{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2RK7XZPGLB3O255ILADKEGDYO3","short_pith_number":"pith:2RK7XZPG","schema_version":"1.0","canonical_sha256":"d455fbe5e65876ed77a85806a2187876e382c0769dd11e199c14be81fc1f5029","source":{"kind":"arxiv","id":"2311.14079","version":2},"attestation_state":"computed","paper":{"title":"Empirical Comparison between Cross-Validation and Mutation-Validation in Model Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abigail Morrison, Jinyang Yu, Kaustubh R. Patil, Leonard Sasse, Sami Hamdan","submitted_at":"2023-11-23T16:14:24Z","abstract_excerpt":"Mutation validation (MV) is a recently proposed approach for model selection, garnering significant interest due to its unique characteristics and potential benefits compared to the widely used cross-validation (CV) method. In this study, we empirically compared MV and $k$-fold CV using benchmark and real-world datasets. By employing Bayesian tests, we compared generalization estimates yielding three posterior probabilities: practical equivalence, CV superiority, and MV superiority. We also evaluated the differences in the capacity of the selected models and computational efficiency. We found "},"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":"2311.14079","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T16:14:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fcd236cf34b5d63e70cea214a5c41f1994d07162fe61538f72f7dd94d32ce43f","abstract_canon_sha256":"5639d825e54bce67cafba47c52de54236a66ecb9fe9efc358794f51b32a880d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:48.133065Z","signature_b64":"6SpHXR7JGKD7TF+iqHH6c7ntNxPopUzcgzpiZeeSRMfSf68a4eCc6kEA5YF21MInDvXiwvkgIlE3cCVvv915Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d455fbe5e65876ed77a85806a2187876e382c0769dd11e199c14be81fc1f5029","last_reissued_at":"2026-07-05T08:47:48.132588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:48.132588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Comparison between Cross-Validation and Mutation-Validation in Model Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abigail Morrison, Jinyang Yu, Kaustubh R. Patil, Leonard Sasse, Sami Hamdan","submitted_at":"2023-11-23T16:14:24Z","abstract_excerpt":"Mutation validation (MV) is a recently proposed approach for model selection, garnering significant interest due to its unique characteristics and potential benefits compared to the widely used cross-validation (CV) method. In this study, we empirically compared MV and $k$-fold CV using benchmark and real-world datasets. By employing Bayesian tests, we compared generalization estimates yielding three posterior probabilities: practical equivalence, CV superiority, and MV superiority. We also evaluated the differences in the capacity of the selected models and computational efficiency. We found "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14079","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/2311.14079/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":"2311.14079","created_at":"2026-07-05T08:47:48.132641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14079v2","created_at":"2026-07-05T08:47:48.132641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14079","created_at":"2026-07-05T08:47:48.132641+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RK7XZPGLB3O","created_at":"2026-07-05T08:47:48.132641+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RK7XZPGLB3O255I","created_at":"2026-07-05T08:47:48.132641+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RK7XZPG","created_at":"2026-07-05T08:47:48.132641+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/2RK7XZPGLB3O255ILADKEGDYO3","json":"https://pith.science/pith/2RK7XZPGLB3O255ILADKEGDYO3.json","graph_json":"https://pith.science/api/pith-number/2RK7XZPGLB3O255ILADKEGDYO3/graph.json","events_json":"https://pith.science/api/pith-number/2RK7XZPGLB3O255ILADKEGDYO3/events.json","paper":"https://pith.science/paper/2RK7XZPG"},"agent_actions":{"view_html":"https://pith.science/pith/2RK7XZPGLB3O255ILADKEGDYO3","download_json":"https://pith.science/pith/2RK7XZPGLB3O255ILADKEGDYO3.json","view_paper":"https://pith.science/paper/2RK7XZPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14079&json=true","fetch_graph":"https://pith.science/api/pith-number/2RK7XZPGLB3O255ILADKEGDYO3/graph.json","fetch_events":"https://pith.science/api/pith-number/2RK7XZPGLB3O255ILADKEGDYO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RK7XZPGLB3O255ILADKEGDYO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RK7XZPGLB3O255ILADKEGDYO3/action/storage_attestation","attest_author":"https://pith.science/pith/2RK7XZPGLB3O255ILADKEGDYO3/action/author_attestation","sign_citation":"https://pith.science/pith/2RK7XZPGLB3O255ILADKEGDYO3/action/citation_signature","submit_replication":"https://pith.science/pith/2RK7XZPGLB3O255ILADKEGDYO3/action/replication_record"}},"created_at":"2026-07-05T08:47:48.132641+00:00","updated_at":"2026-07-05T08:47:48.132641+00:00"}