{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VLL3AYR5D6FGMFGEXYFUXNB4A3","short_pith_number":"pith:VLL3AYR5","canonical_record":{"source":{"id":"2606.24160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T05:28:33Z","cross_cats_sorted":[],"title_canon_sha256":"c9776e09e140fdca85455e7886984270df416a3bdfe5e47de7d04881eeeaddbd","abstract_canon_sha256":"74a2d37ad34afaa0cb6ae5e42e5b1dec1a9c44086234fe99f2dabaf64f268c9e"},"schema_version":"1.0"},"canonical_sha256":"aad7b0623d1f8a6614c4be0b4bb43c06eef369d0630a988e11280702498d4bc1","source":{"kind":"arxiv","id":"2606.24160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24160","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24160v1","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24160","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"VLL3AYR5D6FG","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_16","alias_value":"VLL3AYR5D6FGMFGE","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_8","alias_value":"VLL3AYR5","created_at":"2026-06-24T01:14:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VLL3AYR5D6FGMFGEXYFUXNB4A3","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T05:28:33Z","cross_cats_sorted":[],"title_canon_sha256":"c9776e09e140fdca85455e7886984270df416a3bdfe5e47de7d04881eeeaddbd","abstract_canon_sha256":"74a2d37ad34afaa0cb6ae5e42e5b1dec1a9c44086234fe99f2dabaf64f268c9e"},"schema_version":"1.0"},"canonical_sha256":"aad7b0623d1f8a6614c4be0b4bb43c06eef369d0630a988e11280702498d4bc1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:43.266160Z","signature_b64":"+96fPtc2hKFWXMumTQNTn/HF6FROBixVNNBMJuX4LKGmNTUOpSfhKy7gzKXCUAKgKb3ASelT6P6bWhvHZ/tBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aad7b0623d1f8a6614c4be0b4bb43c06eef369d0630a988e11280702498d4bc1","last_reissued_at":"2026-06-24T01:14:43.265353Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:43.265353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24160","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":"2026-06-24T01:14:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E5stGbfZ+7uroiTADYvxYvzBwa3AWS6aS0zj7BFBPazSbZp9Wg4mDCmviEba8r1SWl6rixPjk6E8aweam9CeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T07:52:56.203151Z"},"content_sha256":"de3b212109c7a537c29180d0c125976c4f93f3a31923b4263aa6d4067e3d45f4","schema_version":"1.0","event_id":"sha256:de3b212109c7a537c29180d0c125976c4f93f3a31923b4263aa6d4067e3d45f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VLL3AYR5D6FGMFGEXYFUXNB4A3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Introduction to Causal Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Elias Bareinboim, Junzhe Zhang, Sanghack Lee","submitted_at":"2026-06-23T05:28:33Z","abstract_excerpt":"Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i.e., what would have happened had reality been different, even when no data of this unrealized reality is currently available. Reinforcement learning provides methods to learn a policy that optimizes a specific measure (e.g., reward, regret) when the agent is deployed in an environment and pursues an exploratory, trial-and-error approach. These two disciplines have evolved independently and with virtually no interaction be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24160","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/2606.24160/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":"2026-06-24T01:14:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VWTNFqT6O74v2iFE4o8LmrI0cc/40SyuoIdNbtV0E3ZxYHGqG8L94by1Vy4eajmxPTR11Avy2KjxNy8QyYhoCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T07:52:56.203558Z"},"content_sha256":"4dc38c1b673c422bde9378f957448c6e6aa99d5c3782315a2e7c9ab27e067c3a","schema_version":"1.0","event_id":"sha256:4dc38c1b673c422bde9378f957448c6e6aa99d5c3782315a2e7c9ab27e067c3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VLL3AYR5D6FGMFGEXYFUXNB4A3/bundle.json","state_url":"https://pith.science/pith/VLL3AYR5D6FGMFGEXYFUXNB4A3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VLL3AYR5D6FGMFGEXYFUXNB4A3/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":"2026-06-26T07:52:56Z","links":{"resolver":"https://pith.science/pith/VLL3AYR5D6FGMFGEXYFUXNB4A3","bundle":"https://pith.science/pith/VLL3AYR5D6FGMFGEXYFUXNB4A3/bundle.json","state":"https://pith.science/pith/VLL3AYR5D6FGMFGEXYFUXNB4A3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VLL3AYR5D6FGMFGEXYFUXNB4A3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VLL3AYR5D6FGMFGEXYFUXNB4A3","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":"74a2d37ad34afaa0cb6ae5e42e5b1dec1a9c44086234fe99f2dabaf64f268c9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T05:28:33Z","title_canon_sha256":"c9776e09e140fdca85455e7886984270df416a3bdfe5e47de7d04881eeeaddbd"},"schema_version":"1.0","source":{"id":"2606.24160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24160","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24160v1","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24160","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"VLL3AYR5D6FG","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_16","alias_value":"VLL3AYR5D6FGMFGE","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_8","alias_value":"VLL3AYR5","created_at":"2026-06-24T01:14:43Z"}],"graph_snapshots":[{"event_id":"sha256:4dc38c1b673c422bde9378f957448c6e6aa99d5c3782315a2e7c9ab27e067c3a","target":"graph","created_at":"2026-06-24T01:14:43Z","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/2606.24160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i.e., what would have happened had reality been different, even when no data of this unrealized reality is currently available. Reinforcement learning provides methods to learn a policy that optimizes a specific measure (e.g., reward, regret) when the agent is deployed in an environment and pursues an exploratory, trial-and-error approach. These two disciplines have evolved independently and with virtually no interaction be","authors_text":"Elias Bareinboim, Junzhe Zhang, Sanghack Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T05:28:33Z","title":"An Introduction to Causal Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24160","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:de3b212109c7a537c29180d0c125976c4f93f3a31923b4263aa6d4067e3d45f4","target":"record","created_at":"2026-06-24T01:14:43Z","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":"74a2d37ad34afaa0cb6ae5e42e5b1dec1a9c44086234fe99f2dabaf64f268c9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T05:28:33Z","title_canon_sha256":"c9776e09e140fdca85455e7886984270df416a3bdfe5e47de7d04881eeeaddbd"},"schema_version":"1.0","source":{"id":"2606.24160","kind":"arxiv","version":1}},"canonical_sha256":"aad7b0623d1f8a6614c4be0b4bb43c06eef369d0630a988e11280702498d4bc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aad7b0623d1f8a6614c4be0b4bb43c06eef369d0630a988e11280702498d4bc1","first_computed_at":"2026-06-24T01:14:43.265353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:43.265353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+96fPtc2hKFWXMumTQNTn/HF6FROBixVNNBMJuX4LKGmNTUOpSfhKy7gzKXCUAKgKb3ASelT6P6bWhvHZ/tBAA==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:43.266160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de3b212109c7a537c29180d0c125976c4f93f3a31923b4263aa6d4067e3d45f4","sha256:4dc38c1b673c422bde9378f957448c6e6aa99d5c3782315a2e7c9ab27e067c3a"],"state_sha256":"7efa9b8c5b98f6b051d2f11c8925a4b0f41e1abf1e423dbbd7871465d26347e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"egpKgPQQVFZVBLh3GRlIQ+hngudGJuTxJoqtBeIA9v7IViLp23yVy+5kytyT6S8G17LVHvxqbltj6SrT/VKPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T07:52:56.205604Z","bundle_sha256":"3fbf430d775abba913ffb7b3a8841224ed6a0925e6517b09abe8c8d3317f52d2"}}