{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YLBBR7SHXNWNFXR7GQWGGXKQNB","short_pith_number":"pith:YLBBR7SH","canonical_record":{"source":{"id":"1802.08163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-22T16:50:08Z","cross_cats_sorted":[],"title_canon_sha256":"91b55f76eb673dfea8a832abb45297817dc22ad468f2538aaa36cbca24b0ac43","abstract_canon_sha256":"0c3c2201c893ae583e57cdfd6dbab9af1a69ce4a72c7dcb31b93ececa4021c1e"},"schema_version":"1.0"},"canonical_sha256":"c2c218fe47bb6cd2de3f342c635d50684e2a1a07372080f7953e694b25c115b1","source":{"kind":"arxiv","id":"1802.08163","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08163","created_at":"2026-05-18T00:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08163v1","created_at":"2026-05-18T00:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08163","created_at":"2026-05-18T00:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"YLBBR7SHXNWN","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YLBBR7SHXNWNFXR7","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YLBBR7SH","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YLBBR7SHXNWNFXR7GQWGGXKQNB","target":"record","payload":{"canonical_record":{"source":{"id":"1802.08163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-22T16:50:08Z","cross_cats_sorted":[],"title_canon_sha256":"91b55f76eb673dfea8a832abb45297817dc22ad468f2538aaa36cbca24b0ac43","abstract_canon_sha256":"0c3c2201c893ae583e57cdfd6dbab9af1a69ce4a72c7dcb31b93ececa4021c1e"},"schema_version":"1.0"},"canonical_sha256":"c2c218fe47bb6cd2de3f342c635d50684e2a1a07372080f7953e694b25c115b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:45.364252Z","signature_b64":"14Uw4kJGyIYH0I4nP+RjmqqFbnYu29spAgIG/WrGMUirDcUsDS4zHuHpzK4j8anITNFbftu0g7UKTVziaG8bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2c218fe47bb6cd2de3f342c635d50684e2a1a07372080f7953e694b25c115b1","last_reissued_at":"2026-05-18T00:22:45.363808Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:45.363808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.08163","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":"2026-05-18T00:22:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qpck0NkB0Dk8x8l1SdbXDcOwsBBAmClgzUqCFY/U+8xiL0OfHhmS5n8r3FCxtIG8TznWRYfXG0Cw5tJ10otwAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T11:57:19.501492Z"},"content_sha256":"c37208330c2f57d4d93a784f0f4811a979498e57072866a887c22d392628cd32","schema_version":"1.0","event_id":"sha256:c37208330c2f57d4d93a784f0f4811a979498e57072866a887c22d392628cd32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YLBBR7SHXNWNFXR7GQWGGXKQNB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Analysis of Categorical Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Marc G. Bellemare, Mark Rowland, R\\'emi Munos, Will Dabney, Yee Whye Teh","submitted_at":"2018-02-22T16:50:08Z","abstract_excerpt":"Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yield state-of-the-art empirical performance. This was demonstrated by the recently proposed C51 algorithm, based on categorical distributional reinforcement learning (CDRL) [Bellemare et al., 2017]. However, the theoretical properties of CDRL algorithms are not yet well understood. In this paper, we introduce a framework to analyse CDRL algorithms, establish the importance of the projected distributional Bellman opera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08163","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":""},"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":"2026-05-18T00:22:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75nxrvgN3gVFrxp6Y8bwH1tbYkBlvuRR2xVjICP1Zo3UYsHKrVC9iP9mCzBajElcOnD4gbC4S3FPo7cMxFJ3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T11:57:19.501839Z"},"content_sha256":"aa5e37a140ef640ac1fba2a13a0be0fffc73f849f30cb50d5952a6529d5c0c6a","schema_version":"1.0","event_id":"sha256:aa5e37a140ef640ac1fba2a13a0be0fffc73f849f30cb50d5952a6529d5c0c6a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/bundle.json","state_url":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/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":"2026-06-11T11:57:19Z","links":{"resolver":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB","bundle":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/bundle.json","state":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YLBBR7SHXNWNFXR7GQWGGXKQNB","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":"0c3c2201c893ae583e57cdfd6dbab9af1a69ce4a72c7dcb31b93ececa4021c1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-22T16:50:08Z","title_canon_sha256":"91b55f76eb673dfea8a832abb45297817dc22ad468f2538aaa36cbca24b0ac43"},"schema_version":"1.0","source":{"id":"1802.08163","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08163","created_at":"2026-05-18T00:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08163v1","created_at":"2026-05-18T00:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08163","created_at":"2026-05-18T00:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"YLBBR7SHXNWN","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YLBBR7SHXNWNFXR7","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YLBBR7SH","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:aa5e37a140ef640ac1fba2a13a0be0fffc73f849f30cb50d5952a6529d5c0c6a","target":"graph","created_at":"2026-05-18T00:22:45Z","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"},"paper":{"abstract_excerpt":"Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yield state-of-the-art empirical performance. This was demonstrated by the recently proposed C51 algorithm, based on categorical distributional reinforcement learning (CDRL) [Bellemare et al., 2017]. However, the theoretical properties of CDRL algorithms are not yet well understood. In this paper, we introduce a framework to analyse CDRL algorithms, establish the importance of the projected distributional Bellman opera","authors_text":"Marc G. Bellemare, Mark Rowland, R\\'emi Munos, Will Dabney, Yee Whye Teh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-22T16:50:08Z","title":"An Analysis of Categorical Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08163","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:c37208330c2f57d4d93a784f0f4811a979498e57072866a887c22d392628cd32","target":"record","created_at":"2026-05-18T00:22:45Z","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":"0c3c2201c893ae583e57cdfd6dbab9af1a69ce4a72c7dcb31b93ececa4021c1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-22T16:50:08Z","title_canon_sha256":"91b55f76eb673dfea8a832abb45297817dc22ad468f2538aaa36cbca24b0ac43"},"schema_version":"1.0","source":{"id":"1802.08163","kind":"arxiv","version":1}},"canonical_sha256":"c2c218fe47bb6cd2de3f342c635d50684e2a1a07372080f7953e694b25c115b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2c218fe47bb6cd2de3f342c635d50684e2a1a07372080f7953e694b25c115b1","first_computed_at":"2026-05-18T00:22:45.363808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:45.363808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"14Uw4kJGyIYH0I4nP+RjmqqFbnYu29spAgIG/WrGMUirDcUsDS4zHuHpzK4j8anITNFbftu0g7UKTVziaG8bBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:45.364252Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.08163","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c37208330c2f57d4d93a784f0f4811a979498e57072866a887c22d392628cd32","sha256:aa5e37a140ef640ac1fba2a13a0be0fffc73f849f30cb50d5952a6529d5c0c6a"],"state_sha256":"fa2f7ed2c56c285e7305a85b37681eb4f89d92a6ada9222f711d7a0d1fa40587"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVO+5MIeYe6oerRVnZd+CiGVf0u9QyFfRirLrClqpVEfe/pgyNQsQ3GHpbRMjPePf1IC0Fjev6vqlogixJKQCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T11:57:19.503685Z","bundle_sha256":"fffe07ec5fe11593694425cc90680a5c589e4223221184571e2067c835dbede6"}}