{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XTZR3TCQDQAKPBZDLV3JN5N2NN","short_pith_number":"pith:XTZR3TCQ","canonical_record":{"source":{"id":"2403.08955","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-13T20:50:49Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"df478decd7f3aaf0af59717598c77a507a48d78763733ee78b5ea1b0088d7c26","abstract_canon_sha256":"a3f3873f7cd01af2b1adcab9495e447d81fea42d87a2d013fca6aa9d55bc280f"},"schema_version":"1.0"},"canonical_sha256":"bcf31dcc501c00a787235d7696f5ba6b466bac6c11c82486383c3c58d5ba4d62","source":{"kind":"arxiv","id":"2403.08955","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08955","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08955v4","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08955","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"pith_short_12","alias_value":"XTZR3TCQDQAK","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"pith_short_16","alias_value":"XTZR3TCQDQAKPBZD","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"pith_short_8","alias_value":"XTZR3TCQ","created_at":"2026-07-05T12:01:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XTZR3TCQDQAKPBZDLV3JN5N2NN","target":"record","payload":{"canonical_record":{"source":{"id":"2403.08955","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-13T20:50:49Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"df478decd7f3aaf0af59717598c77a507a48d78763733ee78b5ea1b0088d7c26","abstract_canon_sha256":"a3f3873f7cd01af2b1adcab9495e447d81fea42d87a2d013fca6aa9d55bc280f"},"schema_version":"1.0"},"canonical_sha256":"bcf31dcc501c00a787235d7696f5ba6b466bac6c11c82486383c3c58d5ba4d62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:53.444462Z","signature_b64":"tuy9qTE4EFzfaF/TzqClZBiTCe58hleemwTr0QgTbhIvWBWvv57Hdr04rMNRV+kd67kBehyD5paTZh5n7mkBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcf31dcc501c00a787235d7696f5ba6b466bac6c11c82486383c3c58d5ba4d62","last_reissued_at":"2026-07-05T12:01:53.443983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:53.443983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.08955","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+9UbiNY+zzrSnFkDTW3m/1ZdYfGjQEpqQ4IjYCsJdJplWsABG54SuPXWH7ZPGi4GvjUFvGqjx0SafT4Q1+jmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:07:16.099434Z"},"content_sha256":"7ed6045028f100ba83732aae97e9bb38103cb522f41b18299c8acef31c84b051","schema_version":"1.0","event_id":"sha256:7ed6045028f100ba83732aae97e9bb38103cb522f41b18299c8acef31c84b051"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XTZR3TCQDQAKPBZDLV3JN5N2NN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Anish Gupta, Erfaun Noorani, Pratap Tokekar, Rui Liu","submitted_at":"2024-03-13T20:50:49Z","abstract_excerpt":"Reinforcement Learning (RL) has shown exceptional performance across various applications, enabling autonomous agents to learn optimal policies through interaction with their environments. However, traditional RL frameworks often face challenges in terms of iteration efficiency and safety. Risk-sensitive policy gradient methods, which incorporate both expected return and risk measures, have been explored for their ability to yield safe policies, yet their iteration complexity remains largely underexplored. In this work, we conduct a rigorous iteration complexity analysis for the risk-sensitive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08955","kind":"arxiv","version":4},"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/2403.08955/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":"2026-07-05T12:01:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3++CAwQAmgoZg9dawG8PiYPwtMSG0bv31Yzsvh1wiIsHQmrIeuldGaJGRR2uU2JujhdrWHBGtmDTM4yhWFNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:07:16.100175Z"},"content_sha256":"102f4f8b664e391866c98bad9ba1c15f5c87092a25793ffdda9a72a76323abd1","schema_version":"1.0","event_id":"sha256:102f4f8b664e391866c98bad9ba1c15f5c87092a25793ffdda9a72a76323abd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTZR3TCQDQAKPBZDLV3JN5N2NN/bundle.json","state_url":"https://pith.science/pith/XTZR3TCQDQAKPBZDLV3JN5N2NN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTZR3TCQDQAKPBZDLV3JN5N2NN/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":"2026-08-04T01:07:16Z","links":{"resolver":"https://pith.science/pith/XTZR3TCQDQAKPBZDLV3JN5N2NN","bundle":"https://pith.science/pith/XTZR3TCQDQAKPBZDLV3JN5N2NN/bundle.json","state":"https://pith.science/pith/XTZR3TCQDQAKPBZDLV3JN5N2NN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTZR3TCQDQAKPBZDLV3JN5N2NN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XTZR3TCQDQAKPBZDLV3JN5N2NN","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":"a3f3873f7cd01af2b1adcab9495e447d81fea42d87a2d013fca6aa9d55bc280f","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-13T20:50:49Z","title_canon_sha256":"df478decd7f3aaf0af59717598c77a507a48d78763733ee78b5ea1b0088d7c26"},"schema_version":"1.0","source":{"id":"2403.08955","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08955","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08955v4","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08955","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"pith_short_12","alias_value":"XTZR3TCQDQAK","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"pith_short_16","alias_value":"XTZR3TCQDQAKPBZD","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"pith_short_8","alias_value":"XTZR3TCQ","created_at":"2026-07-05T12:01:53Z"}],"graph_snapshots":[{"event_id":"sha256:102f4f8b664e391866c98bad9ba1c15f5c87092a25793ffdda9a72a76323abd1","target":"graph","created_at":"2026-07-05T12:01:53Z","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/2403.08955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has shown exceptional performance across various applications, enabling autonomous agents to learn optimal policies through interaction with their environments. However, traditional RL frameworks often face challenges in terms of iteration efficiency and safety. Risk-sensitive policy gradient methods, which incorporate both expected return and risk measures, have been explored for their ability to yield safe policies, yet their iteration complexity remains largely underexplored. In this work, we conduct a rigorous iteration complexity analysis for the risk-sensitive","authors_text":"Anish Gupta, Erfaun Noorani, Pratap Tokekar, Rui Liu","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-13T20:50:49Z","title":"Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08955","kind":"arxiv","version":4},"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":"sha256:7ed6045028f100ba83732aae97e9bb38103cb522f41b18299c8acef31c84b051","target":"record","created_at":"2026-07-05T12:01:53Z","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":"a3f3873f7cd01af2b1adcab9495e447d81fea42d87a2d013fca6aa9d55bc280f","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-13T20:50:49Z","title_canon_sha256":"df478decd7f3aaf0af59717598c77a507a48d78763733ee78b5ea1b0088d7c26"},"schema_version":"1.0","source":{"id":"2403.08955","kind":"arxiv","version":4}},"canonical_sha256":"bcf31dcc501c00a787235d7696f5ba6b466bac6c11c82486383c3c58d5ba4d62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcf31dcc501c00a787235d7696f5ba6b466bac6c11c82486383c3c58d5ba4d62","first_computed_at":"2026-07-05T12:01:53.443983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:53.443983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tuy9qTE4EFzfaF/TzqClZBiTCe58hleemwTr0QgTbhIvWBWvv57Hdr04rMNRV+kd67kBehyD5paTZh5n7mkBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:53.444462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08955","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ed6045028f100ba83732aae97e9bb38103cb522f41b18299c8acef31c84b051","sha256:102f4f8b664e391866c98bad9ba1c15f5c87092a25793ffdda9a72a76323abd1"],"state_sha256":"4c5a3ebfe4aa20669671f8c0a4e4a43edb0aa997cd9218f280e8801e3ca8e7ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"507xGf3lBOns6ar3IJLPMm3NxYh8ng49BgSW6M8Jp+QsHH/PyrlzJQdCe9aV8MMPKO3ucUbV1SFQ6q+/JIZpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:07:16.105305Z","bundle_sha256":"94835794362071adeb7ae70d5bff6c0537230e6ebcd028227c2bd39e70f65c5f"}}