{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5WZ6PQSMOYRCVNYZJPUYVF5VXG","short_pith_number":"pith:5WZ6PQSM","canonical_record":{"source":{"id":"2206.01474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T09:53:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f88bf5789abf041af6cf03dbd73e3da4009ada43a30532e699cb6c047792e04e","abstract_canon_sha256":"699a71a28ff237535ed59bb61241ff68dc630474edeb23dbf794fe57a304d8b4"},"schema_version":"1.0"},"canonical_sha256":"edb3e7c24c76222ab7194be98a97b5b9a08ec2085214e0118e83090b356b6a4a","source":{"kind":"arxiv","id":"2206.01474","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01474","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01474v1","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01474","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"5WZ6PQSMOYRC","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"5WZ6PQSMOYRCVNYZ","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"5WZ6PQSM","created_at":"2026-07-05T04:28:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5WZ6PQSMOYRCVNYZJPUYVF5VXG","target":"record","payload":{"canonical_record":{"source":{"id":"2206.01474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T09:53:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f88bf5789abf041af6cf03dbd73e3da4009ada43a30532e699cb6c047792e04e","abstract_canon_sha256":"699a71a28ff237535ed59bb61241ff68dc630474edeb23dbf794fe57a304d8b4"},"schema_version":"1.0"},"canonical_sha256":"edb3e7c24c76222ab7194be98a97b5b9a08ec2085214e0118e83090b356b6a4a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:48.162112Z","signature_b64":"VuBxVR+VcxGZryvJ7oD+2lw+uTehsDcpGl22zBNewjd0zvGZYIWf7+xAUNF+appM+nD6voezQkNpKe4Is3bsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edb3e7c24c76222ab7194be98a97b5b9a08ec2085214e0118e83090b356b6a4a","last_reissued_at":"2026-07-05T04:28:48.161651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:48.161651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.01474","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":"2026-07-05T04:28:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TExIcJ2avZqe2z0vcREeGzxQHNKW72Ao9HvRJpctSY7aBYpRrIGMB/j6pcLJq8nUaYh1tc2u1uwtccRcFK7sAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T16:50:48.410791Z"},"content_sha256":"c3666508acde5e2a8f7293455b7780a3d400fcfaf3f1fd6c163566fcdaa11018","schema_version":"1.0","event_id":"sha256:c3666508acde5e2a8f7293455b7780a3d400fcfaf3f1fd6c163566fcdaa11018"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5WZ6PQSMOYRCVNYZJPUYVF5VXG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning with Causal Structured World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hong-Long Tian, Kun Zhang, Xiong-Hui Chen, Yang Yu, Zheng-Mao Zhu","submitted_at":"2022-06-03T09:53:57Z","abstract_excerpt":"Model-based methods have recently shown promising for offline reinforcement learning (RL), aiming to learn good policies from historical data without interacting with the environment. Previous model-based offline RL methods learn fully connected nets as world-models that map the states and actions to the next-step states. However, it is sensible that a world-model should adhere to the underlying causal effect such that it will support learning an effective policy generalizing well in unseen states. In this paper, We first provide theoretical results that causal world-models can outperform plai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01474","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/2206.01474/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":"2026-07-05T04:28:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYkiHmv9BwZefrjKObmscOuU9JBb51KmnmKjN0LOAz3BrqWQo9zqpAJOSQ9Hb069ICenOhUPNP9d1xDbs6GxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T16:50:48.411166Z"},"content_sha256":"5cb7c77e73e3d862ca543f0d6ddf609d69059dd53c9c4ce6396f664505adca4a","schema_version":"1.0","event_id":"sha256:5cb7c77e73e3d862ca543f0d6ddf609d69059dd53c9c4ce6396f664505adca4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WZ6PQSMOYRCVNYZJPUYVF5VXG/bundle.json","state_url":"https://pith.science/pith/5WZ6PQSMOYRCVNYZJPUYVF5VXG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WZ6PQSMOYRCVNYZJPUYVF5VXG/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":"2026-08-22T16:50:48Z","links":{"resolver":"https://pith.science/pith/5WZ6PQSMOYRCVNYZJPUYVF5VXG","bundle":"https://pith.science/pith/5WZ6PQSMOYRCVNYZJPUYVF5VXG/bundle.json","state":"https://pith.science/pith/5WZ6PQSMOYRCVNYZJPUYVF5VXG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WZ6PQSMOYRCVNYZJPUYVF5VXG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5WZ6PQSMOYRCVNYZJPUYVF5VXG","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":"699a71a28ff237535ed59bb61241ff68dc630474edeb23dbf794fe57a304d8b4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T09:53:57Z","title_canon_sha256":"f88bf5789abf041af6cf03dbd73e3da4009ada43a30532e699cb6c047792e04e"},"schema_version":"1.0","source":{"id":"2206.01474","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01474","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01474v1","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01474","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"5WZ6PQSMOYRC","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"5WZ6PQSMOYRCVNYZ","created_at":"2026-07-05T04:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"5WZ6PQSM","created_at":"2026-07-05T04:28:48Z"}],"graph_snapshots":[{"event_id":"sha256:5cb7c77e73e3d862ca543f0d6ddf609d69059dd53c9c4ce6396f664505adca4a","target":"graph","created_at":"2026-07-05T04:28:48Z","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/2206.01474/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based methods have recently shown promising for offline reinforcement learning (RL), aiming to learn good policies from historical data without interacting with the environment. Previous model-based offline RL methods learn fully connected nets as world-models that map the states and actions to the next-step states. However, it is sensible that a world-model should adhere to the underlying causal effect such that it will support learning an effective policy generalizing well in unseen states. In this paper, We first provide theoretical results that causal world-models can outperform plai","authors_text":"Hong-Long Tian, Kun Zhang, Xiong-Hui Chen, Yang Yu, Zheng-Mao Zhu","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T09:53:57Z","title":"Offline Reinforcement Learning with Causal Structured World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01474","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:c3666508acde5e2a8f7293455b7780a3d400fcfaf3f1fd6c163566fcdaa11018","target":"record","created_at":"2026-07-05T04:28:48Z","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":"699a71a28ff237535ed59bb61241ff68dc630474edeb23dbf794fe57a304d8b4","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T09:53:57Z","title_canon_sha256":"f88bf5789abf041af6cf03dbd73e3da4009ada43a30532e699cb6c047792e04e"},"schema_version":"1.0","source":{"id":"2206.01474","kind":"arxiv","version":1}},"canonical_sha256":"edb3e7c24c76222ab7194be98a97b5b9a08ec2085214e0118e83090b356b6a4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edb3e7c24c76222ab7194be98a97b5b9a08ec2085214e0118e83090b356b6a4a","first_computed_at":"2026-07-05T04:28:48.161651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:48.161651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VuBxVR+VcxGZryvJ7oD+2lw+uTehsDcpGl22zBNewjd0zvGZYIWf7+xAUNF+appM+nD6voezQkNpKe4Is3bsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:48.162112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.01474","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3666508acde5e2a8f7293455b7780a3d400fcfaf3f1fd6c163566fcdaa11018","sha256:5cb7c77e73e3d862ca543f0d6ddf609d69059dd53c9c4ce6396f664505adca4a"],"state_sha256":"fc55c002e7b2397d6bcd05aa2b406053f865d12212894c9f5a1f2c40cf8bac58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8b6HImgC9ohyLN0P78RIB6O+4sz+zSWrwTZ+ENHCaX2rlHIj6rJ9r8GCxBergNK64Eg/DLj8w0AX0bCcoOSBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T16:50:48.413716Z","bundle_sha256":"3b766279669392bbbf0146ca7a1d0bb557bb7f2175e180343ad28ad7c0667d07"}}