{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FPODNIRO32K2P5J6N35ZINTM3S","short_pith_number":"pith:FPODNIRO","canonical_record":{"source":{"id":"2302.05209","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-10T12:25:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb31f5dba8a6d71c6706da0fb8cd6ecf29aebf17c7b1ec08471c2be4106e4023","abstract_canon_sha256":"0859066889d57f7d44e60cfc22b6bcc360e8b6de51c0772b0cc9c8c21454d3fb"},"schema_version":"1.0"},"canonical_sha256":"2bdc36a22ede95a7f53e6efb94366cdcb279bbedb9cdb1c2abd22e52892b468e","source":{"kind":"arxiv","id":"2302.05209","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05209","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05209v3","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05209","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"FPODNIRO32K2","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"pith_short_16","alias_value":"FPODNIRO32K2P5J6","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"pith_short_8","alias_value":"FPODNIRO","created_at":"2026-07-05T06:16:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FPODNIRO32K2P5J6N35ZINTM3S","target":"record","payload":{"canonical_record":{"source":{"id":"2302.05209","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-10T12:25:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb31f5dba8a6d71c6706da0fb8cd6ecf29aebf17c7b1ec08471c2be4106e4023","abstract_canon_sha256":"0859066889d57f7d44e60cfc22b6bcc360e8b6de51c0772b0cc9c8c21454d3fb"},"schema_version":"1.0"},"canonical_sha256":"2bdc36a22ede95a7f53e6efb94366cdcb279bbedb9cdb1c2abd22e52892b468e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:15.987279Z","signature_b64":"nseU8AzzXONHgvX0DDrZ+/UQBXUfHIZdojnC8pHjwGNj0Q6mdt4lyVeJrud6H9ATzYmbiHB7d6UmoCO62kaADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bdc36a22ede95a7f53e6efb94366cdcb279bbedb9cdb1c2abd22e52892b468e","last_reissued_at":"2026-07-05T06:16:15.986759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:15.986759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.05209","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WL8dwF32iWljrSpYoBgp/DeDxe/WBL1vLbWwxUgzvo1uXn8jsrlj+ZoJNfMg7nnb327XrWKb+qCVgvFygEcjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:31:44.501228Z"},"content_sha256":"dded8c476ec75217baf185007b91cc4d467d83547889bb5698b7a7b74b5bb7f3","schema_version":"1.0","event_id":"sha256:dded8c476ec75217baf185007b91cc4d467d83547889bb5698b7a7b74b5bb7f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FPODNIRO32K2P5J6N35ZINTM3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Causal Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fuchun Sun, Libo Huang, Ruichu Cai, Yan Zeng, Zhifeng Hao","submitted_at":"2023-02-10T12:25:08Z","abstract_excerpt":"While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have leveraged insights from the causality literature recently, bringing forth flourishing works to unify the merits of causality and address well the challenges from RL. As such, it is of great necessity and significance to collate these Causal Reinforcement Learning (CRL) works, offer a review of CRL methods, and investigate the potential functionality from cau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05209","kind":"arxiv","version":3},"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/2302.05209/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":"2026-07-05T06:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oM9HCq46j8z25t1ua/1nGj+S7pdR/bgzf7abLxsfCIErhSD2EB2JKHziUzztxuT3gMUOxqdOLsdk7kbl0ZefBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:31:44.501812Z"},"content_sha256":"41e96ad49676b0e652938964308d5970261183af7f99e8eae855dffeebb72d55","schema_version":"1.0","event_id":"sha256:41e96ad49676b0e652938964308d5970261183af7f99e8eae855dffeebb72d55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S/bundle.json","state_url":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPODNIRO32K2P5J6N35ZINTM3S/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":"2026-08-08T03:31:44Z","links":{"resolver":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S","bundle":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S/bundle.json","state":"https://pith.science/pith/FPODNIRO32K2P5J6N35ZINTM3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPODNIRO32K2P5J6N35ZINTM3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FPODNIRO32K2P5J6N35ZINTM3S","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":"0859066889d57f7d44e60cfc22b6bcc360e8b6de51c0772b0cc9c8c21454d3fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-10T12:25:08Z","title_canon_sha256":"cb31f5dba8a6d71c6706da0fb8cd6ecf29aebf17c7b1ec08471c2be4106e4023"},"schema_version":"1.0","source":{"id":"2302.05209","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05209","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05209v3","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05209","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"FPODNIRO32K2","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"pith_short_16","alias_value":"FPODNIRO32K2P5J6","created_at":"2026-07-05T06:16:15Z"},{"alias_kind":"pith_short_8","alias_value":"FPODNIRO","created_at":"2026-07-05T06:16:15Z"}],"graph_snapshots":[{"event_id":"sha256:41e96ad49676b0e652938964308d5970261183af7f99e8eae855dffeebb72d55","target":"graph","created_at":"2026-07-05T06:16:15Z","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/2302.05209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have leveraged insights from the causality literature recently, bringing forth flourishing works to unify the merits of causality and address well the challenges from RL. As such, it is of great necessity and significance to collate these Causal Reinforcement Learning (CRL) works, offer a review of CRL methods, and investigate the potential functionality from cau","authors_text":"Fuchun Sun, Libo Huang, Ruichu Cai, Yan Zeng, Zhifeng Hao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-10T12:25:08Z","title":"A Survey on Causal Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05209","kind":"arxiv","version":3},"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:dded8c476ec75217baf185007b91cc4d467d83547889bb5698b7a7b74b5bb7f3","target":"record","created_at":"2026-07-05T06:16:15Z","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":"0859066889d57f7d44e60cfc22b6bcc360e8b6de51c0772b0cc9c8c21454d3fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-02-10T12:25:08Z","title_canon_sha256":"cb31f5dba8a6d71c6706da0fb8cd6ecf29aebf17c7b1ec08471c2be4106e4023"},"schema_version":"1.0","source":{"id":"2302.05209","kind":"arxiv","version":3}},"canonical_sha256":"2bdc36a22ede95a7f53e6efb94366cdcb279bbedb9cdb1c2abd22e52892b468e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bdc36a22ede95a7f53e6efb94366cdcb279bbedb9cdb1c2abd22e52892b468e","first_computed_at":"2026-07-05T06:16:15.986759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:15.986759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nseU8AzzXONHgvX0DDrZ+/UQBXUfHIZdojnC8pHjwGNj0Q6mdt4lyVeJrud6H9ATzYmbiHB7d6UmoCO62kaADA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:15.987279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05209","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dded8c476ec75217baf185007b91cc4d467d83547889bb5698b7a7b74b5bb7f3","sha256:41e96ad49676b0e652938964308d5970261183af7f99e8eae855dffeebb72d55"],"state_sha256":"b71c4126772be3f54e3fa5ece5049e97fd8162c38789318e9142da5051f4a58d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qTp4eXo3SC4tZRasFwrCSuKWgkl2jPcSC7lsD0Zbjg2WiGDU/qQQDhsCanrXHdpUstkMxn/QQ0TJNiy/X61tDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:31:44.506418Z","bundle_sha256":"d5b5a352a084aee96ac5e23e70f2a824230406ad00c4d8d88ea9890a044b67b1"}}