{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YX4MBSLAOH64DP4MUFDKMUVSSB","short_pith_number":"pith:YX4MBSLA","canonical_record":{"source":{"id":"2204.05275","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-11T17:26:19Z","cross_cats_sorted":["cs.IT","cs.LG","cs.SY","eess.SY","math.IT","math.ST","stat.TH"],"title_canon_sha256":"f15928b4b802fea31581e4f2c315666f093a2d999a0b8dff58015ad641ed4f07","abstract_canon_sha256":"4252a1c1d4a2466b098a22b288e441611e10a89515563d4c4535a1ea9b906da6"},"schema_version":"1.0"},"canonical_sha256":"c5f8c0c96071fdc1bf8ca146a652b2906de536a8dc67f90ce9867ac27ab34ae0","source":{"kind":"arxiv","id":"2204.05275","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05275","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05275v4","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05275","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"YX4MBSLAOH64","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"YX4MBSLAOH64DP4M","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"YX4MBSLA","created_at":"2026-07-05T07:53:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YX4MBSLAOH64DP4MUFDKMUVSSB","target":"record","payload":{"canonical_record":{"source":{"id":"2204.05275","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-11T17:26:19Z","cross_cats_sorted":["cs.IT","cs.LG","cs.SY","eess.SY","math.IT","math.ST","stat.TH"],"title_canon_sha256":"f15928b4b802fea31581e4f2c315666f093a2d999a0b8dff58015ad641ed4f07","abstract_canon_sha256":"4252a1c1d4a2466b098a22b288e441611e10a89515563d4c4535a1ea9b906da6"},"schema_version":"1.0"},"canonical_sha256":"c5f8c0c96071fdc1bf8ca146a652b2906de536a8dc67f90ce9867ac27ab34ae0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:45.551292Z","signature_b64":"0/Ov2LNQdvVikwNj9HQOmltVeoxk9jjA77ELS773mhj+BmbrxouUrfBdgl1cdBXKTzAkcQlKk1+2jX55BsK6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5f8c0c96071fdc1bf8ca146a652b2906de536a8dc67f90ce9867ac27ab34ae0","last_reissued_at":"2026-07-05T07:53:45.550865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:45.550865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.05275","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":"2026-07-05T07:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qwaOXfg6S5fiIhNHypV3B6k2Qde+vAX+onY877sdmQpRPxHOfL9A5d66tbOxq9yFaFnsCTNwR0ODDdMhydWTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:38:11.242410Z"},"content_sha256":"0a5945e3c7a171d4ea466e919156b6689f029b0e2a718af0d6f4e7ca7b1cbc76","schema_version":"1.0","event_id":"sha256:0a5945e3c7a171d4ea466e919156b6689f029b0e2a718af0d6f4e7ca7b1cbc76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YX4MBSLAOH64DP4MUFDKMUVSSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Settling the Sample Complexity of Model-Based Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","cs.SY","eess.SY","math.IT","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Gen Li, Laixi Shi, Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2022-04-11T17:26:19Z","abstract_excerpt":"This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data coverage. However, prior algorithms or analyses either suffer from suboptimal sample complexities or incur high burn-in cost to reach sample optimality, thus posing an impediment to efficient offline RL in sample-starved applications.\n  We demonstrate that the model-based (or \"plug-in\") approach achieves minimax-optimal sample complexity without burn-in cost for tabular Markov d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05275","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/2204.05275/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":"2026-07-05T07:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrsQ/AengjBcdMgOdUYh0E+LRQ2kWql838BKMz4joCWlGhO1+QF68xNuP6HCGpaU4puMDQqeREBWOANjkQ1MCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:38:11.242948Z"},"content_sha256":"170f125a24b3fa9a51c4bae2fd6ef6381de87d3b1f0baa1a1567f64df257124c","schema_version":"1.0","event_id":"sha256:170f125a24b3fa9a51c4bae2fd6ef6381de87d3b1f0baa1a1567f64df257124c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YX4MBSLAOH64DP4MUFDKMUVSSB/bundle.json","state_url":"https://pith.science/pith/YX4MBSLAOH64DP4MUFDKMUVSSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YX4MBSLAOH64DP4MUFDKMUVSSB/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":"2026-08-16T12:38:11Z","links":{"resolver":"https://pith.science/pith/YX4MBSLAOH64DP4MUFDKMUVSSB","bundle":"https://pith.science/pith/YX4MBSLAOH64DP4MUFDKMUVSSB/bundle.json","state":"https://pith.science/pith/YX4MBSLAOH64DP4MUFDKMUVSSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YX4MBSLAOH64DP4MUFDKMUVSSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YX4MBSLAOH64DP4MUFDKMUVSSB","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":"4252a1c1d4a2466b098a22b288e441611e10a89515563d4c4535a1ea9b906da6","cross_cats_sorted":["cs.IT","cs.LG","cs.SY","eess.SY","math.IT","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-11T17:26:19Z","title_canon_sha256":"f15928b4b802fea31581e4f2c315666f093a2d999a0b8dff58015ad641ed4f07"},"schema_version":"1.0","source":{"id":"2204.05275","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.05275","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2204.05275v4","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05275","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"YX4MBSLAOH64","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"YX4MBSLAOH64DP4M","created_at":"2026-07-05T07:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"YX4MBSLA","created_at":"2026-07-05T07:53:45Z"}],"graph_snapshots":[{"event_id":"sha256:170f125a24b3fa9a51c4bae2fd6ef6381de87d3b1f0baa1a1567f64df257124c","target":"graph","created_at":"2026-07-05T07:53:45Z","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/2204.05275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data coverage. However, prior algorithms or analyses either suffer from suboptimal sample complexities or incur high burn-in cost to reach sample optimality, thus posing an impediment to efficient offline RL in sample-starved applications.\n  We demonstrate that the model-based (or \"plug-in\") approach achieves minimax-optimal sample complexity without burn-in cost for tabular Markov d","authors_text":"Gen Li, Laixi Shi, Yuejie Chi, Yuting Wei, Yuxin Chen","cross_cats":["cs.IT","cs.LG","cs.SY","eess.SY","math.IT","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-11T17:26:19Z","title":"Settling the Sample Complexity of Model-Based Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05275","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":"sha256:0a5945e3c7a171d4ea466e919156b6689f029b0e2a718af0d6f4e7ca7b1cbc76","target":"record","created_at":"2026-07-05T07:53:45Z","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":"4252a1c1d4a2466b098a22b288e441611e10a89515563d4c4535a1ea9b906da6","cross_cats_sorted":["cs.IT","cs.LG","cs.SY","eess.SY","math.IT","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-04-11T17:26:19Z","title_canon_sha256":"f15928b4b802fea31581e4f2c315666f093a2d999a0b8dff58015ad641ed4f07"},"schema_version":"1.0","source":{"id":"2204.05275","kind":"arxiv","version":4}},"canonical_sha256":"c5f8c0c96071fdc1bf8ca146a652b2906de536a8dc67f90ce9867ac27ab34ae0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5f8c0c96071fdc1bf8ca146a652b2906de536a8dc67f90ce9867ac27ab34ae0","first_computed_at":"2026-07-05T07:53:45.550865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:45.550865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0/Ov2LNQdvVikwNj9HQOmltVeoxk9jjA77ELS773mhj+BmbrxouUrfBdgl1cdBXKTzAkcQlKk1+2jX55BsK6BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:45.551292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.05275","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a5945e3c7a171d4ea466e919156b6689f029b0e2a718af0d6f4e7ca7b1cbc76","sha256:170f125a24b3fa9a51c4bae2fd6ef6381de87d3b1f0baa1a1567f64df257124c"],"state_sha256":"721b9306283a8d2e0da4a94817270e4380b77e02a68be1c2fd4a363dafa4d4b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5bbUw74VqlZedoYfgViqp8+t/TozWIsbGQeK1UiXsJ7aERq2FJhTVgt2bZs9TLaEX0UNXBONzrC8IKA3jcyqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T12:38:11.247017Z","bundle_sha256":"0b99eebe9ae53e8fb6eeeb87f526dcb0b97e2c2380e647084e4d262e16a754ca"}}