{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OPVOSQF7EIECOWEQDQ7M3XV4ZZ","short_pith_number":"pith:OPVOSQF7","canonical_record":{"source":{"id":"2507.01381","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T05:50:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c67b0c4f4163a2c65bbd7286622985860ff7a54d865d54dad3d1cfcf5b115a48","abstract_canon_sha256":"1a29f2bff123ee08e4e4e452251a95a59e88e61d96a82bc0ed6d641c1b44f588"},"schema_version":"1.0"},"canonical_sha256":"73eae940bf22082758901c3ecddebcce64a52551955347aa52a61c8f4af639af","source":{"kind":"arxiv","id":"2507.01381","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01381","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01381v3","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01381","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"pith_short_12","alias_value":"OPVOSQF7EIEC","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"pith_short_16","alias_value":"OPVOSQF7EIECOWEQ","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"pith_short_8","alias_value":"OPVOSQF7","created_at":"2026-07-05T11:35:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OPVOSQF7EIECOWEQDQ7M3XV4ZZ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.01381","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T05:50:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c67b0c4f4163a2c65bbd7286622985860ff7a54d865d54dad3d1cfcf5b115a48","abstract_canon_sha256":"1a29f2bff123ee08e4e4e452251a95a59e88e61d96a82bc0ed6d641c1b44f588"},"schema_version":"1.0"},"canonical_sha256":"73eae940bf22082758901c3ecddebcce64a52551955347aa52a61c8f4af639af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:14.779568Z","signature_b64":"VRwxZv8aOGfM5reP2idc6Do9/nKt2tqQH5jKD0niWOpYY1Vr0tszioGGnHZJRiZ7LqHElOBryMLXXLCTJdFjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73eae940bf22082758901c3ecddebcce64a52551955347aa52a61c8f4af639af","last_reissued_at":"2026-07-05T11:35:14.779087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:14.779087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.01381","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":"2026-07-05T11:35:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2419riSMgZuLMl+r74WhrXxsi6twyIO2lCQIDfPTsjUq2KgZhqpdga4vK1CSH1zy0LF4RnzNrRMHZXdKMIa5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:06:48.075888Z"},"content_sha256":"8db41d62268540ddd025f92458a8f5dd482090c31dd8d943bb565e3b924124d5","schema_version":"1.0","event_id":"sha256:8db41d62268540ddd025f92458a8f5dd482090c31dd8d943bb565e3b924124d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OPVOSQF7EIECOWEQDQ7M3XV4ZZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributional Soft Actor-Critic with Diffusion Policy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Shuai, Jingliang Duan, Liangfa Chen, Likun Wang, Shengbo Eben Li, Tong Liu, Wenjun Zou, Xujie Song, Yinuo Wang","submitted_at":"2025-07-02T05:50:10Z","abstract_excerpt":"Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However, unimodal distribution often and easily causes bias in value function estimation, leading to poor algorithm performance. This paper proposes a distributional reinforcement learning algorithm called DSAC-D (Distributed Soft Actor Critic with Diffusion Policy) to address the challenges of estimating bias in value functions and obtaining multimodal policy repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01381","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/2507.01381/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":"2026-07-05T11:35:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P9YAuJZvo8sT779aH6UnaSPKq6Su2A0l01Hgk9Y+uJmzDiS8x0bKwnuHQ71nxsrgEguCqTRvVO3EGIpi7H3lDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:06:48.076502Z"},"content_sha256":"d3515648a4f851c29bf7a4276eb5bf468764efea8a0d3c5a6130b4a4ed62c6c5","schema_version":"1.0","event_id":"sha256:d3515648a4f851c29bf7a4276eb5bf468764efea8a0d3c5a6130b4a4ed62c6c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPVOSQF7EIECOWEQDQ7M3XV4ZZ/bundle.json","state_url":"https://pith.science/pith/OPVOSQF7EIECOWEQDQ7M3XV4ZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPVOSQF7EIECOWEQDQ7M3XV4ZZ/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":"2026-08-09T20:06:48Z","links":{"resolver":"https://pith.science/pith/OPVOSQF7EIECOWEQDQ7M3XV4ZZ","bundle":"https://pith.science/pith/OPVOSQF7EIECOWEQDQ7M3XV4ZZ/bundle.json","state":"https://pith.science/pith/OPVOSQF7EIECOWEQDQ7M3XV4ZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPVOSQF7EIECOWEQDQ7M3XV4ZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OPVOSQF7EIECOWEQDQ7M3XV4ZZ","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":"1a29f2bff123ee08e4e4e452251a95a59e88e61d96a82bc0ed6d641c1b44f588","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T05:50:10Z","title_canon_sha256":"c67b0c4f4163a2c65bbd7286622985860ff7a54d865d54dad3d1cfcf5b115a48"},"schema_version":"1.0","source":{"id":"2507.01381","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01381","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01381v3","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01381","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"pith_short_12","alias_value":"OPVOSQF7EIEC","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"pith_short_16","alias_value":"OPVOSQF7EIECOWEQ","created_at":"2026-07-05T11:35:14Z"},{"alias_kind":"pith_short_8","alias_value":"OPVOSQF7","created_at":"2026-07-05T11:35:14Z"}],"graph_snapshots":[{"event_id":"sha256:d3515648a4f851c29bf7a4276eb5bf468764efea8a0d3c5a6130b4a4ed62c6c5","target":"graph","created_at":"2026-07-05T11:35:14Z","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/2507.01381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However, unimodal distribution often and easily causes bias in value function estimation, leading to poor algorithm performance. This paper proposes a distributional reinforcement learning algorithm called DSAC-D (Distributed Soft Actor Critic with Diffusion Policy) to address the challenges of estimating bias in value functions and obtaining multimodal policy repres","authors_text":"Bin Shuai, Jingliang Duan, Liangfa Chen, Likun Wang, Shengbo Eben Li, Tong Liu, Wenjun Zou, Xujie Song, Yinuo Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T05:50:10Z","title":"Distributional Soft Actor-Critic with Diffusion Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01381","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":"sha256:8db41d62268540ddd025f92458a8f5dd482090c31dd8d943bb565e3b924124d5","target":"record","created_at":"2026-07-05T11:35:14Z","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":"1a29f2bff123ee08e4e4e452251a95a59e88e61d96a82bc0ed6d641c1b44f588","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T05:50:10Z","title_canon_sha256":"c67b0c4f4163a2c65bbd7286622985860ff7a54d865d54dad3d1cfcf5b115a48"},"schema_version":"1.0","source":{"id":"2507.01381","kind":"arxiv","version":3}},"canonical_sha256":"73eae940bf22082758901c3ecddebcce64a52551955347aa52a61c8f4af639af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73eae940bf22082758901c3ecddebcce64a52551955347aa52a61c8f4af639af","first_computed_at":"2026-07-05T11:35:14.779087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:14.779087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VRwxZv8aOGfM5reP2idc6Do9/nKt2tqQH5jKD0niWOpYY1Vr0tszioGGnHZJRiZ7LqHElOBryMLXXLCTJdFjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:14.779568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01381","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8db41d62268540ddd025f92458a8f5dd482090c31dd8d943bb565e3b924124d5","sha256:d3515648a4f851c29bf7a4276eb5bf468764efea8a0d3c5a6130b4a4ed62c6c5"],"state_sha256":"b342a4c85d91ef265bd9dc4db3714f8df9b930157f4faab407e282e42fa7ed65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vX/fWIDw4CuQGQQrPVxWtfoa9zVzRBpNEc2pK15/xysiyGojcXBZZ+6Cs1brvqOMGnj5shlg+ZPDp4iIBcBWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:06:48.082104Z","bundle_sha256":"00607d70b7d868ddd83b4d60d92b8a6dd67ab7919fa363294e6c2c0464cee8a2"}}