{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GHZT7D5GXDHOMBZ5RVRCKBCIAZ","short_pith_number":"pith:GHZT7D5G","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"},"canonical_sha256":"31f33f8fa6b8cee6073d8d62250448065355f41f90db0858f752af5da74d4caf","source":{"kind":"arxiv","id":"2311.14110","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14110","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14110v2","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14110","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_12","alias_value":"GHZT7D5GXDHO","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_16","alias_value":"GHZT7D5GXDHOMBZ5","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_8","alias_value":"GHZT7D5G","created_at":"2026-07-05T09:27:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GHZT7D5GXDHOMBZ5RVRCKBCIAZ","target":"record","payload":{"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"},"canonical_sha256":"31f33f8fa6b8cee6073d8d62250448065355f41f90db0858f752af5da74d4caf","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"},"source_kind":"arxiv","source_id":"2311.14110","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fOKc2gc9HF5DaJrvqtZlXTDZaBtOmi/7lKnLQxumJV/8Sa8gmUoTy7BdDh+4wJagxoHnBValIpeLgQMIg3B1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:18:12.775341Z"},"content_sha256":"c027cb547cc13c49b582840e69f771d81fa0007d708692b2eb22269e2b8bc70a","schema_version":"1.0","event_id":"sha256:c027cb547cc13c49b582840e69f771d81fa0007d708692b2eb22269e2b8bc70a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GHZT7D5GXDHOMBZ5RVRCKBCIAZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mzFrTX16GRejuo7J7uZy249DLQiKV3ZPihoESPsOe36uwr8dpjbdwfpG9X6ieOstAbKwvg3aykefmAfNmxc6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:18:12.775872Z"},"content_sha256":"3d9aca7036ff630d390fbc4a0d4858163b1d6aa6d365f3f9112af6ac9cf71dda","schema_version":"1.0","event_id":"sha256:3d9aca7036ff630d390fbc4a0d4858163b1d6aa6d365f3f9112af6ac9cf71dda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/bundle.json","state_url":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T17:18:12Z","links":{"resolver":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ","bundle":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/bundle.json","state":"https://pith.science/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHZT7D5GXDHOMBZ5RVRCKBCIAZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GHZT7D5GXDHOMBZ5RVRCKBCIAZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1ddf40b467d4b93a2932cc94ae21a802462e00337b4c9be45ffbce7b39499135","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T17:13:37Z","title_canon_sha256":"3a7b6b02d5af2f8bd3bc2939ccef019e4e26adf934b2422be6b473b0d3b513de"},"schema_version":"1.0","source":{"id":"2311.14110","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14110","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14110v2","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14110","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_12","alias_value":"GHZT7D5GXDHO","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_16","alias_value":"GHZT7D5GXDHOMBZ5","created_at":"2026-07-05T09:27:19Z"},{"alias_kind":"pith_short_8","alias_value":"GHZT7D5G","created_at":"2026-07-05T09:27:19Z"}],"graph_snapshots":[{"event_id":"sha256:3d9aca7036ff630d390fbc4a0d4858163b1d6aa6d365f3f9112af6ac9cf71dda","target":"graph","created_at":"2026-07-05T09:27:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.14110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Alex J. Chan, Alihan H\\\"uy\\\"uk, Hao Sun, Mihaela van der Schaar, Nabeel Seedat","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T17:13:37Z","title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14110","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c027cb547cc13c49b582840e69f771d81fa0007d708692b2eb22269e2b8bc70a","target":"record","created_at":"2026-07-05T09:27:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1ddf40b467d4b93a2932cc94ae21a802462e00337b4c9be45ffbce7b39499135","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-23T17:13:37Z","title_canon_sha256":"3a7b6b02d5af2f8bd3bc2939ccef019e4e26adf934b2422be6b473b0d3b513de"},"schema_version":"1.0","source":{"id":"2311.14110","kind":"arxiv","version":2}},"canonical_sha256":"31f33f8fa6b8cee6073d8d62250448065355f41f90db0858f752af5da74d4caf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31f33f8fa6b8cee6073d8d62250448065355f41f90db0858f752af5da74d4caf","first_computed_at":"2026-07-05T09:27:19.771123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:19.771123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rHismSB/pQQY+WQZPeJ2oeYvjMCinTPJ3BYoT2lVca1ou+4dj2xwBoqX2GKyMgRbpejL2Q8KWXlAodd2gDNgCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:19.771714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.14110","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c027cb547cc13c49b582840e69f771d81fa0007d708692b2eb22269e2b8bc70a","sha256:3d9aca7036ff630d390fbc4a0d4858163b1d6aa6d365f3f9112af6ac9cf71dda"],"state_sha256":"a9a4a156d649194c2f338e04d134cb2d91a2f7acaa27986d2dd494beecd2cf50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DgWt58+XMuXYh3/P4RUVD7eBq24Rv+CtP/13wgcWeP+36vhScUlFJY9s77krJcu7uvtHHR8fzc66CKUCC1yQCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:18:12.781267Z","bundle_sha256":"536340291ba0eb885e5a6f80edc9a3481c36827dfb495020982d13bd05167419"}}