{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QMO67W62WMQHUL5SK5YP5PDL5D","short_pith_number":"pith:QMO67W62","schema_version":"1.0","canonical_sha256":"831defdbdab3207a2fb25770febc6be8f36e1b03108c93698748d538346d4a50","source":{"kind":"arxiv","id":"2405.15332","version":4},"attestation_state":"computed","paper":{"title":"Cross-Validated Off-Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Matej Cief, Michal Kompan","submitted_at":"2024-05-24T08:13:16Z","abstract_excerpt":"We study estimator selection and hyper-parameter tuning in off-policy evaluation. Although cross-validation is the most popular method for model selection in supervised learning, off-policy evaluation relies mostly on theory, which provides only limited guidance to practitioners. We show how to use cross-validation for off-policy evaluation. This challenges a popular belief that cross-validation in off-policy evaluation is not feasible. We evaluate our method empirically and show that it addresses a variety of use cases."},"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":"2405.15332","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T08:13:16Z","cross_cats_sorted":[],"title_canon_sha256":"f00e448a5d83c94797f8b90712a622cfa86a78fa519a8a4ba2eb7797e221432c","abstract_canon_sha256":"dfa2a05d518a29f3eb6f94f7fef7155ea03536d68a6e1188fe70d43b60902747"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:11.876359Z","signature_b64":"dCS6o2jn5evnNjCcsz+GDFJ1YUfB7jhaWHRQD83PsOO2zueE7TI92FgTbkFuYIjRDiZ8ilMIjrFyuMqHj+MsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"831defdbdab3207a2fb25770febc6be8f36e1b03108c93698748d538346d4a50","last_reissued_at":"2026-07-05T09:52:11.875905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:11.875905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Validated Off-Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Matej Cief, Michal Kompan","submitted_at":"2024-05-24T08:13:16Z","abstract_excerpt":"We study estimator selection and hyper-parameter tuning in off-policy evaluation. Although cross-validation is the most popular method for model selection in supervised learning, off-policy evaluation relies mostly on theory, which provides only limited guidance to practitioners. We show how to use cross-validation for off-policy evaluation. This challenges a popular belief that cross-validation in off-policy evaluation is not feasible. We evaluate our method empirically and show that it addresses a variety of use cases."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15332","kind":"arxiv","version":4},"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/2405.15332/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":"2405.15332","created_at":"2026-07-05T09:52:11.875970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15332v4","created_at":"2026-07-05T09:52:11.875970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15332","created_at":"2026-07-05T09:52:11.875970+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMO67W62WMQH","created_at":"2026-07-05T09:52:11.875970+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMO67W62WMQHUL5S","created_at":"2026-07-05T09:52:11.875970+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMO67W62","created_at":"2026-07-05T09:52:11.875970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20417","citing_title":"Off-Policy Evaluation and Learning for the Future under Non-Stationarity","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QMO67W62WMQHUL5SK5YP5PDL5D","json":"https://pith.science/pith/QMO67W62WMQHUL5SK5YP5PDL5D.json","graph_json":"https://pith.science/api/pith-number/QMO67W62WMQHUL5SK5YP5PDL5D/graph.json","events_json":"https://pith.science/api/pith-number/QMO67W62WMQHUL5SK5YP5PDL5D/events.json","paper":"https://pith.science/paper/QMO67W62"},"agent_actions":{"view_html":"https://pith.science/pith/QMO67W62WMQHUL5SK5YP5PDL5D","download_json":"https://pith.science/pith/QMO67W62WMQHUL5SK5YP5PDL5D.json","view_paper":"https://pith.science/paper/QMO67W62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15332&json=true","fetch_graph":"https://pith.science/api/pith-number/QMO67W62WMQHUL5SK5YP5PDL5D/graph.json","fetch_events":"https://pith.science/api/pith-number/QMO67W62WMQHUL5SK5YP5PDL5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMO67W62WMQHUL5SK5YP5PDL5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMO67W62WMQHUL5SK5YP5PDL5D/action/storage_attestation","attest_author":"https://pith.science/pith/QMO67W62WMQHUL5SK5YP5PDL5D/action/author_attestation","sign_citation":"https://pith.science/pith/QMO67W62WMQHUL5SK5YP5PDL5D/action/citation_signature","submit_replication":"https://pith.science/pith/QMO67W62WMQHUL5SK5YP5PDL5D/action/replication_record"}},"created_at":"2026-07-05T09:52:11.875970+00:00","updated_at":"2026-07-05T09:52:11.875970+00:00"}