{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KL2DYJCMBMUMKYUPB4ARG4M4S3","short_pith_number":"pith:KL2DYJCM","schema_version":"1.0","canonical_sha256":"52f43c244c0b28c5628f0f0113719c96f37884e4c4ed92eb59a1f90284e92094","source":{"kind":"arxiv","id":"1709.02899","version":1},"attestation_state":"computed","paper":{"title":"Estimating the theoretical error rate for prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Adeline Lo, Herman Chernoff, Shaw-Hwa Lo, Tian Zheng","submitted_at":"2017-09-09T03:28:47Z","abstract_excerpt":"Prediction for very large data sets is typically carried out in two stages, variable selection and pattern recognition. Ordinarily variable selection involves seeing how well individual explanatory variables are correlated with the dependent variable. This practice neglects the possible interactions among the variables. Simulations have shown that a statistic I, that we used for variable selection is much better correlated with predictivity than significance levels. We explain this by defining theoretical predictivity and show how I is related to predictivity. We calculate the biases of the ov"},"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":"1709.02899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-09-09T03:28:47Z","cross_cats_sorted":[],"title_canon_sha256":"0a76cef023f5e120f5d235f676f898502fbba1880b8027184539bc7d0bf69975","abstract_canon_sha256":"b23996f4070fb87acff0f96ec89ee2b6017ce4f8f82818f67866a12043975c5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:40.171828Z","signature_b64":"DdFLuz9LJtsKDJ9mPXRpalw72lg3WQB9gggrSM+ehcf6Nrgj9UYImGFN+KQcVTku8mkgHbMVHIQRfe66+dSvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52f43c244c0b28c5628f0f0113719c96f37884e4c4ed92eb59a1f90284e92094","last_reissued_at":"2026-05-18T00:35:40.171182Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:40.171182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimating the theoretical error rate for prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Adeline Lo, Herman Chernoff, Shaw-Hwa Lo, Tian Zheng","submitted_at":"2017-09-09T03:28:47Z","abstract_excerpt":"Prediction for very large data sets is typically carried out in two stages, variable selection and pattern recognition. Ordinarily variable selection involves seeing how well individual explanatory variables are correlated with the dependent variable. This practice neglects the possible interactions among the variables. Simulations have shown that a statistic I, that we used for variable selection is much better correlated with predictivity than significance levels. We explain this by defining theoretical predictivity and show how I is related to predictivity. We calculate the biases of the ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02899","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":"1709.02899","created_at":"2026-05-18T00:35:40.171266+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.02899v1","created_at":"2026-05-18T00:35:40.171266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02899","created_at":"2026-05-18T00:35:40.171266+00:00"},{"alias_kind":"pith_short_12","alias_value":"KL2DYJCMBMUM","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"KL2DYJCMBMUMKYUP","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"KL2DYJCM","created_at":"2026-05-18T12:31:24.725408+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/KL2DYJCMBMUMKYUPB4ARG4M4S3","json":"https://pith.science/pith/KL2DYJCMBMUMKYUPB4ARG4M4S3.json","graph_json":"https://pith.science/api/pith-number/KL2DYJCMBMUMKYUPB4ARG4M4S3/graph.json","events_json":"https://pith.science/api/pith-number/KL2DYJCMBMUMKYUPB4ARG4M4S3/events.json","paper":"https://pith.science/paper/KL2DYJCM"},"agent_actions":{"view_html":"https://pith.science/pith/KL2DYJCMBMUMKYUPB4ARG4M4S3","download_json":"https://pith.science/pith/KL2DYJCMBMUMKYUPB4ARG4M4S3.json","view_paper":"https://pith.science/paper/KL2DYJCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.02899&json=true","fetch_graph":"https://pith.science/api/pith-number/KL2DYJCMBMUMKYUPB4ARG4M4S3/graph.json","fetch_events":"https://pith.science/api/pith-number/KL2DYJCMBMUMKYUPB4ARG4M4S3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KL2DYJCMBMUMKYUPB4ARG4M4S3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KL2DYJCMBMUMKYUPB4ARG4M4S3/action/storage_attestation","attest_author":"https://pith.science/pith/KL2DYJCMBMUMKYUPB4ARG4M4S3/action/author_attestation","sign_citation":"https://pith.science/pith/KL2DYJCMBMUMKYUPB4ARG4M4S3/action/citation_signature","submit_replication":"https://pith.science/pith/KL2DYJCMBMUMKYUPB4ARG4M4S3/action/replication_record"}},"created_at":"2026-05-18T00:35:40.171266+00:00","updated_at":"2026-05-18T00:35:40.171266+00:00"}