{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PRFVH2QJVSJ4LQTWIRKN6CNYXC","short_pith_number":"pith:PRFVH2QJ","canonical_record":{"source":{"id":"2405.14749","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T16:16:58Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"67ea860e230d5e02674ba5c34c34daaaf7e2af0b0114a02d572c206a123811b9","abstract_canon_sha256":"dce3ed0822fee564cf953db62940b48d64ed17d2744d6368e6d84312e5ee4cd8"},"schema_version":"1.0"},"canonical_sha256":"7c4b53ea09ac93c5c2764454df09b8b8b116a3aea3d3171dc7e356577dd3c4a1","source":{"kind":"arxiv","id":"2405.14749","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14749","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14749v2","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14749","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_12","alias_value":"PRFVH2QJVSJ4","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_16","alias_value":"PRFVH2QJVSJ4LQTW","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_8","alias_value":"PRFVH2QJ","created_at":"2026-07-05T10:07:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PRFVH2QJVSJ4LQTWIRKN6CNYXC","target":"record","payload":{"canonical_record":{"source":{"id":"2405.14749","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T16:16:58Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"67ea860e230d5e02674ba5c34c34daaaf7e2af0b0114a02d572c206a123811b9","abstract_canon_sha256":"dce3ed0822fee564cf953db62940b48d64ed17d2744d6368e6d84312e5ee4cd8"},"schema_version":"1.0"},"canonical_sha256":"7c4b53ea09ac93c5c2764454df09b8b8b116a3aea3d3171dc7e356577dd3c4a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:41.626974Z","signature_b64":"mul0ep0hxv9sRhF6n/6V0W0U+Wli7CJJ8GyjeVB3e0TgAcoVt4EEf6qeiLDSbyUA3lGLjqwg6Rhj+NHFKk9bCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c4b53ea09ac93c5c2764454df09b8b8b116a3aea3d3171dc7e356577dd3c4a1","last_reissued_at":"2026-07-05T10:07:41.626534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:41.626534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.14749","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":"2026-07-05T10:07:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kgsUAZafz9ad46T1lKyUxr3XW/YC94cURxVw+Ksuz9Oiac15z+dFdnbrZQLHKAlJZ6lx66RV0MmPc8ucwbBsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:38:38.812139Z"},"content_sha256":"29a2622c60669e44ecd484085bd09cfd7239c1f0c974f9170202d34a6a6847bb","schema_version":"1.0","event_id":"sha256:29a2622c60669e44ecd484085bd09cfd7239c1f0c974f9170202d34a6a6847bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PRFVH2QJVSJ4LQTWIRKN6CNYXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Lei Ying, Minheng Xiao, Xian Yu","submitted_at":"2024-05-23T16:16:58Z","abstract_excerpt":"Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn a point estimate of the random cumulative cost, distributional RL (DRL) seeks to estimate the entire distribution of it, which leads to a unified framework for handling different risk measures. However, developing policy gradient methods for risk-sensitive DRL is inherently more complex as it involves finding the gradient of a probability measure. This paper introduces a new policy gradient method for risk-sensitive DRL with general c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14749","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/2405.14749/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":"2026-07-05T10:07:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dA1oisKJMnXQo9lVHMm/NZGTbHbRAbN4iO5FjLi+WKxvCdUBna0s03Ski2BHe1aK/VwMEAxLQxOm6kAu53oYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:38:38.812549Z"},"content_sha256":"5b4d5b426142131c21f3a218ec6cc78aa205a416e70752b5ff3ff697026f31de","schema_version":"1.0","event_id":"sha256:5b4d5b426142131c21f3a218ec6cc78aa205a416e70752b5ff3ff697026f31de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PRFVH2QJVSJ4LQTWIRKN6CNYXC/bundle.json","state_url":"https://pith.science/pith/PRFVH2QJVSJ4LQTWIRKN6CNYXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PRFVH2QJVSJ4LQTWIRKN6CNYXC/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":"2026-08-19T02:38:38Z","links":{"resolver":"https://pith.science/pith/PRFVH2QJVSJ4LQTWIRKN6CNYXC","bundle":"https://pith.science/pith/PRFVH2QJVSJ4LQTWIRKN6CNYXC/bundle.json","state":"https://pith.science/pith/PRFVH2QJVSJ4LQTWIRKN6CNYXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PRFVH2QJVSJ4LQTWIRKN6CNYXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PRFVH2QJVSJ4LQTWIRKN6CNYXC","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":"dce3ed0822fee564cf953db62940b48d64ed17d2744d6368e6d84312e5ee4cd8","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T16:16:58Z","title_canon_sha256":"67ea860e230d5e02674ba5c34c34daaaf7e2af0b0114a02d572c206a123811b9"},"schema_version":"1.0","source":{"id":"2405.14749","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14749","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14749v2","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14749","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_12","alias_value":"PRFVH2QJVSJ4","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_16","alias_value":"PRFVH2QJVSJ4LQTW","created_at":"2026-07-05T10:07:41Z"},{"alias_kind":"pith_short_8","alias_value":"PRFVH2QJ","created_at":"2026-07-05T10:07:41Z"}],"graph_snapshots":[{"event_id":"sha256:5b4d5b426142131c21f3a218ec6cc78aa205a416e70752b5ff3ff697026f31de","target":"graph","created_at":"2026-07-05T10:07:41Z","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/2405.14749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn a point estimate of the random cumulative cost, distributional RL (DRL) seeks to estimate the entire distribution of it, which leads to a unified framework for handling different risk measures. However, developing policy gradient methods for risk-sensitive DRL is inherently more complex as it involves finding the gradient of a probability measure. This paper introduces a new policy gradient method for risk-sensitive DRL with general c","authors_text":"Lei Ying, Minheng Xiao, Xian Yu","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T16:16:58Z","title":"Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14749","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":"sha256:29a2622c60669e44ecd484085bd09cfd7239c1f0c974f9170202d34a6a6847bb","target":"record","created_at":"2026-07-05T10:07:41Z","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":"dce3ed0822fee564cf953db62940b48d64ed17d2744d6368e6d84312e5ee4cd8","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T16:16:58Z","title_canon_sha256":"67ea860e230d5e02674ba5c34c34daaaf7e2af0b0114a02d572c206a123811b9"},"schema_version":"1.0","source":{"id":"2405.14749","kind":"arxiv","version":2}},"canonical_sha256":"7c4b53ea09ac93c5c2764454df09b8b8b116a3aea3d3171dc7e356577dd3c4a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c4b53ea09ac93c5c2764454df09b8b8b116a3aea3d3171dc7e356577dd3c4a1","first_computed_at":"2026-07-05T10:07:41.626534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:41.626534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mul0ep0hxv9sRhF6n/6V0W0U+Wli7CJJ8GyjeVB3e0TgAcoVt4EEf6qeiLDSbyUA3lGLjqwg6Rhj+NHFKk9bCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:41.626974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14749","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29a2622c60669e44ecd484085bd09cfd7239c1f0c974f9170202d34a6a6847bb","sha256:5b4d5b426142131c21f3a218ec6cc78aa205a416e70752b5ff3ff697026f31de"],"state_sha256":"544c641a96eebacc69a32ae36a371844525c87cdf291b023c3eaef34de0f0370"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C8ECiJv3deiHad7muBND75nVaHUTlmK+uI64F/KaUh/mRvmEtmxzPipCg2tnMGnRar2nOp073ziAaIzeiQYxDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:38:38.816360Z","bundle_sha256":"23ef08c7906dfedbc199e615ad0c386ef625c51940aae794a8479833cb1db4b4"}}