{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EMD2HODIZMDVLVXJR2JROJ4HBO","short_pith_number":"pith:EMD2HODI","canonical_record":{"source":{"id":"2211.15065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T04:56:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93c3a4482a8634b1232ea9fb497cc065f7bae3fe259b0af281925763b16b79b7","abstract_canon_sha256":"db06ab614fe0fd0795270393a1b4b69d7a505b48da59eff5b804d67a556b6959"},"schema_version":"1.0"},"canonical_sha256":"2307a3b868cb0755d6e98e931727870bbaa297b492240de7323ecbcb18649db0","source":{"kind":"arxiv","id":"2211.15065","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15065","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15065v1","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15065","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"EMD2HODIZMDV","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"EMD2HODIZMDVLVXJ","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"EMD2HODI","created_at":"2026-07-05T05:19:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EMD2HODIZMDVLVXJR2JROJ4HBO","target":"record","payload":{"canonical_record":{"source":{"id":"2211.15065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T04:56:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93c3a4482a8634b1232ea9fb497cc065f7bae3fe259b0af281925763b16b79b7","abstract_canon_sha256":"db06ab614fe0fd0795270393a1b4b69d7a505b48da59eff5b804d67a556b6959"},"schema_version":"1.0"},"canonical_sha256":"2307a3b868cb0755d6e98e931727870bbaa297b492240de7323ecbcb18649db0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:59.376226Z","signature_b64":"eEeziLyuQsV2CVVzM+Y3UE6fbEXiP9o4pACqkRZdJtEIiUlcesQNomfYVmRkWSh5nOhY7eoDoBIcXhWLnsFNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2307a3b868cb0755d6e98e931727870bbaa297b492240de7323ecbcb18649db0","last_reissued_at":"2026-07-05T05:19:59.375818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:59.375818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.15065","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":"2026-07-05T05:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+yIVL887V8jEU54yW4pJldYNOmr81lcdISwSQG3by8jowKOfBdwG91nk/sjA/xgTumuOdoGPJVDWbccBd59FBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T14:49:06.710305Z"},"content_sha256":"bf0fef3ddf1d853023b37d15bfffb5de2244ad271f14034433a088ce8becb192","schema_version":"1.0","event_id":"sha256:bf0fef3ddf1d853023b37d15bfffb5de2244ad271f14034433a088ce8becb192"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EMD2HODIZMDVLVXJR2JROJ4HBO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Wang, Chen Chen, Dong Li, Hongyao Tang, Jianye Hao, Qianli Shen, Yi Ma","submitted_at":"2022-11-28T04:56:40Z","abstract_excerpt":"Pessimism is of great importance in offline reinforcement learning (RL). One broad category of offline RL algorithms fulfills pessimism by explicit or implicit behavior regularization. However, most of them only consider policy divergence as behavior regularization, ignoring the effect of how the offline state distribution differs with that of the learning policy, which may lead to under-pessimism for some states and over-pessimism for others. Taking account of this problem, we propose a principled algorithmic framework for offline RL, called \\emph{State-Aware Proximal Pessimism} (SA-PP). The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15065","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/2211.15065/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":"2026-07-05T05:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rnV92NhlinPCAirSVtR1UTl9MUUCAmcmLOIbRw0jSbpVLWgkWFmea6+PurYOnIOiww6RarUu2LM8hIr1xSzwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T14:49:06.710711Z"},"content_sha256":"cb91159886b51598d9a97946d0762cf07eed0963a0d61fcb3bb4b52f7f7d074c","schema_version":"1.0","event_id":"sha256:cb91159886b51598d9a97946d0762cf07eed0963a0d61fcb3bb4b52f7f7d074c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EMD2HODIZMDVLVXJR2JROJ4HBO/bundle.json","state_url":"https://pith.science/pith/EMD2HODIZMDVLVXJR2JROJ4HBO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EMD2HODIZMDVLVXJR2JROJ4HBO/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":"2026-07-16T14:49:06Z","links":{"resolver":"https://pith.science/pith/EMD2HODIZMDVLVXJR2JROJ4HBO","bundle":"https://pith.science/pith/EMD2HODIZMDVLVXJR2JROJ4HBO/bundle.json","state":"https://pith.science/pith/EMD2HODIZMDVLVXJR2JROJ4HBO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EMD2HODIZMDVLVXJR2JROJ4HBO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EMD2HODIZMDVLVXJR2JROJ4HBO","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":"db06ab614fe0fd0795270393a1b4b69d7a505b48da59eff5b804d67a556b6959","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T04:56:40Z","title_canon_sha256":"93c3a4482a8634b1232ea9fb497cc065f7bae3fe259b0af281925763b16b79b7"},"schema_version":"1.0","source":{"id":"2211.15065","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15065","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15065v1","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15065","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"EMD2HODIZMDV","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"EMD2HODIZMDVLVXJ","created_at":"2026-07-05T05:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"EMD2HODI","created_at":"2026-07-05T05:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:cb91159886b51598d9a97946d0762cf07eed0963a0d61fcb3bb4b52f7f7d074c","target":"graph","created_at":"2026-07-05T05:19:59Z","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/2211.15065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pessimism is of great importance in offline reinforcement learning (RL). One broad category of offline RL algorithms fulfills pessimism by explicit or implicit behavior regularization. However, most of them only consider policy divergence as behavior regularization, ignoring the effect of how the offline state distribution differs with that of the learning policy, which may lead to under-pessimism for some states and over-pessimism for others. Taking account of this problem, we propose a principled algorithmic framework for offline RL, called \\emph{State-Aware Proximal Pessimism} (SA-PP). The ","authors_text":"Chao Wang, Chen Chen, Dong Li, Hongyao Tang, Jianye Hao, Qianli Shen, Yi Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T04:56:40Z","title":"State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15065","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:bf0fef3ddf1d853023b37d15bfffb5de2244ad271f14034433a088ce8becb192","target":"record","created_at":"2026-07-05T05:19:59Z","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":"db06ab614fe0fd0795270393a1b4b69d7a505b48da59eff5b804d67a556b6959","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T04:56:40Z","title_canon_sha256":"93c3a4482a8634b1232ea9fb497cc065f7bae3fe259b0af281925763b16b79b7"},"schema_version":"1.0","source":{"id":"2211.15065","kind":"arxiv","version":1}},"canonical_sha256":"2307a3b868cb0755d6e98e931727870bbaa297b492240de7323ecbcb18649db0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2307a3b868cb0755d6e98e931727870bbaa297b492240de7323ecbcb18649db0","first_computed_at":"2026-07-05T05:19:59.375818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:59.375818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eEeziLyuQsV2CVVzM+Y3UE6fbEXiP9o4pACqkRZdJtEIiUlcesQNomfYVmRkWSh5nOhY7eoDoBIcXhWLnsFNAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:59.376226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.15065","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf0fef3ddf1d853023b37d15bfffb5de2244ad271f14034433a088ce8becb192","sha256:cb91159886b51598d9a97946d0762cf07eed0963a0d61fcb3bb4b52f7f7d074c"],"state_sha256":"1e97afaeadae1a35b20cde288876362f1e8744ad6d77d3687397d7f1b17c2fd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GdPbLYdrydGw/+Z4z2UQae+GS+VeduvYc0zkB7iX2Txu34rsLHuXSMi1tk1AQovT4D22Tw+b2KFwo2jppHPmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T14:49:06.714190Z","bundle_sha256":"95cf4cfad80368f4a6539d35cc72fae02e3326a26e18c841809b374c45bd37d8"}}