{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:37JR44VDWVW4Z3XTMQJE4CBK6E","short_pith_number":"pith:37JR44VD","canonical_record":{"source":{"id":"2307.01452","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T03:00:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0648e6066805dbae51f09ab051a7f07a9f4884fe12691b8eef126fa4f126c447","abstract_canon_sha256":"056f07be9de327ee21c3c798b90804f4801595bf70fd2641219ba6139ed399df"},"schema_version":"1.0"},"canonical_sha256":"dfd31e72a3b56dcceef364124e082af12e80144b950ca4d49a97f24a6b7cdf86","source":{"kind":"arxiv","id":"2307.01452","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01452","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01452v2","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01452","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"37JR44VDWVW4","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"37JR44VDWVW4Z3XT","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"37JR44VD","created_at":"2026-07-05T07:14:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:37JR44VDWVW4Z3XTMQJE4CBK6E","target":"record","payload":{"canonical_record":{"source":{"id":"2307.01452","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T03:00:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0648e6066805dbae51f09ab051a7f07a9f4884fe12691b8eef126fa4f126c447","abstract_canon_sha256":"056f07be9de327ee21c3c798b90804f4801595bf70fd2641219ba6139ed399df"},"schema_version":"1.0"},"canonical_sha256":"dfd31e72a3b56dcceef364124e082af12e80144b950ca4d49a97f24a6b7cdf86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:54.855095Z","signature_b64":"AcUoj4sGr1sHFQy2wqqpXeNFBDopTU2V45kzfYqhl3VxXwWkYTUvDlnX3VxOBBPoQx99cdpWT+FB7M/m0C8aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfd31e72a3b56dcceef364124e082af12e80144b950ca4d49a97f24a6b7cdf86","last_reissued_at":"2026-07-05T07:14:54.854611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:54.854611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.01452","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:14:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQptz/VWNPhBLo8qR1scDe5WIqEmkrxhCU9qdMqXnBW70FC3LHtFTzz20OYH2d0IxQXNKll7dql6DBZjhgHHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:22:50.040168Z"},"content_sha256":"06544e79c8e213733fc8952a41005c96599ab83f10dfb85d15f8b9fbbff62442","schema_version":"1.0","event_id":"sha256:06544e79c8e213733fc8952a41005c96599ab83f10dfb85d15f8b9fbbff62442"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:37JR44VDWVW4Z3XTMQJE4CBK6E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Causal Reinforcement Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Zhihong Deng","submitted_at":"2023-07-04T03:00:43Z","abstract_excerpt":"Reinforcement learning is an essential paradigm for solving sequential decision problems under uncertainty. Despite many remarkable achievements in recent decades, applying reinforcement learning methods in the real world remains challenging. One of the main obstacles is that reinforcement learning agents lack a fundamental understanding of the world and must therefore learn from scratch through numerous trial-and-error interactions. They may also face challenges in providing explanations for their decisions and generalizing the acquired knowledge. Causality, however, offers a notable advantag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01452","kind":"arxiv","version":2},"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/2307.01452/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":"2026-07-05T07:14:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DquvXUrVpFbzdXlyhTZ13Gq4Q5+PuugONf++h7pSHYXm497d7KhnukckBqXVZO2fsP+8ykolyKIi9E9R+vI8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:22:50.041075Z"},"content_sha256":"b83de3895f2b7f79bc0e6404f79f031ac67fcbea0bf30b4c53c74c1472093bde","schema_version":"1.0","event_id":"sha256:b83de3895f2b7f79bc0e6404f79f031ac67fcbea0bf30b4c53c74c1472093bde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37JR44VDWVW4Z3XTMQJE4CBK6E/bundle.json","state_url":"https://pith.science/pith/37JR44VDWVW4Z3XTMQJE4CBK6E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37JR44VDWVW4Z3XTMQJE4CBK6E/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":"2026-08-09T01:22:50Z","links":{"resolver":"https://pith.science/pith/37JR44VDWVW4Z3XTMQJE4CBK6E","bundle":"https://pith.science/pith/37JR44VDWVW4Z3XTMQJE4CBK6E/bundle.json","state":"https://pith.science/pith/37JR44VDWVW4Z3XTMQJE4CBK6E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37JR44VDWVW4Z3XTMQJE4CBK6E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:37JR44VDWVW4Z3XTMQJE4CBK6E","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":"056f07be9de327ee21c3c798b90804f4801595bf70fd2641219ba6139ed399df","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T03:00:43Z","title_canon_sha256":"0648e6066805dbae51f09ab051a7f07a9f4884fe12691b8eef126fa4f126c447"},"schema_version":"1.0","source":{"id":"2307.01452","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01452","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01452v2","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01452","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"37JR44VDWVW4","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"37JR44VDWVW4Z3XT","created_at":"2026-07-05T07:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"37JR44VD","created_at":"2026-07-05T07:14:54Z"}],"graph_snapshots":[{"event_id":"sha256:b83de3895f2b7f79bc0e6404f79f031ac67fcbea0bf30b4c53c74c1472093bde","target":"graph","created_at":"2026-07-05T07:14:54Z","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/2307.01452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning is an essential paradigm for solving sequential decision problems under uncertainty. Despite many remarkable achievements in recent decades, applying reinforcement learning methods in the real world remains challenging. One of the main obstacles is that reinforcement learning agents lack a fundamental understanding of the world and must therefore learn from scratch through numerous trial-and-error interactions. They may also face challenges in providing explanations for their decisions and generalizing the acquired knowledge. Causality, however, offers a notable advantag","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Zhihong Deng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T03:00:43Z","title":"Causal Reinforcement Learning: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01452","kind":"arxiv","version":2},"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":"sha256:06544e79c8e213733fc8952a41005c96599ab83f10dfb85d15f8b9fbbff62442","target":"record","created_at":"2026-07-05T07:14:54Z","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":"056f07be9de327ee21c3c798b90804f4801595bf70fd2641219ba6139ed399df","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-04T03:00:43Z","title_canon_sha256":"0648e6066805dbae51f09ab051a7f07a9f4884fe12691b8eef126fa4f126c447"},"schema_version":"1.0","source":{"id":"2307.01452","kind":"arxiv","version":2}},"canonical_sha256":"dfd31e72a3b56dcceef364124e082af12e80144b950ca4d49a97f24a6b7cdf86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfd31e72a3b56dcceef364124e082af12e80144b950ca4d49a97f24a6b7cdf86","first_computed_at":"2026-07-05T07:14:54.854611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:54.854611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AcUoj4sGr1sHFQy2wqqpXeNFBDopTU2V45kzfYqhl3VxXwWkYTUvDlnX3VxOBBPoQx99cdpWT+FB7M/m0C8aAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:54.855095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01452","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06544e79c8e213733fc8952a41005c96599ab83f10dfb85d15f8b9fbbff62442","sha256:b83de3895f2b7f79bc0e6404f79f031ac67fcbea0bf30b4c53c74c1472093bde"],"state_sha256":"c60aefc473af640e24cea133d805ab218f03661f41b30753492b60703c5565e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PSbQVSXhh6TaNN7AM9eGoOFcWXu6RaXo6RPJ6fdOsbtiCJOVFmUN3iLZZxOu7TkK12hd0W0Bp332jCZAQwwbCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:22:50.047559Z","bundle_sha256":"518b732761394833a57d40b2fac8cd9a86a3dbe64d663a9312b8ba57728d3088"}}