{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XVO3NXI3S6T5BDSY4UZEFNNFGV","short_pith_number":"pith:XVO3NXI3","canonical_record":{"source":{"id":"2212.09900","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-19T22:43:08Z","cross_cats_sorted":["math.ST","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"bb7884c7215f2c57d8c1e1adc2f97a2f2919152d6b61ac120980ba071519a8f5","abstract_canon_sha256":"a107b4768b68a76b2bcdd57bf025581f73f03f862886eddef5ee455136115b3e"},"schema_version":"1.0"},"canonical_sha256":"bd5db6dd1b97a7d08e58e53242b5a53567567580294969ff9b707aa702136c33","source":{"kind":"arxiv","id":"2212.09900","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09900","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09900v4","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09900","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"pith_short_12","alias_value":"XVO3NXI3S6T5","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"pith_short_16","alias_value":"XVO3NXI3S6T5BDSY","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"pith_short_8","alias_value":"XVO3NXI3","created_at":"2026-07-05T11:16:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XVO3NXI3S6T5BDSY4UZEFNNFGV","target":"record","payload":{"canonical_record":{"source":{"id":"2212.09900","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-19T22:43:08Z","cross_cats_sorted":["math.ST","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"bb7884c7215f2c57d8c1e1adc2f97a2f2919152d6b61ac120980ba071519a8f5","abstract_canon_sha256":"a107b4768b68a76b2bcdd57bf025581f73f03f862886eddef5ee455136115b3e"},"schema_version":"1.0"},"canonical_sha256":"bd5db6dd1b97a7d08e58e53242b5a53567567580294969ff9b707aa702136c33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:00.034823Z","signature_b64":"a+eX0jbAjdPOZfMVPhPjJreil2/cXVsev9KVvwKyEjTZ1p8n5t2pJnED68ZuSQyb+SUwyL44MKeZ8SKyIQaUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd5db6dd1b97a7d08e58e53242b5a53567567580294969ff9b707aa702136c33","last_reissued_at":"2026-07-05T11:16:00.034483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:00.034483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.09900","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EulcMmEzd/K6ffsdbJQqMQtSnziqpSR0MQodz/xBSp3CKf+M+J/Cg+pRHxLku5MnxuNlMUsp8j6EQ/hhUvbuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:59:28.118013Z"},"content_sha256":"1fcf7d851c002411d70c8afa0b347aa6502fa46d6fea7a0923cf59f56b24f4ad","schema_version":"1.0","event_id":"sha256:1fcf7d851c002411d70c8afa0b347aa6502fa46d6fea7a0923cf59f56b24f4ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XVO3NXI3S6T5BDSY4UZEFNNFGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ME","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Ying Jin, Zhaoran Wang, Zhimei Ren, Zhuoran Yang","submitted_at":"2022-12-19T22:43:08Z","abstract_excerpt":"This paper studies offline policy learning, which aims at utilizing observations collected a priori (from either fixed or adaptively evolving behavior policies) to learn an optimal individualized decision rule that achieves the best overall outcomes for a given population. Existing policy learning methods rely on a uniform overlap assumption, i.e., the propensities of exploring all actions for all individual characteristics must be lower bounded. As one has no control over the data collection process, this assumption can be unrealistic in many situations, especially when the behavior policies "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09900","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/2212.09900/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":"2026-07-05T11:16:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uSXG08a84gcxna48DFB+LTVmctiR3oRoEEwJ93SCIG0FoPBKuBGnWCmLXn70tk+st3CTQbNReeSw1K8dafo+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:59:28.118559Z"},"content_sha256":"95ac823ed4e4305f940e4366bad0eb8512e604fad52d692f94062ab2b376c489","schema_version":"1.0","event_id":"sha256:95ac823ed4e4305f940e4366bad0eb8512e604fad52d692f94062ab2b376c489"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVO3NXI3S6T5BDSY4UZEFNNFGV/bundle.json","state_url":"https://pith.science/pith/XVO3NXI3S6T5BDSY4UZEFNNFGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVO3NXI3S6T5BDSY4UZEFNNFGV/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":"2026-08-15T21:59:28Z","links":{"resolver":"https://pith.science/pith/XVO3NXI3S6T5BDSY4UZEFNNFGV","bundle":"https://pith.science/pith/XVO3NXI3S6T5BDSY4UZEFNNFGV/bundle.json","state":"https://pith.science/pith/XVO3NXI3S6T5BDSY4UZEFNNFGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVO3NXI3S6T5BDSY4UZEFNNFGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XVO3NXI3S6T5BDSY4UZEFNNFGV","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":"a107b4768b68a76b2bcdd57bf025581f73f03f862886eddef5ee455136115b3e","cross_cats_sorted":["math.ST","stat.ME","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-19T22:43:08Z","title_canon_sha256":"bb7884c7215f2c57d8c1e1adc2f97a2f2919152d6b61ac120980ba071519a8f5"},"schema_version":"1.0","source":{"id":"2212.09900","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09900","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09900v4","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09900","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"pith_short_12","alias_value":"XVO3NXI3S6T5","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"pith_short_16","alias_value":"XVO3NXI3S6T5BDSY","created_at":"2026-07-05T11:16:00Z"},{"alias_kind":"pith_short_8","alias_value":"XVO3NXI3","created_at":"2026-07-05T11:16:00Z"}],"graph_snapshots":[{"event_id":"sha256:95ac823ed4e4305f940e4366bad0eb8512e604fad52d692f94062ab2b376c489","target":"graph","created_at":"2026-07-05T11:16:00Z","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/2212.09900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies offline policy learning, which aims at utilizing observations collected a priori (from either fixed or adaptively evolving behavior policies) to learn an optimal individualized decision rule that achieves the best overall outcomes for a given population. Existing policy learning methods rely on a uniform overlap assumption, i.e., the propensities of exploring all actions for all individual characteristics must be lower bounded. As one has no control over the data collection process, this assumption can be unrealistic in many situations, especially when the behavior policies ","authors_text":"Ying Jin, Zhaoran Wang, Zhimei Ren, Zhuoran Yang","cross_cats":["math.ST","stat.ME","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-19T22:43:08Z","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09900","kind":"arxiv","version":4},"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":"sha256:1fcf7d851c002411d70c8afa0b347aa6502fa46d6fea7a0923cf59f56b24f4ad","target":"record","created_at":"2026-07-05T11:16:00Z","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":"a107b4768b68a76b2bcdd57bf025581f73f03f862886eddef5ee455136115b3e","cross_cats_sorted":["math.ST","stat.ME","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-19T22:43:08Z","title_canon_sha256":"bb7884c7215f2c57d8c1e1adc2f97a2f2919152d6b61ac120980ba071519a8f5"},"schema_version":"1.0","source":{"id":"2212.09900","kind":"arxiv","version":4}},"canonical_sha256":"bd5db6dd1b97a7d08e58e53242b5a53567567580294969ff9b707aa702136c33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd5db6dd1b97a7d08e58e53242b5a53567567580294969ff9b707aa702136c33","first_computed_at":"2026-07-05T11:16:00.034483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:00.034483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a+eX0jbAjdPOZfMVPhPjJreil2/cXVsev9KVvwKyEjTZ1p8n5t2pJnED68ZuSQyb+SUwyL44MKeZ8SKyIQaUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:00.034823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09900","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fcf7d851c002411d70c8afa0b347aa6502fa46d6fea7a0923cf59f56b24f4ad","sha256:95ac823ed4e4305f940e4366bad0eb8512e604fad52d692f94062ab2b376c489"],"state_sha256":"de455a084e33dda3a809fb723a7d3e7cce2e8eeee9d838c43ac5c0835e16334e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bwpMaY8Qx0b1RyxthVTtuGkTgzyQTGnff92DiosQWy22l7EQPFeHfpDiozlzmP8QAAjjW2b/AHGnXN1hQakcBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:59:28.122856Z","bundle_sha256":"b7b1ad1d5c123067c70639dfe083d74d88abee355833ab17cc656432b3e06d5f"}}