{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:K7AULTKZZ6QLX3KTQZSBKVU5NF","short_pith_number":"pith:K7AULTKZ","canonical_record":{"source":{"id":"2103.08050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-14T22:11:40Z","cross_cats_sorted":[],"title_canon_sha256":"a5fe9c3fbd6af219fa0f69631bc740ffa448d5ce3be92c0dc91d32922b3ec6c9","abstract_canon_sha256":"baccad898a60929de09bbc02255a9f8b1e7197e1f80a66616d1a9e4e99e6bbe4"},"schema_version":"1.0"},"canonical_sha256":"57c145cd59cfa0bbed53866415569d697e784cbeb620a19e94d0e3c0bc8ff5e0","source":{"kind":"arxiv","id":"2103.08050","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08050","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08050v1","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08050","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"K7AULTKZZ6QL","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"K7AULTKZZ6QLX3KT","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"K7AULTKZ","created_at":"2026-07-05T02:22:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:K7AULTKZZ6QLX3KTQZSBKVU5NF","target":"record","payload":{"canonical_record":{"source":{"id":"2103.08050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-14T22:11:40Z","cross_cats_sorted":[],"title_canon_sha256":"a5fe9c3fbd6af219fa0f69631bc740ffa448d5ce3be92c0dc91d32922b3ec6c9","abstract_canon_sha256":"baccad898a60929de09bbc02255a9f8b1e7197e1f80a66616d1a9e4e99e6bbe4"},"schema_version":"1.0"},"canonical_sha256":"57c145cd59cfa0bbed53866415569d697e784cbeb620a19e94d0e3c0bc8ff5e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:47.243898Z","signature_b64":"bYqGYhRjk97ut0y+l7bJdm8MDw5logOtEc+qJcLZf5Za/9UE3aCsP7+/ECeXhuQDAzqEDbFd8rcUPd6QTCgPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57c145cd59cfa0bbed53866415569d697e784cbeb620a19e94d0e3c0bc8ff5e0","last_reissued_at":"2026-07-05T02:22:47.243436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:47.243436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.08050","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":"2026-07-05T02:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8zuVYS9lbqU80AzfZn/x1VTtaHyRqyOEQ9w0CfhRIt5PNuNG43cqkI8brycoSzLJ4Duwl8K0xx5SkgnPwNk3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:04:00.157986Z"},"content_sha256":"80d93d13b09b127637370062c2e59b8f208756d353c734f171e7afd5a8891c58","schema_version":"1.0","event_id":"sha256:80d93d13b09b127637370062c2e59b8f208756d353c734f171e7afd5a8891c58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:K7AULTKZZ6QLX3KTQZSBKVU5NF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilya Kostrikov, Jonathan Tompson, Ofir Nachum, Rob Fergus","submitted_at":"2021-03-14T22:11:40Z","abstract_excerpt":"Many modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty measuring divergence of the policy from the offline data. In this work, we propose an alternative approach to encouraging the learned policy to stay close to the data, namely parameterizing the critic as the log-behavior-policy, which generated the offline data, plus a state-action value offset term, which can be learned using a neural network. Behavior regularization then corresponds to an appropriate regularizer on the offset t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08050","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/2103.08050/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":"2026-07-05T02:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2PMTYOSEq/Nz8nSp66YykQGGOfesFvUoWSupFMxZByzZVNslc13GbPG7TbrdpXRo3olfXN5SQwXHEj0d98U7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:04:00.158472Z"},"content_sha256":"22b57fd73d000101a4e186c21cc2eec8efe530e3f567085ab7b9e1fb627f08ba","schema_version":"1.0","event_id":"sha256:22b57fd73d000101a4e186c21cc2eec8efe530e3f567085ab7b9e1fb627f08ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K7AULTKZZ6QLX3KTQZSBKVU5NF/bundle.json","state_url":"https://pith.science/pith/K7AULTKZZ6QLX3KTQZSBKVU5NF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K7AULTKZZ6QLX3KTQZSBKVU5NF/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":"2026-08-05T18:04:00Z","links":{"resolver":"https://pith.science/pith/K7AULTKZZ6QLX3KTQZSBKVU5NF","bundle":"https://pith.science/pith/K7AULTKZZ6QLX3KTQZSBKVU5NF/bundle.json","state":"https://pith.science/pith/K7AULTKZZ6QLX3KTQZSBKVU5NF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K7AULTKZZ6QLX3KTQZSBKVU5NF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:K7AULTKZZ6QLX3KTQZSBKVU5NF","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":"baccad898a60929de09bbc02255a9f8b1e7197e1f80a66616d1a9e4e99e6bbe4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-14T22:11:40Z","title_canon_sha256":"a5fe9c3fbd6af219fa0f69631bc740ffa448d5ce3be92c0dc91d32922b3ec6c9"},"schema_version":"1.0","source":{"id":"2103.08050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08050","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08050v1","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08050","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"K7AULTKZZ6QL","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"K7AULTKZZ6QLX3KT","created_at":"2026-07-05T02:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"K7AULTKZ","created_at":"2026-07-05T02:22:47Z"}],"graph_snapshots":[{"event_id":"sha256:22b57fd73d000101a4e186c21cc2eec8efe530e3f567085ab7b9e1fb627f08ba","target":"graph","created_at":"2026-07-05T02:22:47Z","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/2103.08050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty measuring divergence of the policy from the offline data. In this work, we propose an alternative approach to encouraging the learned policy to stay close to the data, namely parameterizing the critic as the log-behavior-policy, which generated the offline data, plus a state-action value offset term, which can be learned using a neural network. Behavior regularization then corresponds to an appropriate regularizer on the offset t","authors_text":"Ilya Kostrikov, Jonathan Tompson, Ofir Nachum, Rob Fergus","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-14T22:11:40Z","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08050","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":"sha256:80d93d13b09b127637370062c2e59b8f208756d353c734f171e7afd5a8891c58","target":"record","created_at":"2026-07-05T02:22:47Z","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":"baccad898a60929de09bbc02255a9f8b1e7197e1f80a66616d1a9e4e99e6bbe4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-14T22:11:40Z","title_canon_sha256":"a5fe9c3fbd6af219fa0f69631bc740ffa448d5ce3be92c0dc91d32922b3ec6c9"},"schema_version":"1.0","source":{"id":"2103.08050","kind":"arxiv","version":1}},"canonical_sha256":"57c145cd59cfa0bbed53866415569d697e784cbeb620a19e94d0e3c0bc8ff5e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57c145cd59cfa0bbed53866415569d697e784cbeb620a19e94d0e3c0bc8ff5e0","first_computed_at":"2026-07-05T02:22:47.243436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:47.243436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bYqGYhRjk97ut0y+l7bJdm8MDw5logOtEc+qJcLZf5Za/9UE3aCsP7+/ECeXhuQDAzqEDbFd8rcUPd6QTCgPAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:47.243898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.08050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80d93d13b09b127637370062c2e59b8f208756d353c734f171e7afd5a8891c58","sha256:22b57fd73d000101a4e186c21cc2eec8efe530e3f567085ab7b9e1fb627f08ba"],"state_sha256":"667c5668e957b46e3ec22a2679a317d97318f5f3136ae8cf29218c48fea1ccd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GrE5sQ1bSxzjN4G4UQFIfdAXgMRbIsGrRn9dDBpfmrRPB+g9dmYNr7zUpnjeiUEZwKdbISUOpAFWrd2O5s1mAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:04:00.161668Z","bundle_sha256":"d885d5a88e68bb7fba5d2d96cbe4008a49d552c107e4793533132e3467c556ed"}}