{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GHZT7D5GXDHOMBZ5RVRCKBCIAZ","short_pith_number":"pith:GHZT7D5G","schema_version":"1.0","canonical_sha256":"31f33f8fa6b8cee6073d8d62250448065355f41f90db0858f752af5da74d4caf","source":{"kind":"arxiv","id":"2311.14110","version":2},"attestation_state":"computed","paper":{"title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex J. Chan, Alihan H\\\"uy\\\"uk, Hao Sun, Mihaela van der Schaar, Nabeel Seedat","submitted_at":"2023-11-23T17:13:37Z","abstract_excerpt":"Evaluating the value of a hypothetical target policy with only a logged dataset is important but challenging. On the one hand, it brings opportunities for safe policy improvement under high-stakes scenarios like clinical guidelines. On the other hand, such opportunities raise a need for precise off-policy evaluation (OPE). While previous work on OPE focused on improving the algorithm in value estimation, in this work, we emphasize the importance of the offline dataset, hence putting forward a data-centric framework for evaluating OPE problems. We propose DataCOPE, a data-centric framework for "},"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":"2311.14110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T17:13:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a7b6b02d5af2f8bd3bc2939ccef019e4e26adf934b2422be6b473b0d3b513de","abstract_canon_sha256":"1ddf40b467d4b93a2932cc94ae21a802462e00337b4c9be45ffbce7b39499135"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:19.771714Z","signature_b64":"rHismSB/pQQY+WQZPeJ2oeYvjMCinTPJ3BYoT2lVca1ou+4dj2xwBoqX2GKyMgRbpejL2Q8KWXlAodd2gDNgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31f33f8fa6b8cee6073d8d62250448065355f41f90db0858f752af5da74d4caf","last_reissued_at":"2026-07-05T09:27:19.771123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:19.771123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex J. Chan, Alihan H\\\"uy\\\"uk, Hao Sun, Mihaela van der Schaar, Nabeel Seedat","submitted_at":"2023-11-23T17:13:37Z","abstract_excerpt":"Evaluating the value of a hypothetical target policy with only a logged dataset is important but challenging. On the one hand, it brings opportunities for safe policy improvement under high-stakes scenarios like clinical guidelines. On the other hand, such opportunities raise a need for precise off-policy evaluation (OPE). While previous work on OPE focused on improving the algorithm in value estimation, in this work, we emphasize the importance of the offline dataset, hence putting forward a data-centric framework for evaluating OPE problems. We propose DataCOPE, a data-centric framework for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14110","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/2311.14110/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":"2311.14110","created_at":"2026-07-05T09:27:19.771219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14110v2","created_at":"2026-07-05T09:27:19.771219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14110","created_at":"2026-07-05T09:27:19.771219+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHZT7D5GXDHO","created_at":"2026-07-05T09:27:19.771219+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHZT7D5GXDHOMBZ5","created_at":"2026-07-05T09:27:19.771219+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHZT7D5G","created_at":"2026-07-05T09:27:19.771219+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/GHZT7D5GXDHOMBZ5RVRCKBCIAZ","json":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ.json","graph_json":"https://pith.science/api/pith-number/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/graph.json","events_json":"https://pith.science/api/pith-number/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/events.json","paper":"https://pith.science/paper/GHZT7D5G"},"agent_actions":{"view_html":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ","download_json":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ.json","view_paper":"https://pith.science/paper/GHZT7D5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14110&json=true","fetch_graph":"https://pith.science/api/pith-number/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/action/storage_attestation","attest_author":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/action/author_attestation","sign_citation":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/action/citation_signature","submit_replication":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/action/replication_record"}},"created_at":"2026-07-05T09:27:19.771219+00:00","updated_at":"2026-07-05T09:27:19.771219+00:00"}