{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D6G34IZJ7QQVP465UTHTEFEMKR","short_pith_number":"pith:D6G34IZJ","canonical_record":{"source":{"id":"2403.17646","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-26T12:28:04Z","cross_cats_sorted":[],"title_canon_sha256":"a2d3e0a8086045c321a31d0687380e66c8230e4bd327ab9d865190767f49ad6c","abstract_canon_sha256":"3cb21ce869af57a52cd20b843b0c3ae824b6a30acf5608e5e135d957eb344646"},"schema_version":"1.0"},"canonical_sha256":"1f8dbe2329fc2157f3dda4cf32148c547dbd6240c80a89fd72b45bb961be5b81","source":{"kind":"arxiv","id":"2403.17646","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17646","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17646v2","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17646","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"pith_short_12","alias_value":"D6G34IZJ7QQV","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"pith_short_16","alias_value":"D6G34IZJ7QQVP465","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"pith_short_8","alias_value":"D6G34IZJ","created_at":"2026-07-05T11:30:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D6G34IZJ7QQVP465UTHTEFEMKR","target":"record","payload":{"canonical_record":{"source":{"id":"2403.17646","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-26T12:28:04Z","cross_cats_sorted":[],"title_canon_sha256":"a2d3e0a8086045c321a31d0687380e66c8230e4bd327ab9d865190767f49ad6c","abstract_canon_sha256":"3cb21ce869af57a52cd20b843b0c3ae824b6a30acf5608e5e135d957eb344646"},"schema_version":"1.0"},"canonical_sha256":"1f8dbe2329fc2157f3dda4cf32148c547dbd6240c80a89fd72b45bb961be5b81","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:20.357061Z","signature_b64":"pTlzMExld33lzW5VbcrY1AI50Wyab8rvBQ5gWMBTnV/3zIrMYjDFYTOspCorvBblhtdCn1Xjb+B7oX6YceOlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f8dbe2329fc2157f3dda4cf32148c547dbd6240c80a89fd72b45bb961be5b81","last_reissued_at":"2026-07-05T11:30:20.356426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:20.356426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.17646","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":"2026-07-05T11:30:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkdkAGL2pa+sfSqXunnTNPfCJqW78m5ubkDLaqpqctvlwAPUuCWOm2y4fsMa3/4NLPlQiK75B+EE/DG/+mN7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:08:38.534913Z"},"content_sha256":"0221d788dd438889951d767f2ee6b94c0bfe01b804362ae84e50aa6b6f71c1bc","schema_version":"1.0","event_id":"sha256:0221d788dd438889951d767f2ee6b94c0bfe01b804362ae84e50aa6b6f71c1bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D6G34IZJ7QQVP465UTHTEFEMKR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lina Yao, Siyu Wang, Tong Yu, Xiaocong Chen","submitted_at":"2024-03-26T12:28:04Z","abstract_excerpt":"Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various actions and environmental stochasticity. Traditional approaches primarily emphasize mitigating epistemic uncertainty by learning risk-averse policies, often overlooking environmental stochasticity. In this study, we propose an uncertainty-aware distributional offline RL method to simultaneously address both epistemic uncertainty and environmental stochastici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17646","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/2403.17646/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":"2026-07-05T11:30:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7FYsKhYF19CwyeilSu9tQh2AIY5gSs9mKFu2jkr1eHbon0Cdykmfx+VLITuSemZHEIHKJB09GyAeIxfwED/CAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:08:38.535574Z"},"content_sha256":"b28c96c922656645e09938e6c9355e8f47ff8a0fffad69e979bc8fe52143bdb8","schema_version":"1.0","event_id":"sha256:b28c96c922656645e09938e6c9355e8f47ff8a0fffad69e979bc8fe52143bdb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6G34IZJ7QQVP465UTHTEFEMKR/bundle.json","state_url":"https://pith.science/pith/D6G34IZJ7QQVP465UTHTEFEMKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6G34IZJ7QQVP465UTHTEFEMKR/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":"2026-07-07T05:08:38Z","links":{"resolver":"https://pith.science/pith/D6G34IZJ7QQVP465UTHTEFEMKR","bundle":"https://pith.science/pith/D6G34IZJ7QQVP465UTHTEFEMKR/bundle.json","state":"https://pith.science/pith/D6G34IZJ7QQVP465UTHTEFEMKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6G34IZJ7QQVP465UTHTEFEMKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D6G34IZJ7QQVP465UTHTEFEMKR","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":"3cb21ce869af57a52cd20b843b0c3ae824b6a30acf5608e5e135d957eb344646","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-26T12:28:04Z","title_canon_sha256":"a2d3e0a8086045c321a31d0687380e66c8230e4bd327ab9d865190767f49ad6c"},"schema_version":"1.0","source":{"id":"2403.17646","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17646","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17646v2","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17646","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"pith_short_12","alias_value":"D6G34IZJ7QQV","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"pith_short_16","alias_value":"D6G34IZJ7QQVP465","created_at":"2026-07-05T11:30:20Z"},{"alias_kind":"pith_short_8","alias_value":"D6G34IZJ","created_at":"2026-07-05T11:30:20Z"}],"graph_snapshots":[{"event_id":"sha256:b28c96c922656645e09938e6c9355e8f47ff8a0fffad69e979bc8fe52143bdb8","target":"graph","created_at":"2026-07-05T11:30:20Z","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/2403.17646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various actions and environmental stochasticity. Traditional approaches primarily emphasize mitigating epistemic uncertainty by learning risk-averse policies, often overlooking environmental stochasticity. In this study, we propose an uncertainty-aware distributional offline RL method to simultaneously address both epistemic uncertainty and environmental stochastici","authors_text":"Lina Yao, Siyu Wang, Tong Yu, Xiaocong Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-26T12:28:04Z","title":"Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17646","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":"sha256:0221d788dd438889951d767f2ee6b94c0bfe01b804362ae84e50aa6b6f71c1bc","target":"record","created_at":"2026-07-05T11:30:20Z","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":"3cb21ce869af57a52cd20b843b0c3ae824b6a30acf5608e5e135d957eb344646","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-26T12:28:04Z","title_canon_sha256":"a2d3e0a8086045c321a31d0687380e66c8230e4bd327ab9d865190767f49ad6c"},"schema_version":"1.0","source":{"id":"2403.17646","kind":"arxiv","version":2}},"canonical_sha256":"1f8dbe2329fc2157f3dda4cf32148c547dbd6240c80a89fd72b45bb961be5b81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f8dbe2329fc2157f3dda4cf32148c547dbd6240c80a89fd72b45bb961be5b81","first_computed_at":"2026-07-05T11:30:20.356426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:20.356426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pTlzMExld33lzW5VbcrY1AI50Wyab8rvBQ5gWMBTnV/3zIrMYjDFYTOspCorvBblhtdCn1Xjb+B7oX6YceOlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:20.357061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.17646","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0221d788dd438889951d767f2ee6b94c0bfe01b804362ae84e50aa6b6f71c1bc","sha256:b28c96c922656645e09938e6c9355e8f47ff8a0fffad69e979bc8fe52143bdb8"],"state_sha256":"bf4d1e4702ada8c1a65d6da02bf67a2034c049a916ff33f6242fe582b455a893"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CEmAiLVo8vL+UNSGjk/5qk1Dqj2wTU51MpIQiOIplZ4C5gUZOa2huJrvHJdj5on3S2p3AVJRTBMyyb4BQLyuCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:08:38.538868Z","bundle_sha256":"c9c985da8c8f9bacb2c571bc346d27d8378c06cd98c340689ae9b895d2d2bcfe"}}