{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FQBA73SBC5RSL3EAVTO5YVCNPK","short_pith_number":"pith:FQBA73SB","schema_version":"1.0","canonical_sha256":"2c020fee41176325ec80acdddc544d7a841bebecd56ee32f43b915ed55922653","source":{"kind":"arxiv","id":"2104.08961","version":2},"attestation_state":"computed","paper":{"title":"A cross-study analysis of drug response prediction in cancer cell lines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Alexander Partin, Austin Clyde, Cristina Garcia-Cardona, Eric Stahlberg, Fangfang Xia, George Zaki, Hyunseung Yoo, James Doroshow, Jason Gans, Jonathan Allen, Judith Cohn, Justin M. Wozniak, Maulik Shukla, Pinyi Lu, Prasanna Balaprakash, Rick Stevens, Sergei Maslov, Stewart He, Thomas Brettin, Veronika Dubinkina, Xiaotian Duan, Ya Ju Fan, Yitan Zhu, Yvonne Evrard","submitted_at":"2021-04-18T21:40:51Z","abstract_excerpt":"To enable personalized cancer treatment, machine learning models have been developed to predict drug response as a function of tumor and drug features. However, most algorithm development efforts have relied on cross validation within a single study to assess model accuracy. While an essential first step, cross validation within a biological data set typically provides an overly optimistic estimate of the prediction performance on independent test sets. To provide a more rigorous assessment of model generalizability between different studies, we use machine learning to analyze five publicly av"},"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":"2104.08961","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2021-04-18T21:40:51Z","cross_cats_sorted":[],"title_canon_sha256":"dc8a466fb9cb2ad2746287e2b69486bff35c74a67231a4774bf665dd6c22da99","abstract_canon_sha256":"5be30878d63692fa9b49fb1a4cdccf5aab5d40cb584997194edc3a316ec0e8ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:49.455463Z","signature_b64":"4doZ5K5TV7KtuNWusEU067cNrjX64Ns3R9XTzbCsUETwLckzdLvB77MtOxfM0DanE8y3nj726XNn80xsCXlKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c020fee41176325ec80acdddc544d7a841bebecd56ee32f43b915ed55922653","last_reissued_at":"2026-07-05T03:05:49.454957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:49.454957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A cross-study analysis of drug response prediction in cancer cell lines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Alexander Partin, Austin Clyde, Cristina Garcia-Cardona, Eric Stahlberg, Fangfang Xia, George Zaki, Hyunseung Yoo, James Doroshow, Jason Gans, Jonathan Allen, Judith Cohn, Justin M. Wozniak, Maulik Shukla, Pinyi Lu, Prasanna Balaprakash, Rick Stevens, Sergei Maslov, Stewart He, Thomas Brettin, Veronika Dubinkina, Xiaotian Duan, Ya Ju Fan, Yitan Zhu, Yvonne Evrard","submitted_at":"2021-04-18T21:40:51Z","abstract_excerpt":"To enable personalized cancer treatment, machine learning models have been developed to predict drug response as a function of tumor and drug features. However, most algorithm development efforts have relied on cross validation within a single study to assess model accuracy. While an essential first step, cross validation within a biological data set typically provides an overly optimistic estimate of the prediction performance on independent test sets. To provide a more rigorous assessment of model generalizability between different studies, we use machine learning to analyze five publicly av"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08961","kind":"arxiv","version":2},"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/2104.08961/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":"2104.08961","created_at":"2026-07-05T03:05:49.455022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08961v2","created_at":"2026-07-05T03:05:49.455022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08961","created_at":"2026-07-05T03:05:49.455022+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQBA73SBC5RS","created_at":"2026-07-05T03:05:49.455022+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQBA73SBC5RSL3EA","created_at":"2026-07-05T03:05:49.455022+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQBA73SB","created_at":"2026-07-05T03:05:49.455022+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/FQBA73SBC5RSL3EAVTO5YVCNPK","json":"https://pith.science/pith/FQBA73SBC5RSL3EAVTO5YVCNPK.json","graph_json":"https://pith.science/api/pith-number/FQBA73SBC5RSL3EAVTO5YVCNPK/graph.json","events_json":"https://pith.science/api/pith-number/FQBA73SBC5RSL3EAVTO5YVCNPK/events.json","paper":"https://pith.science/paper/FQBA73SB"},"agent_actions":{"view_html":"https://pith.science/pith/FQBA73SBC5RSL3EAVTO5YVCNPK","download_json":"https://pith.science/pith/FQBA73SBC5RSL3EAVTO5YVCNPK.json","view_paper":"https://pith.science/paper/FQBA73SB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08961&json=true","fetch_graph":"https://pith.science/api/pith-number/FQBA73SBC5RSL3EAVTO5YVCNPK/graph.json","fetch_events":"https://pith.science/api/pith-number/FQBA73SBC5RSL3EAVTO5YVCNPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQBA73SBC5RSL3EAVTO5YVCNPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQBA73SBC5RSL3EAVTO5YVCNPK/action/storage_attestation","attest_author":"https://pith.science/pith/FQBA73SBC5RSL3EAVTO5YVCNPK/action/author_attestation","sign_citation":"https://pith.science/pith/FQBA73SBC5RSL3EAVTO5YVCNPK/action/citation_signature","submit_replication":"https://pith.science/pith/FQBA73SBC5RSL3EAVTO5YVCNPK/action/replication_record"}},"created_at":"2026-07-05T03:05:49.455022+00:00","updated_at":"2026-07-05T03:05:49.455022+00:00"}