{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:EMSTJLD5P3QS7IWU4UKIKZACC7","short_pith_number":"pith:EMSTJLD5","canonical_record":{"source":{"id":"1911.02140","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-05T23:38:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4b92b07c609d6c47c431fb154ee61820b755644bcd045189b5efd470c6399fce","abstract_canon_sha256":"5648465ec1388f0c2734337b32003573b79cd4a2412b36940dafd4f9f3bcb763"},"schema_version":"1.0"},"canonical_sha256":"232534ac7d7ee12fa2d4e51485640217fdf87426df08dadf45babc172b82fb56","source":{"kind":"arxiv","id":"1911.02140","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02140","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02140v3","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02140","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"pith_short_12","alias_value":"EMSTJLD5P3QS","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"pith_short_16","alias_value":"EMSTJLD5P3QS7IWU","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"pith_short_8","alias_value":"EMSTJLD5","created_at":"2026-07-05T01:23:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:EMSTJLD5P3QS7IWU4UKIKZACC7","target":"record","payload":{"canonical_record":{"source":{"id":"1911.02140","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-05T23:38:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4b92b07c609d6c47c431fb154ee61820b755644bcd045189b5efd470c6399fce","abstract_canon_sha256":"5648465ec1388f0c2734337b32003573b79cd4a2412b36940dafd4f9f3bcb763"},"schema_version":"1.0"},"canonical_sha256":"232534ac7d7ee12fa2d4e51485640217fdf87426df08dadf45babc172b82fb56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:55.606232Z","signature_b64":"HHoufAsWVzS0b9H0ossWNg8/ceB6xP9rlCXPpT608ycoAIVUvjdewRfg14vey+4s+tKzJ9CA3pp3DuAxntysDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"232534ac7d7ee12fa2d4e51485640217fdf87426df08dadf45babc172b82fb56","last_reissued_at":"2026-07-05T01:23:55.605822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:55.605822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.02140","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":"2026-07-05T01:23:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bMqlKJ9VPzbQ1cSQDKFQ63oQiM8URu3uaCgB/e39ae/5oi4D9EVk1rmlb0L2MKlfhReMaXvzRqJc4yS+M76gDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:29:53.541131Z"},"content_sha256":"f01c06c931cf156c14191437bd31e4ce6c3653a26eeb0c3919b0dd9b4eadb89d","schema_version":"1.0","event_id":"sha256:f01c06c931cf156c14191437bd31e4ce6c3653a26eeb0c3919b0dd9b4eadb89d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:EMSTJLD5P3QS7IWU4UKIKZACC7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Derek Yang, Jiang Bian, Li Zhao, Tao Qin, Tieyan Liu, Zichuan Lin","submitted_at":"2019-11-05T23:38:57Z","abstract_excerpt":"Distributional Reinforcement Learning (RL) differs from traditional RL in that, rather than the expectation of total returns, it estimates distributions and has achieved state-of-the-art performance on Atari Games. The key challenge in practical distributional RL algorithms lies in how to parameterize estimated distributions so as to better approximate the true continuous distribution. Existing distributional RL algorithms parameterize either the probability side or the return value side of the distribution function, leaving the other side uniformly fixed as in C51, QR-DQN or randomly sampled "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02140","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/1911.02140/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":"2026-07-05T01:23:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u+rhzHVvRHfvhIY4B06aXT8i45eOpyGdzFvmMwa2b055xB03I7lnihLGiMFfzKK9R1F4cw8lgByexICrUfctBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:29:53.543132Z"},"content_sha256":"3d311ff4cf4de115e2bd6bfdaaf30cf1becf8fc28f5b2e1550d23d65799dc283","schema_version":"1.0","event_id":"sha256:3d311ff4cf4de115e2bd6bfdaaf30cf1becf8fc28f5b2e1550d23d65799dc283"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EMSTJLD5P3QS7IWU4UKIKZACC7/bundle.json","state_url":"https://pith.science/pith/EMSTJLD5P3QS7IWU4UKIKZACC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EMSTJLD5P3QS7IWU4UKIKZACC7/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":"2026-08-01T01:29:53Z","links":{"resolver":"https://pith.science/pith/EMSTJLD5P3QS7IWU4UKIKZACC7","bundle":"https://pith.science/pith/EMSTJLD5P3QS7IWU4UKIKZACC7/bundle.json","state":"https://pith.science/pith/EMSTJLD5P3QS7IWU4UKIKZACC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EMSTJLD5P3QS7IWU4UKIKZACC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EMSTJLD5P3QS7IWU4UKIKZACC7","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":"5648465ec1388f0c2734337b32003573b79cd4a2412b36940dafd4f9f3bcb763","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-05T23:38:57Z","title_canon_sha256":"4b92b07c609d6c47c431fb154ee61820b755644bcd045189b5efd470c6399fce"},"schema_version":"1.0","source":{"id":"1911.02140","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.02140","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"arxiv_version","alias_value":"1911.02140v3","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02140","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"pith_short_12","alias_value":"EMSTJLD5P3QS","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"pith_short_16","alias_value":"EMSTJLD5P3QS7IWU","created_at":"2026-07-05T01:23:55Z"},{"alias_kind":"pith_short_8","alias_value":"EMSTJLD5","created_at":"2026-07-05T01:23:55Z"}],"graph_snapshots":[{"event_id":"sha256:3d311ff4cf4de115e2bd6bfdaaf30cf1becf8fc28f5b2e1550d23d65799dc283","target":"graph","created_at":"2026-07-05T01:23:55Z","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/1911.02140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributional Reinforcement Learning (RL) differs from traditional RL in that, rather than the expectation of total returns, it estimates distributions and has achieved state-of-the-art performance on Atari Games. The key challenge in practical distributional RL algorithms lies in how to parameterize estimated distributions so as to better approximate the true continuous distribution. Existing distributional RL algorithms parameterize either the probability side or the return value side of the distribution function, leaving the other side uniformly fixed as in C51, QR-DQN or randomly sampled ","authors_text":"Derek Yang, Jiang Bian, Li Zhao, Tao Qin, Tieyan Liu, Zichuan Lin","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-05T23:38:57Z","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02140","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:f01c06c931cf156c14191437bd31e4ce6c3653a26eeb0c3919b0dd9b4eadb89d","target":"record","created_at":"2026-07-05T01:23:55Z","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":"5648465ec1388f0c2734337b32003573b79cd4a2412b36940dafd4f9f3bcb763","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-05T23:38:57Z","title_canon_sha256":"4b92b07c609d6c47c431fb154ee61820b755644bcd045189b5efd470c6399fce"},"schema_version":"1.0","source":{"id":"1911.02140","kind":"arxiv","version":3}},"canonical_sha256":"232534ac7d7ee12fa2d4e51485640217fdf87426df08dadf45babc172b82fb56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"232534ac7d7ee12fa2d4e51485640217fdf87426df08dadf45babc172b82fb56","first_computed_at":"2026-07-05T01:23:55.605822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:23:55.605822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HHoufAsWVzS0b9H0ossWNg8/ceB6xP9rlCXPpT608ycoAIVUvjdewRfg14vey+4s+tKzJ9CA3pp3DuAxntysDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:23:55.606232Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.02140","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f01c06c931cf156c14191437bd31e4ce6c3653a26eeb0c3919b0dd9b4eadb89d","sha256:3d311ff4cf4de115e2bd6bfdaaf30cf1becf8fc28f5b2e1550d23d65799dc283"],"state_sha256":"d8982b65a4b40a36d707f018d6989cb0a5fb80af0a6cbbbb3d8d8061e8684be6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c4hxJdgs0GP89Nh5vHv9hXx+E1xFrK2UPCJSven0Ap5ms3aLcPlYEcvu5ecbyRh7sEPiJVNKZNOIc3LkuA6AAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T01:29:53.551782Z","bundle_sha256":"9a0a8c6aeb915028f7363abfdb8c32a5c14bae8d87df3062632571697cc60b0f"}}