{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:E3IBSVCRTIWL2CMIIFNYYRK46U","short_pith_number":"pith:E3IBSVCR","canonical_record":{"source":{"id":"2206.07166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T20:56:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41ce8a8f8b65eeb837031b102eb5e680df74557e78d75e5cd54a67d2a75a5c09","abstract_canon_sha256":"99f6d8db62d4d4f49c191e55de4a71cf88400a14b39c44f1feecc16d393ca306"},"schema_version":"1.0"},"canonical_sha256":"26d01954519a2cbd0988415b8c455cf51303d1e64d93d60e72278069a4c89ffb","source":{"kind":"arxiv","id":"2206.07166","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07166","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07166v1","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07166","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"pith_short_12","alias_value":"E3IBSVCRTIWL","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"pith_short_16","alias_value":"E3IBSVCRTIWL2CMI","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"pith_short_8","alias_value":"E3IBSVCR","created_at":"2026-07-05T04:32:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:E3IBSVCRTIWL2CMIIFNYYRK46U","target":"record","payload":{"canonical_record":{"source":{"id":"2206.07166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T20:56:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41ce8a8f8b65eeb837031b102eb5e680df74557e78d75e5cd54a67d2a75a5c09","abstract_canon_sha256":"99f6d8db62d4d4f49c191e55de4a71cf88400a14b39c44f1feecc16d393ca306"},"schema_version":"1.0"},"canonical_sha256":"26d01954519a2cbd0988415b8c455cf51303d1e64d93d60e72278069a4c89ffb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:01.631791Z","signature_b64":"xORcFCBlpn8+TpR/0QehqF5Fs//cIKwAn0Nbto32q1PGTTPzT8voVwoBl52REFmU6F7srTS+JbPjZx/laPfjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26d01954519a2cbd0988415b8c455cf51303d1e64d93d60e72278069a4c89ffb","last_reissued_at":"2026-07-05T04:32:01.631239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:01.631239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.07166","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":"2026-07-05T04:32:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yOsnf0I0BB03bdQbzrvDwucZ0XpsdoxhmRrTqvSrrUnDDV416BYf0A8zh7zScki515ECb2M5FlWbqURt76+uAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:54:45.328507Z"},"content_sha256":"0fec6d3019123b649e7351b170ff2fb2d760b0eaf6d478eef21144283e07ae6a","schema_version":"1.0","event_id":"sha256:0fec6d3019123b649e7351b170ff2fb2d760b0eaf6d478eef21144283e07ae6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:E3IBSVCRTIWL2CMIIFNYYRK46U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingyuan Zhou, Shentao Yang, Shujian Zhang, Yihao Feng","submitted_at":"2022-06-14T20:56:16Z","abstract_excerpt":"Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process. A key challenge of offline RL is the instability of policy training, caused by the mismatch between the distribution of the offline data and the undiscounted stationary state-action distribution of the learned policy. To avoid the detrimental impact of distribution mismatch, we regularize the undiscounted stationary distribution of the current policy towards the offline data during the polic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07166","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/2206.07166/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":"2026-07-05T04:32:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GgG9V4qha6ba0r8Q4dKhmK4STfov0od0xrn9DtLIf5/m9guYHrtQawmuOY44/Slc90GGzpwJTOU4ooEu4EqgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:54:45.329044Z"},"content_sha256":"1256cdfc14b2a1be3a5ec2dae0ba60cbfe447d5a542f0724490e359a5b9858df","schema_version":"1.0","event_id":"sha256:1256cdfc14b2a1be3a5ec2dae0ba60cbfe447d5a542f0724490e359a5b9858df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3IBSVCRTIWL2CMIIFNYYRK46U/bundle.json","state_url":"https://pith.science/pith/E3IBSVCRTIWL2CMIIFNYYRK46U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3IBSVCRTIWL2CMIIFNYYRK46U/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":"2026-08-06T22:54:45Z","links":{"resolver":"https://pith.science/pith/E3IBSVCRTIWL2CMIIFNYYRK46U","bundle":"https://pith.science/pith/E3IBSVCRTIWL2CMIIFNYYRK46U/bundle.json","state":"https://pith.science/pith/E3IBSVCRTIWL2CMIIFNYYRK46U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3IBSVCRTIWL2CMIIFNYYRK46U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E3IBSVCRTIWL2CMIIFNYYRK46U","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":"99f6d8db62d4d4f49c191e55de4a71cf88400a14b39c44f1feecc16d393ca306","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T20:56:16Z","title_canon_sha256":"41ce8a8f8b65eeb837031b102eb5e680df74557e78d75e5cd54a67d2a75a5c09"},"schema_version":"1.0","source":{"id":"2206.07166","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07166","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07166v1","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07166","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"pith_short_12","alias_value":"E3IBSVCRTIWL","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"pith_short_16","alias_value":"E3IBSVCRTIWL2CMI","created_at":"2026-07-05T04:32:01Z"},{"alias_kind":"pith_short_8","alias_value":"E3IBSVCR","created_at":"2026-07-05T04:32:01Z"}],"graph_snapshots":[{"event_id":"sha256:1256cdfc14b2a1be3a5ec2dae0ba60cbfe447d5a542f0724490e359a5b9858df","target":"graph","created_at":"2026-07-05T04:32:01Z","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/2206.07166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process. A key challenge of offline RL is the instability of policy training, caused by the mismatch between the distribution of the offline data and the undiscounted stationary state-action distribution of the learned policy. To avoid the detrimental impact of distribution mismatch, we regularize the undiscounted stationary distribution of the current policy towards the offline data during the polic","authors_text":"Mingyuan Zhou, Shentao Yang, Shujian Zhang, Yihao Feng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T20:56:16Z","title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07166","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":"sha256:0fec6d3019123b649e7351b170ff2fb2d760b0eaf6d478eef21144283e07ae6a","target":"record","created_at":"2026-07-05T04:32:01Z","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":"99f6d8db62d4d4f49c191e55de4a71cf88400a14b39c44f1feecc16d393ca306","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T20:56:16Z","title_canon_sha256":"41ce8a8f8b65eeb837031b102eb5e680df74557e78d75e5cd54a67d2a75a5c09"},"schema_version":"1.0","source":{"id":"2206.07166","kind":"arxiv","version":1}},"canonical_sha256":"26d01954519a2cbd0988415b8c455cf51303d1e64d93d60e72278069a4c89ffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26d01954519a2cbd0988415b8c455cf51303d1e64d93d60e72278069a4c89ffb","first_computed_at":"2026-07-05T04:32:01.631239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:01.631239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xORcFCBlpn8+TpR/0QehqF5Fs//cIKwAn0Nbto32q1PGTTPzT8voVwoBl52REFmU6F7srTS+JbPjZx/laPfjDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:01.631791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07166","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fec6d3019123b649e7351b170ff2fb2d760b0eaf6d478eef21144283e07ae6a","sha256:1256cdfc14b2a1be3a5ec2dae0ba60cbfe447d5a542f0724490e359a5b9858df"],"state_sha256":"c3635b3e182185bb9c133202a4ba6cfa462829805f94b29805a239ef6aedbd0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hdjeTbpeJcLqD8uy2n01sK1vGysKVxb5H9wlk63ReB7YzwFeU09UyCKDhlECJr8B5lhxBdDjpxeZ247LBSmoBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:54:45.334794Z","bundle_sha256":"1e75bbbdd381af9b59d7534517f32da6a1fa598da4fd424a175f8e0f5c308bef"}}