T11:11:49.472043+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFTKQMJ5","created_at":"2026-07-05T11:11:49.472043+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/TFTKQMJ5HBP3O2SEKN6F6AKQMO","json":"https://pith.science/pith/TFTKQMJ5HBP3O2SEKN6F6AKQMO.json","graph_json":"https://pith.science/api/pith-number/TFTKQMJ5HBP3O2SEKN6F6AKQMO/graph.json","events_json":"https://pith.science/api/pith-number/TFTKQMJ5HBP3O2SEKN6F6AKQMO/events.json","paper":"https://pith.science/paper/TFTKQMJ5"},"agent_actions":{"view_html":"https://pith.science/pith/TFTKQMJ5HBP3O2SEKN6F6AKQMO","download_json":"https://pith.science/pith/TFTKQMJ5HBP3O2SEKN6F6AKQMO.json","view_paper":"https://pith.science/paper/TFTKQMJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22746&json=true","fetch_graph":"https://pith.science/api/pith-number/TFTKQMJ5HBP3O2SEKN6F6AKQMO/graph.json","fetch_events":"https://pith.science/api/pith-number/TFTKQMJ5HBP3O2SEKN6F6AKQMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFTKQMJ5HBP3O2SEKN6F6AKQMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFTKQMJ5HBP3O2SEKN6F6AKQMO/action/storage_attestation","attest_author":"https://pith.science/pith/TFTKQMJ5HBP3O2SEKN6F6AKQMO/action/author_attestation","sign_citation":"https://pith.science/pith/TFTKQMJ5HBP3O2SEKN6F6AKQMO/action/citation_signature","submit_replication":"https://pith.science/pith/TFTKQMJ5HBP3O2SEKN6F6AKQMO/action/replication_record"}},"created_at":"2026-07-05T11:11:49.472043+00:00","updated_at":"2026-07-05T11:11:49.472043+00:00"}