{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:BCVPMOE6HML25OP4ZP7G65CIAM","short_pith_number":"pith:BCVPMOE6","schema_version":"1.0","canonical_sha256":"08aaf6389e3b17aeb9fccbfe6f7448032b86a47c45401c2de7080b0d530f584c","source":{"kind":"arxiv","id":"1108.6043","version":1},"attestation_state":"computed","paper":{"title":"Optimal Data Split Methodology for Model Validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ME"],"primary_cat":"physics.data-an","authors_text":"Corey Bryant, Gabriel Terejanu, Kenji Miki, Rebecca Morrison, Serge Prudhomme","submitted_at":"2011-08-30T19:24:12Z","abstract_excerpt":"The decision to incorporate cross-validation into validation processes of mathematical models raises an immediate question - how should one partition the data into calibration and validation sets? We answer this question systematically: we present an algorithm to find the optimal partition of the data subject to certain constraints. While doing this, we address two critical issues: 1) that the model be evaluated with respect to predictions of a given quantity of interest and its ability to reproduce the data, and 2) that the model be highly challenged by the validation set, assuming it is prop"},"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":"1108.6043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.data-an","submitted_at":"2011-08-30T19:24:12Z","cross_cats_sorted":["math.PR","stat.ME"],"title_canon_sha256":"57ebe4bb9b63ae172df4ffa09fa1312aab2b2eeffa832fb7a511b90a7f650398","abstract_canon_sha256":"80822a8b334ed4528afe3b4fa308de380acc461b1a921a5b1ad5afdff21f593b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:14:27.956421Z","signature_b64":"fXE9bkFUGKL/MuIJYUiDY6rErek43/0+Q3haMJ9WwWoy4xqiq7FKH/MOaaE0zBgOAFrHe2RrKqexxTj2oMKMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08aaf6389e3b17aeb9fccbfe6f7448032b86a47c45401c2de7080b0d530f584c","last_reissued_at":"2026-05-18T04:14:27.955668Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:14:27.955668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Data Split Methodology for Model Validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ME"],"primary_cat":"physics.data-an","authors_text":"Corey Bryant, Gabriel Terejanu, Kenji Miki, Rebecca Morrison, Serge Prudhomme","submitted_at":"2011-08-30T19:24:12Z","abstract_excerpt":"The decision to incorporate cross-validation into validation processes of mathematical models raises an immediate question - how should one partition the data into calibration and validation sets? We answer this question systematically: we present an algorithm to find the optimal partition of the data subject to certain constraints. While doing this, we address two critical issues: 1) that the model be evaluated with respect to predictions of a given quantity of interest and its ability to reproduce the data, and 2) that the model be highly challenged by the validation set, assuming it is prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.6043","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":"1108.6043","created_at":"2026-05-18T04:14:27.955800+00:00"},{"alias_kind":"arxiv_version","alias_value":"1108.6043v1","created_at":"2026-05-18T04:14:27.955800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.6043","created_at":"2026-05-18T04:14:27.955800+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCVPMOE6HML2","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCVPMOE6HML25OP4","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCVPMOE6","created_at":"2026-05-18T12:26:24.575870+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/BCVPMOE6HML25OP4ZP7G65CIAM","json":"https://pith.science/pith/BCVPMOE6HML25OP4ZP7G65CIAM.json","graph_json":"https://pith.science/api/pith-number/BCVPMOE6HML25OP4ZP7G65CIAM/graph.json","events_json":"https://pith.science/api/pith-number/BCVPMOE6HML25OP4ZP7G65CIAM/events.json","paper":"https://pith.science/paper/BCVPMOE6"},"agent_actions":{"view_html":"https://pith.science/pith/BCVPMOE6HML25OP4ZP7G65CIAM","download_json":"https://pith.science/pith/BCVPMOE6HML25OP4ZP7G65CIAM.json","view_paper":"https://pith.science/paper/BCVPMOE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1108.6043&json=true","fetch_graph":"https://pith.science/api/pith-number/BCVPMOE6HML25OP4ZP7G65CIAM/graph.json","fetch_events":"https://pith.science/api/pith-number/BCVPMOE6HML25OP4ZP7G65CIAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCVPMOE6HML25OP4ZP7G65CIAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCVPMOE6HML25OP4ZP7G65CIAM/action/storage_attestation","attest_author":"https://pith.science/pith/BCVPMOE6HML25OP4ZP7G65CIAM/action/author_attestation","sign_citation":"https://pith.science/pith/BCVPMOE6HML25OP4ZP7G65CIAM/action/citation_signature","submit_replication":"https://pith.science/pith/BCVPMOE6HML25OP4ZP7G65CIAM/action/replication_record"}},"created_at":"2026-05-18T04:14:27.955800+00:00","updated_at":"2026-05-18T04:14:27.955800+00:00"}