{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:AAHUOGJNE4UXHNCZXFLNW4P5KM","short_pith_number":"pith:AAHUOGJN","schema_version":"1.0","canonical_sha256":"000f47192d272973b459b956db71fd531323b73bb299c01b05f58016eb3f6139","source":{"kind":"arxiv","id":"1601.07925","version":1},"attestation_state":"computed","paper":{"title":"Automating biomedical data science through tree-based pipeline optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Jason H. Moore, La Creis Kidd, Nicole A. Lavender, Peter C. Andrews, Randal S. Olson, Ryan J. Urbanowicz","submitted_at":"2016-01-28T21:45:55Z","abstract_excerpt":"Over the past decade, data science and machine learning has grown from a mysterious art form to a staple tool across a variety of fields in academia, business, and government. In this paper, we introduce the concept of tree-based pipeline optimization for automating one of the most tedious parts of machine learning---pipeline design. We implement a Tree-based Pipeline Optimization Tool (TPOT) and demonstrate its effectiveness on a series of simulated and real-world genetic data sets. In particular, we show that TPOT can build machine learning pipelines that achieve competitive classification a"},"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":"1601.07925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-01-28T21:45:55Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"861c3bb09b606ce3ac2c64748b27917abba734f9eec7a92cf2ac4f327f492fa5","abstract_canon_sha256":"1f93076b4010e016584db1a70b72c03a9e5e13c1a7bbb9d90d56c905cf0200ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:41.478934Z","signature_b64":"gZYWUE/lvsZHbhDHtw/lXbIpZGkCPhZhXo0bj9KAEw7XUE9CkuWSG0ni51XV29E5TMMZcUVpjwKins1eDuUaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"000f47192d272973b459b956db71fd531323b73bb299c01b05f58016eb3f6139","last_reissued_at":"2026-05-18T01:21:41.478440Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:41.478440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automating biomedical data science through tree-based pipeline optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Jason H. Moore, La Creis Kidd, Nicole A. Lavender, Peter C. Andrews, Randal S. Olson, Ryan J. Urbanowicz","submitted_at":"2016-01-28T21:45:55Z","abstract_excerpt":"Over the past decade, data science and machine learning has grown from a mysterious art form to a staple tool across a variety of fields in academia, business, and government. In this paper, we introduce the concept of tree-based pipeline optimization for automating one of the most tedious parts of machine learning---pipeline design. We implement a Tree-based Pipeline Optimization Tool (TPOT) and demonstrate its effectiveness on a series of simulated and real-world genetic data sets. In particular, we show that TPOT can build machine learning pipelines that achieve competitive classification a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.07925","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":""},"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":"1601.07925","created_at":"2026-05-18T01:21:41.478517+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.07925v1","created_at":"2026-05-18T01:21:41.478517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.07925","created_at":"2026-05-18T01:21:41.478517+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAHUOGJNE4UX","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAHUOGJNE4UXHNCZ","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAHUOGJN","created_at":"2026-05-18T12:30:04.600751+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/AAHUOGJNE4UXHNCZXFLNW4P5KM","json":"https://pith.science/pith/AAHUOGJNE4UXHNCZXFLNW4P5KM.json","graph_json":"https://pith.science/api/pith-number/AAHUOGJNE4UXHNCZXFLNW4P5KM/graph.json","events_json":"https://pith.science/api/pith-number/AAHUOGJNE4UXHNCZXFLNW4P5KM/events.json","paper":"https://pith.science/paper/AAHUOGJN"},"agent_actions":{"view_html":"https://pith.science/pith/AAHUOGJNE4UXHNCZXFLNW4P5KM","download_json":"https://pith.science/pith/AAHUOGJNE4UXHNCZXFLNW4P5KM.json","view_paper":"https://pith.science/paper/AAHUOGJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.07925&json=true","fetch_graph":"https://pith.science/api/pith-number/AAHUOGJNE4UXHNCZXFLNW4P5KM/graph.json","fetch_events":"https://pith.science/api/pith-number/AAHUOGJNE4UXHNCZXFLNW4P5KM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAHUOGJNE4UXHNCZXFLNW4P5KM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAHUOGJNE4UXHNCZXFLNW4P5KM/action/storage_attestation","attest_author":"https://pith.science/pith/AAHUOGJNE4UXHNCZXFLNW4P5KM/action/author_attestation","sign_citation":"https://pith.science/pith/AAHUOGJNE4UXHNCZXFLNW4P5KM/action/citation_signature","submit_replication":"https://pith.science/pith/AAHUOGJNE4UXHNCZXFLNW4P5KM/action/replication_record"}},"created_at":"2026-05-18T01:21:41.478517+00:00","updated_at":"2026-05-18T01:21:41.478517+00:00"}