{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:M2IYGFRYVD3IYHWCH2S5HLU3TV","short_pith_number":"pith:M2IYGFRY","canonical_record":{"source":{"id":"2301.04462","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T13:41:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"935dc43789cc7748282b1aa22fc2a95832c21da479ae2ad23f9d7ed0d9be6c72","abstract_canon_sha256":"d88f8a37aaa0d32e0ce2c85dbff40db21814f94064205c7acff9bb5c293c0e27"},"schema_version":"1.0"},"canonical_sha256":"6691831638a8f68c1ec23ea5d3ae9b9d6814f873a6305430079c89cbac11011d","source":{"kind":"arxiv","id":"2301.04462","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04462","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04462v3","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04462","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"pith_short_12","alias_value":"M2IYGFRYVD3I","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"pith_short_16","alias_value":"M2IYGFRYVD3IYHWC","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"pith_short_8","alias_value":"M2IYGFRY","created_at":"2026-07-05T08:20:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:M2IYGFRYVD3IYHWCH2S5HLU3TV","target":"record","payload":{"canonical_record":{"source":{"id":"2301.04462","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T13:41:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"935dc43789cc7748282b1aa22fc2a95832c21da479ae2ad23f9d7ed0d9be6c72","abstract_canon_sha256":"d88f8a37aaa0d32e0ce2c85dbff40db21814f94064205c7acff9bb5c293c0e27"},"schema_version":"1.0"},"canonical_sha256":"6691831638a8f68c1ec23ea5d3ae9b9d6814f873a6305430079c89cbac11011d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:49.434906Z","signature_b64":"CgMQ/ssu8bpR39UfUvpquOG0WtXDENuL+fZxTVbHNuq8jA4n5uzKNUzUxfXNLifYsZe8XjDRPVizJUGKUaUwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6691831638a8f68c1ec23ea5d3ae9b9d6814f873a6305430079c89cbac11011d","last_reissued_at":"2026-07-05T08:20:49.434428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:49.434428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.04462","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":"2026-07-05T08:20:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q5mMYkgrzrLmAyE7pwkhxDjAv6H3zabklYzDTopvDMShN6yzHB3TJgCQwM3Yyq+gvvvDqW2hkSkT75XCSq+WDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:14:31.238795Z"},"content_sha256":"8e4e9fb052e349f8818e71924da5239b040d615e46330ac32ec44e2b02c0fba4","schema_version":"1.0","event_id":"sha256:8e4e9fb052e349f8818e71924da5239b040d615e46330ac32ec44e2b02c0fba4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:M2IYGFRYVD3IYHWCH2S5HLU3TV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Analysis of Quantile Temporal-Difference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Harutyunyan, Georg Ostrovski, Karl Tuyls, Marc G. Bellemare, Mark Rowland, Mohammad Gheshlaghi Azar, R\\'emi Munos, Will Dabney, Yunhao Tang","submitted_at":"2023-01-11T13:41:56Z","abstract_excerpt":"We analyse quantile temporal-difference learning (QTD), a distributional reinforcement learning algorithm that has proven to be a key component in several successful large-scale applications of reinforcement learning. Despite these empirical successes, a theoretical understanding of QTD has proven elusive until now. Unlike classical TD learning, which can be analysed with standard stochastic approximation tools, QTD updates do not approximate contraction mappings, are highly non-linear, and may have multiple fixed points. The core result of this paper is a proof of convergence to the fixed poi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04462","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/2301.04462/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":"2026-07-05T08:20:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T2jcwbYwcSoOnjp+GzjG3B0WrcjOHQxEWcx2xfHXMcqiLAkj5lKoBsgXLTdxocSvgVb30dHy1HJW187VoOD1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:14:31.239711Z"},"content_sha256":"ab4c51b2e84db7b94985b3c2db0e2a6aec257c39fe6191b38a14e6e7d7c1b30e","schema_version":"1.0","event_id":"sha256:ab4c51b2e84db7b94985b3c2db0e2a6aec257c39fe6191b38a14e6e7d7c1b30e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2IYGFRYVD3IYHWCH2S5HLU3TV/bundle.json","state_url":"https://pith.science/pith/M2IYGFRYVD3IYHWCH2S5HLU3TV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2IYGFRYVD3IYHWCH2S5HLU3TV/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":"2026-08-17T22:14:31Z","links":{"resolver":"https://pith.science/pith/M2IYGFRYVD3IYHWCH2S5HLU3TV","bundle":"https://pith.science/pith/M2IYGFRYVD3IYHWCH2S5HLU3TV/bundle.json","state":"https://pith.science/pith/M2IYGFRYVD3IYHWCH2S5HLU3TV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2IYGFRYVD3IYHWCH2S5HLU3TV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M2IYGFRYVD3IYHWCH2S5HLU3TV","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":"d88f8a37aaa0d32e0ce2c85dbff40db21814f94064205c7acff9bb5c293c0e27","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T13:41:56Z","title_canon_sha256":"935dc43789cc7748282b1aa22fc2a95832c21da479ae2ad23f9d7ed0d9be6c72"},"schema_version":"1.0","source":{"id":"2301.04462","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04462","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04462v3","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04462","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"pith_short_12","alias_value":"M2IYGFRYVD3I","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"pith_short_16","alias_value":"M2IYGFRYVD3IYHWC","created_at":"2026-07-05T08:20:49Z"},{"alias_kind":"pith_short_8","alias_value":"M2IYGFRY","created_at":"2026-07-05T08:20:49Z"}],"graph_snapshots":[{"event_id":"sha256:ab4c51b2e84db7b94985b3c2db0e2a6aec257c39fe6191b38a14e6e7d7c1b30e","target":"graph","created_at":"2026-07-05T08:20:49Z","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/2301.04462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We analyse quantile temporal-difference learning (QTD), a distributional reinforcement learning algorithm that has proven to be a key component in several successful large-scale applications of reinforcement learning. Despite these empirical successes, a theoretical understanding of QTD has proven elusive until now. Unlike classical TD learning, which can be analysed with standard stochastic approximation tools, QTD updates do not approximate contraction mappings, are highly non-linear, and may have multiple fixed points. The core result of this paper is a proof of convergence to the fixed poi","authors_text":"Anna Harutyunyan, Georg Ostrovski, Karl Tuyls, Marc G. Bellemare, Mark Rowland, Mohammad Gheshlaghi Azar, R\\'emi Munos, Will Dabney, Yunhao Tang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T13:41:56Z","title":"An Analysis of Quantile Temporal-Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04462","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":"sha256:8e4e9fb052e349f8818e71924da5239b040d615e46330ac32ec44e2b02c0fba4","target":"record","created_at":"2026-07-05T08:20:49Z","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":"d88f8a37aaa0d32e0ce2c85dbff40db21814f94064205c7acff9bb5c293c0e27","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T13:41:56Z","title_canon_sha256":"935dc43789cc7748282b1aa22fc2a95832c21da479ae2ad23f9d7ed0d9be6c72"},"schema_version":"1.0","source":{"id":"2301.04462","kind":"arxiv","version":3}},"canonical_sha256":"6691831638a8f68c1ec23ea5d3ae9b9d6814f873a6305430079c89cbac11011d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6691831638a8f68c1ec23ea5d3ae9b9d6814f873a6305430079c89cbac11011d","first_computed_at":"2026-07-05T08:20:49.434428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:49.434428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CgMQ/ssu8bpR39UfUvpquOG0WtXDENuL+fZxTVbHNuq8jA4n5uzKNUzUxfXNLifYsZe8XjDRPVizJUGKUaUwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:49.434906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.04462","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e4e9fb052e349f8818e71924da5239b040d615e46330ac32ec44e2b02c0fba4","sha256:ab4c51b2e84db7b94985b3c2db0e2a6aec257c39fe6191b38a14e6e7d7c1b30e"],"state_sha256":"07d12cb703bbc9182ee6119be3ea935e8302dd9df6cb0b5bccd2874cb61fcc74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iU6SgtQ5QNk2Ek8iwLXnCJ8NUiE51+9tHJfkkQnx7zOK27z2ayNcP8Gvg7FKcw3cG3rloA+On6w9NCHVlKGMBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:14:31.246261Z","bundle_sha256":"bd083ddfea6da87a712914e43fb2e6786420010fdc25160116265139ae8d233b"}}