{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NY5J3X2RVZHD5I6JMBDM5MN3NX","short_pith_number":"pith:NY5J3X2R","canonical_record":{"source":{"id":"2312.01072","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T08:49:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d34a020c04419a76a42a1f3f1dc47c6a4712b7ef003e2bf6e51f98a70b6f996","abstract_canon_sha256":"bb95c5618e6c02c9df629fbea2dbb643eba40dafd066f893b4a51ce717810865"},"schema_version":"1.0"},"canonical_sha256":"6e3a9ddf51ae4e3ea3c96046ceb1bb6df27d775a9ddb37d907fbf5d2bb2bd9f3","source":{"kind":"arxiv","id":"2312.01072","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01072","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01072v2","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01072","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"NY5J3X2RVZHD","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_16","alias_value":"NY5J3X2RVZHD5I6J","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_8","alias_value":"NY5J3X2R","created_at":"2026-07-05T08:40:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NY5J3X2RVZHD5I6JMBDM5MN3NX","target":"record","payload":{"canonical_record":{"source":{"id":"2312.01072","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T08:49:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d34a020c04419a76a42a1f3f1dc47c6a4712b7ef003e2bf6e51f98a70b6f996","abstract_canon_sha256":"bb95c5618e6c02c9df629fbea2dbb643eba40dafd066f893b4a51ce717810865"},"schema_version":"1.0"},"canonical_sha256":"6e3a9ddf51ae4e3ea3c96046ceb1bb6df27d775a9ddb37d907fbf5d2bb2bd9f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:10.870921Z","signature_b64":"1tCCsNK0SPXLoe5FOOcYvj5gdwoffU0lKKSkUnY/vWEFZSKxB8XOvOQpoHd7XmwB8iUz2oEF5G29RG29Z7PiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e3a9ddf51ae4e3ea3c96046ceb1bb6df27d775a9ddb37d907fbf5d2bb2bd9f3","last_reissued_at":"2026-07-05T08:40:10.870521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:10.870521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.01072","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":"2026-07-05T08:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K5QcHGVq/bLvQZrCfs0A2GxI5VmxMBgofU5uL6w4FHZx7ZoOvH9almLY0E8zyaP2BFrROdQcSTv+1PWsJNzqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:05:28.092341Z"},"content_sha256":"ab7652727219cf90ae4db80dde92c6956858bfc7c00b6dd27e3575a61cd11caf","schema_version":"1.0","event_id":"sha256:ab7652727219cf90ae4db80dde92c6956858bfc7c00b6dd27e3575a61cd11caf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NY5J3X2RVZHD5I6JMBDM5MN3NX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eduardo Pignatelli, Hado van Hasselt, Johan Ferret, Laura Toni, Matthieu Geist, Olivier Pietquin, Thomas Mesnard","submitted_at":"2023-12-02T08:49:51Z","abstract_excerpt":"The Credit Assignment Problem (CAP) refers to the longstanding challenge of Reinforcement Learning (RL) agents to associate actions with their long-term consequences. Solving the CAP is a crucial step towards the successful deployment of RL in the real world since most decision problems provide feedback that is noisy, delayed, and with little or no information about the causes. These conditions make it hard to distinguish serendipitous outcomes from those caused by informed decision-making. However, the mathematical nature of credit and the CAP remains poorly understood and defined. In this su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01072","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/2312.01072/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":"2026-07-05T08:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0f15uLNl3DO/DT/ijMkIZXw57Iq30ge5cxmcU/huiEhl7rc8BI38g/49EXudnvakSLL09SJUrPR7arNWwD6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:05:28.092835Z"},"content_sha256":"7226921d28821c2ebff6e6a5448aacd200f285a87e5f4a7546509fcc4955498a","schema_version":"1.0","event_id":"sha256:7226921d28821c2ebff6e6a5448aacd200f285a87e5f4a7546509fcc4955498a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NY5J3X2RVZHD5I6JMBDM5MN3NX/bundle.json","state_url":"https://pith.science/pith/NY5J3X2RVZHD5I6JMBDM5MN3NX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NY5J3X2RVZHD5I6JMBDM5MN3NX/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":"2026-08-03T17:05:28Z","links":{"resolver":"https://pith.science/pith/NY5J3X2RVZHD5I6JMBDM5MN3NX","bundle":"https://pith.science/pith/NY5J3X2RVZHD5I6JMBDM5MN3NX/bundle.json","state":"https://pith.science/pith/NY5J3X2RVZHD5I6JMBDM5MN3NX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NY5J3X2RVZHD5I6JMBDM5MN3NX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NY5J3X2RVZHD5I6JMBDM5MN3NX","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":"bb95c5618e6c02c9df629fbea2dbb643eba40dafd066f893b4a51ce717810865","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T08:49:51Z","title_canon_sha256":"3d34a020c04419a76a42a1f3f1dc47c6a4712b7ef003e2bf6e51f98a70b6f996"},"schema_version":"1.0","source":{"id":"2312.01072","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01072","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01072v2","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01072","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"NY5J3X2RVZHD","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_16","alias_value":"NY5J3X2RVZHD5I6J","created_at":"2026-07-05T08:40:10Z"},{"alias_kind":"pith_short_8","alias_value":"NY5J3X2R","created_at":"2026-07-05T08:40:10Z"}],"graph_snapshots":[{"event_id":"sha256:7226921d28821c2ebff6e6a5448aacd200f285a87e5f4a7546509fcc4955498a","target":"graph","created_at":"2026-07-05T08:40:10Z","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/2312.01072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Credit Assignment Problem (CAP) refers to the longstanding challenge of Reinforcement Learning (RL) agents to associate actions with their long-term consequences. Solving the CAP is a crucial step towards the successful deployment of RL in the real world since most decision problems provide feedback that is noisy, delayed, and with little or no information about the causes. These conditions make it hard to distinguish serendipitous outcomes from those caused by informed decision-making. However, the mathematical nature of credit and the CAP remains poorly understood and defined. In this su","authors_text":"Eduardo Pignatelli, Hado van Hasselt, Johan Ferret, Laura Toni, Matthieu Geist, Olivier Pietquin, Thomas Mesnard","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T08:49:51Z","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01072","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:ab7652727219cf90ae4db80dde92c6956858bfc7c00b6dd27e3575a61cd11caf","target":"record","created_at":"2026-07-05T08:40:10Z","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":"bb95c5618e6c02c9df629fbea2dbb643eba40dafd066f893b4a51ce717810865","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-02T08:49:51Z","title_canon_sha256":"3d34a020c04419a76a42a1f3f1dc47c6a4712b7ef003e2bf6e51f98a70b6f996"},"schema_version":"1.0","source":{"id":"2312.01072","kind":"arxiv","version":2}},"canonical_sha256":"6e3a9ddf51ae4e3ea3c96046ceb1bb6df27d775a9ddb37d907fbf5d2bb2bd9f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e3a9ddf51ae4e3ea3c96046ceb1bb6df27d775a9ddb37d907fbf5d2bb2bd9f3","first_computed_at":"2026-07-05T08:40:10.870521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:10.870521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1tCCsNK0SPXLoe5FOOcYvj5gdwoffU0lKKSkUnY/vWEFZSKxB8XOvOQpoHd7XmwB8iUz2oEF5G29RG29Z7PiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:10.870921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01072","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab7652727219cf90ae4db80dde92c6956858bfc7c00b6dd27e3575a61cd11caf","sha256:7226921d28821c2ebff6e6a5448aacd200f285a87e5f4a7546509fcc4955498a"],"state_sha256":"f25eb69f45ca808425fd68ed5f6d2542ab1e628792acd6e617f325e7c6cb1d57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tQAdG/UQuQv+vuds35DYQKagnC7TQFMSBEv48iaNKdLj7mcwotETU4jI67CEWAWR8HdH4g7cOwfFrSQxiksjAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:05:28.096291Z","bundle_sha256":"0eeba63cc64ad22c5ee8e78c846ff15f06a17679e4fbf1c483f8b6da261adc7b"}}