{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UZN5EQEY6VVWQUPR2KIXHWITI5","short_pith_number":"pith:UZN5EQEY","canonical_record":{"source":{"id":"2211.00716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-01T19:28:48Z","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"2b9f4452aabb131cf0012dcae68286685cbe4575997f4d04d6a377d4bf53e72c","abstract_canon_sha256":"ebc011000c8b9261a40013c733def174f8d870dc38b51cb2df55e67f6b82770e"},"schema_version":"1.0"},"canonical_sha256":"a65bd24098f56b6851f1d29173d913474582281dda680284d0b9493bf6a4b3ae","source":{"kind":"arxiv","id":"2211.00716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.00716","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"arxiv_version","alias_value":"2211.00716v1","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00716","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"pith_short_12","alias_value":"UZN5EQEY6VVW","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"pith_short_16","alias_value":"UZN5EQEY6VVWQUPR","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"pith_short_8","alias_value":"UZN5EQEY","created_at":"2026-07-05T05:12:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UZN5EQEY6VVWQUPR2KIXHWITI5","target":"record","payload":{"canonical_record":{"source":{"id":"2211.00716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-01T19:28:48Z","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"2b9f4452aabb131cf0012dcae68286685cbe4575997f4d04d6a377d4bf53e72c","abstract_canon_sha256":"ebc011000c8b9261a40013c733def174f8d870dc38b51cb2df55e67f6b82770e"},"schema_version":"1.0"},"canonical_sha256":"a65bd24098f56b6851f1d29173d913474582281dda680284d0b9493bf6a4b3ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:33.498284Z","signature_b64":"kLPswfaFb/o8GrQKxtMoxoHkzXqDHExWNkrpz2/OJARBqwuEZFeXFQWTooyTkWY+oGjRcwnE2woL1T8EH835BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a65bd24098f56b6851f1d29173d913474582281dda680284d0b9493bf6a4b3ae","last_reissued_at":"2026-07-05T05:12:33.497888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:33.497888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.00716","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:12:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BHun/8+rxwigjVHSGF++XVTh6cn0ZfFWrjq2ZVJcocqySRdYIChDjY1hlYAaTatC0HUISv+Z0agDU6X0duqxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:38.082480Z"},"content_sha256":"02ce0dfe0eef5e0b64ae6615bde6f3f1f04e9ccc564c82ef03d5b3b8d2f59134","schema_version":"1.0","event_id":"sha256:02ce0dfe0eef5e0b64ae6615bde6f3f1f04e9ccc564c82ef03d5b3b8d2f59134"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UZN5EQEY6VVWQUPR2KIXHWITI5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Hanlin Zhu, Jiantao Jiao, Kunhe Yang, Paria Rashidinejad, Stuart Russell","submitted_at":"2022-11-01T19:28:48Z","abstract_excerpt":"Offline reinforcement learning (RL), which refers to decision-making from a previously-collected dataset of interactions, has received significant attention over the past years. Much effort has focused on improving offline RL practicality by addressing the prevalent issue of partial data coverage through various forms of conservative policy learning. While the majority of algorithms do not have finite-sample guarantees, several provable conservative offline RL algorithms are designed and analyzed within the single-policy concentrability framework that handles partial coverage. Yet, in the nonl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00716","kind":"arxiv","version":1},"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/2211.00716/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":"2026-07-05T05:12:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RqjAOq/HENpcc5kqRONh+dydWBmLIkbYTqH1MT2K7coNbRf4eDb4BxvPBkEOzDTItLNeLSy+aPXKVfndfH3ACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:38.083437Z"},"content_sha256":"4799fbb9fedf020105fd113a985ec2e5969129f9ee044143c059ed36c0233fc1","schema_version":"1.0","event_id":"sha256:4799fbb9fedf020105fd113a985ec2e5969129f9ee044143c059ed36c0233fc1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UZN5EQEY6VVWQUPR2KIXHWITI5/bundle.json","state_url":"https://pith.science/pith/UZN5EQEY6VVWQUPR2KIXHWITI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UZN5EQEY6VVWQUPR2KIXHWITI5/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":"2026-08-09T11:20:38Z","links":{"resolver":"https://pith.science/pith/UZN5EQEY6VVWQUPR2KIXHWITI5","bundle":"https://pith.science/pith/UZN5EQEY6VVWQUPR2KIXHWITI5/bundle.json","state":"https://pith.science/pith/UZN5EQEY6VVWQUPR2KIXHWITI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UZN5EQEY6VVWQUPR2KIXHWITI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UZN5EQEY6VVWQUPR2KIXHWITI5","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":"ebc011000c8b9261a40013c733def174f8d870dc38b51cb2df55e67f6b82770e","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-01T19:28:48Z","title_canon_sha256":"2b9f4452aabb131cf0012dcae68286685cbe4575997f4d04d6a377d4bf53e72c"},"schema_version":"1.0","source":{"id":"2211.00716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.00716","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"arxiv_version","alias_value":"2211.00716v1","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00716","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"pith_short_12","alias_value":"UZN5EQEY6VVW","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"pith_short_16","alias_value":"UZN5EQEY6VVWQUPR","created_at":"2026-07-05T05:12:33Z"},{"alias_kind":"pith_short_8","alias_value":"UZN5EQEY","created_at":"2026-07-05T05:12:33Z"}],"graph_snapshots":[{"event_id":"sha256:4799fbb9fedf020105fd113a985ec2e5969129f9ee044143c059ed36c0233fc1","target":"graph","created_at":"2026-07-05T05:12:33Z","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/2211.00716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL), which refers to decision-making from a previously-collected dataset of interactions, has received significant attention over the past years. Much effort has focused on improving offline RL practicality by addressing the prevalent issue of partial data coverage through various forms of conservative policy learning. While the majority of algorithms do not have finite-sample guarantees, several provable conservative offline RL algorithms are designed and analyzed within the single-policy concentrability framework that handles partial coverage. Yet, in the nonl","authors_text":"Hanlin Zhu, Jiantao Jiao, Kunhe Yang, Paria Rashidinejad, Stuart Russell","cross_cats":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-01T19:28:48Z","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00716","kind":"arxiv","version":1},"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":"sha256:02ce0dfe0eef5e0b64ae6615bde6f3f1f04e9ccc564c82ef03d5b3b8d2f59134","target":"record","created_at":"2026-07-05T05:12:33Z","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":"ebc011000c8b9261a40013c733def174f8d870dc38b51cb2df55e67f6b82770e","cross_cats_sorted":["cs.AI","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-01T19:28:48Z","title_canon_sha256":"2b9f4452aabb131cf0012dcae68286685cbe4575997f4d04d6a377d4bf53e72c"},"schema_version":"1.0","source":{"id":"2211.00716","kind":"arxiv","version":1}},"canonical_sha256":"a65bd24098f56b6851f1d29173d913474582281dda680284d0b9493bf6a4b3ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a65bd24098f56b6851f1d29173d913474582281dda680284d0b9493bf6a4b3ae","first_computed_at":"2026-07-05T05:12:33.497888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:33.497888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kLPswfaFb/o8GrQKxtMoxoHkzXqDHExWNkrpz2/OJARBqwuEZFeXFQWTooyTkWY+oGjRcwnE2woL1T8EH835BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:33.498284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.00716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02ce0dfe0eef5e0b64ae6615bde6f3f1f04e9ccc564c82ef03d5b3b8d2f59134","sha256:4799fbb9fedf020105fd113a985ec2e5969129f9ee044143c059ed36c0233fc1"],"state_sha256":"17e88294128501f8a53b3af25e65f1da769a6c29ce621e295cc77213b3e536f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2qstC9pf5g7qwe4Oc4dDYIlc2nVO/16wXFRbgKIzUWa5NksoRe0aiK8yR3V6BcK5K3z0izyz0TJR7nlnwEicCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:20:38.089092Z","bundle_sha256":"96f09aba57fa4354d214c7b85a552d7fe550a0800590bb6a0148f92a8b2fe4f0"}}