{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GBOHE3BYL5AW6KSX64XLHPDWDK","short_pith_number":"pith:GBOHE3BY","canonical_record":{"source":{"id":"2306.05726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:46:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d05287772dc1aa5414f3a28d45e0004d0ced1f45ea3e37cb403c52743b001a7","abstract_canon_sha256":"d48fbb8dcf93b409b0a6127501b4b2ba390432fb9c3fa8e2153da41a5c8b4518"},"schema_version":"1.0"},"canonical_sha256":"305c726c385f416f2a57f72eb3bc761a9eb0dbc79e8d688700164c56274be08e","source":{"kind":"arxiv","id":"2306.05726","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05726","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05726v2","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05726","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"GBOHE3BYL5AW","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"GBOHE3BYL5AW6KSX","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"GBOHE3BY","created_at":"2026-07-05T07:01:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GBOHE3BYL5AW6KSX64XLHPDWDK","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:46:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d05287772dc1aa5414f3a28d45e0004d0ced1f45ea3e37cb403c52743b001a7","abstract_canon_sha256":"d48fbb8dcf93b409b0a6127501b4b2ba390432fb9c3fa8e2153da41a5c8b4518"},"schema_version":"1.0"},"canonical_sha256":"305c726c385f416f2a57f72eb3bc761a9eb0dbc79e8d688700164c56274be08e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:42.586089Z","signature_b64":"9RwjxmLjS6IPJT7yMk9hv5tp5ohtmjbKOimEAekC4akrSeYJJz6/t9b6C9wAhUUaKOi2gEhX2sY4gT5nJkh5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"305c726c385f416f2a57f72eb3bc761a9eb0dbc79e8d688700164c56274be08e","last_reissued_at":"2026-07-05T07:01:42.585614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:42.585614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05726","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":"2026-07-05T07:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1al5wkCu+S/M/lTLORZxvjJ1AjnZp/ZWCE4bhiHFn8rJtp/QYxntdR+YcG33jYLLwvTPK43n5k5Dx6S1mQk7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:52:11.416499Z"},"content_sha256":"adc4ffd3b1ef7001c9e3487cf960782be80c1f7f6c4050543a9dd2f0619dae4f","schema_version":"1.0","event_id":"sha256:adc4ffd3b1ef7001c9e3487cf960782be80c1f7f6c4050543a9dd2f0619dae4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GBOHE3BYL5AW6KSX64XLHPDWDK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Iteratively Refined Behavior Regularization for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenjun Xiao, Jianye Hao, Xiaohan Hu, Yan Zheng, Yi Ma","submitted_at":"2023-06-09T07:46:24Z","abstract_excerpt":"One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its ability to learn an effective control policy that seamlessly aligns with the inherent distribution of offline data. Unfortunately, behavior regularization, a simple yet effective offline RL algorithm, tends to struggle in this regard. In this paper, we propose a new algorithm that substantially enhances behavior-regularization based on conservative policy itera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05726","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/2306.05726/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":"2026-07-05T07:01:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LGxbYqmM50xs2xgG+FmPDHWzthr2Xa7ztlzRex4EW/0aoHFihfTDsKjgLArWkFqQ6d5Kb8LjiXbQkeRiD7DNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:52:11.416999Z"},"content_sha256":"278bd17b618838a3a86103558ea4177f26efa8c3e7e9f639401c52bc73c380a3","schema_version":"1.0","event_id":"sha256:278bd17b618838a3a86103558ea4177f26efa8c3e7e9f639401c52bc73c380a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GBOHE3BYL5AW6KSX64XLHPDWDK/bundle.json","state_url":"https://pith.science/pith/GBOHE3BYL5AW6KSX64XLHPDWDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GBOHE3BYL5AW6KSX64XLHPDWDK/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":"2026-08-14T22:52:11Z","links":{"resolver":"https://pith.science/pith/GBOHE3BYL5AW6KSX64XLHPDWDK","bundle":"https://pith.science/pith/GBOHE3BYL5AW6KSX64XLHPDWDK/bundle.json","state":"https://pith.science/pith/GBOHE3BYL5AW6KSX64XLHPDWDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GBOHE3BYL5AW6KSX64XLHPDWDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GBOHE3BYL5AW6KSX64XLHPDWDK","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":"d48fbb8dcf93b409b0a6127501b4b2ba390432fb9c3fa8e2153da41a5c8b4518","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:46:24Z","title_canon_sha256":"0d05287772dc1aa5414f3a28d45e0004d0ced1f45ea3e37cb403c52743b001a7"},"schema_version":"1.0","source":{"id":"2306.05726","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05726","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05726v2","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05726","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"GBOHE3BYL5AW","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"GBOHE3BYL5AW6KSX","created_at":"2026-07-05T07:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"GBOHE3BY","created_at":"2026-07-05T07:01:42Z"}],"graph_snapshots":[{"event_id":"sha256:278bd17b618838a3a86103558ea4177f26efa8c3e7e9f639401c52bc73c380a3","target":"graph","created_at":"2026-07-05T07:01:42Z","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/2306.05726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its ability to learn an effective control policy that seamlessly aligns with the inherent distribution of offline data. Unfortunately, behavior regularization, a simple yet effective offline RL algorithm, tends to struggle in this regard. In this paper, we propose a new algorithm that substantially enhances behavior-regularization based on conservative policy itera","authors_text":"Chenjun Xiao, Jianye Hao, Xiaohan Hu, Yan Zheng, Yi Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:46:24Z","title":"Iteratively Refined Behavior Regularization for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05726","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:adc4ffd3b1ef7001c9e3487cf960782be80c1f7f6c4050543a9dd2f0619dae4f","target":"record","created_at":"2026-07-05T07:01:42Z","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":"d48fbb8dcf93b409b0a6127501b4b2ba390432fb9c3fa8e2153da41a5c8b4518","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T07:46:24Z","title_canon_sha256":"0d05287772dc1aa5414f3a28d45e0004d0ced1f45ea3e37cb403c52743b001a7"},"schema_version":"1.0","source":{"id":"2306.05726","kind":"arxiv","version":2}},"canonical_sha256":"305c726c385f416f2a57f72eb3bc761a9eb0dbc79e8d688700164c56274be08e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"305c726c385f416f2a57f72eb3bc761a9eb0dbc79e8d688700164c56274be08e","first_computed_at":"2026-07-05T07:01:42.585614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:42.585614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9RwjxmLjS6IPJT7yMk9hv5tp5ohtmjbKOimEAekC4akrSeYJJz6/t9b6C9wAhUUaKOi2gEhX2sY4gT5nJkh5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:42.586089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05726","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adc4ffd3b1ef7001c9e3487cf960782be80c1f7f6c4050543a9dd2f0619dae4f","sha256:278bd17b618838a3a86103558ea4177f26efa8c3e7e9f639401c52bc73c380a3"],"state_sha256":"e40614cb0730c5c433478e2e46adc3bf2ca8f173a64429943f48703eeb2f68a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cm5N1SIyri0QXz5XRYuwGa1a77VGwnFFr+xd5oGBTnwv5NfpZss2chY4xBqfQ6zn/JLR+XTxfVcPhL3gRaOuAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:52:11.420837Z","bundle_sha256":"d46ded4dc196b1e27a9aa334c4bbedd31a984ac12cc6078deae4596439f96c83"}}