{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QKGOE3F5AKN4IDOEXRRHXIYDFC","short_pith_number":"pith:QKGOE3F5","schema_version":"1.0","canonical_sha256":"828ce26cbd029bc40dc4bc627ba30328aee7525006f53a6194f18845217f72c0","source":{"kind":"arxiv","id":"1509.04897","version":1},"attestation_state":"computed","paper":{"title":"Sample size determination for training cancer classifiers from microarray and RNA-seq data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Kevin K. Dobbin, Sandra Safo, Xiao Song","submitted_at":"2015-09-16T12:10:11Z","abstract_excerpt":"The objective of many high-dimensional microarray and RNA-seq studies is to develop a classifier of cancer patients based on characteristics of their disease. The germinal center B-cell (GCB) classifier study in lymphoma and the National Cancer Institute's Director's Challenge lung (DC-lung) study are two examples. In recent years, such classifiers are often developed using regularized regression, such as the lasso. A critical question is whether a better classifier can be developed from a larger training set size and, if so, how large the training set should be. This paper examines these two "},"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":"1509.04897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2015-09-16T12:10:11Z","cross_cats_sorted":[],"title_canon_sha256":"27864fce30f6969805c303c9fadcb7060cc31489ed90c364260f0147b26ef18c","abstract_canon_sha256":"e5cbf8ec104b8758696d6702a2fdf697631eddfaae95edcb43b20c564fab05a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:51.398061Z","signature_b64":"A7zZt/KNAA3XpBBuaVxNm2wNGOuWMc1Mj/wjoBMJote3dIi8aLrYe5y6yGLmYvhAXbf64neA6/QJ63CbvzaOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"828ce26cbd029bc40dc4bc627ba30328aee7525006f53a6194f18845217f72c0","last_reissued_at":"2026-05-18T01:32:51.397338Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:51.397338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample size determination for training cancer classifiers from microarray and RNA-seq data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Kevin K. Dobbin, Sandra Safo, Xiao Song","submitted_at":"2015-09-16T12:10:11Z","abstract_excerpt":"The objective of many high-dimensional microarray and RNA-seq studies is to develop a classifier of cancer patients based on characteristics of their disease. The germinal center B-cell (GCB) classifier study in lymphoma and the National Cancer Institute's Director's Challenge lung (DC-lung) study are two examples. In recent years, such classifiers are often developed using regularized regression, such as the lasso. A critical question is whether a better classifier can be developed from a larger training set size and, if so, how large the training set should be. This paper examines these two "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.04897","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":"1509.04897","created_at":"2026-05-18T01:32:51.397458+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.04897v1","created_at":"2026-05-18T01:32:51.397458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.04897","created_at":"2026-05-18T01:32:51.397458+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKGOE3F5AKN4","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKGOE3F5AKN4IDOE","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKGOE3F5","created_at":"2026-05-18T12:29:37.295048+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/QKGOE3F5AKN4IDOEXRRHXIYDFC","json":"https://pith.science/pith/QKGOE3F5AKN4IDOEXRRHXIYDFC.json","graph_json":"https://pith.science/api/pith-number/QKGOE3F5AKN4IDOEXRRHXIYDFC/graph.json","events_json":"https://pith.science/api/pith-number/QKGOE3F5AKN4IDOEXRRHXIYDFC/events.json","paper":"https://pith.science/paper/QKGOE3F5"},"agent_actions":{"view_html":"https://pith.science/pith/QKGOE3F5AKN4IDOEXRRHXIYDFC","download_json":"https://pith.science/pith/QKGOE3F5AKN4IDOEXRRHXIYDFC.json","view_paper":"https://pith.science/paper/QKGOE3F5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.04897&json=true","fetch_graph":"https://pith.science/api/pith-number/QKGOE3F5AKN4IDOEXRRHXIYDFC/graph.json","fetch_events":"https://pith.science/api/pith-number/QKGOE3F5AKN4IDOEXRRHXIYDFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKGOE3F5AKN4IDOEXRRHXIYDFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKGOE3F5AKN4IDOEXRRHXIYDFC/action/storage_attestation","attest_author":"https://pith.science/pith/QKGOE3F5AKN4IDOEXRRHXIYDFC/action/author_attestation","sign_citation":"https://pith.science/pith/QKGOE3F5AKN4IDOEXRRHXIYDFC/action/citation_signature","submit_replication":"https://pith.science/pith/QKGOE3F5AKN4IDOEXRRHXIYDFC/action/replication_record"}},"created_at":"2026-05-18T01:32:51.397458+00:00","updated_at":"2026-05-18T01:32:51.397458+00:00"}