{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JBYRTBWKRTECOKOZHKGZLCA537","short_pith_number":"pith:JBYRTBWK","canonical_record":{"source":{"id":"2310.05333","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T01:29:17Z","cross_cats_sorted":[],"title_canon_sha256":"6062542f4a608e9c13877cc2cbd145ba89bce80dd195efa11da890c3e58a0208","abstract_canon_sha256":"8870c596e64fdf56d0c742af5129c6511e96e81f9924a496af63cf46751cda80"},"schema_version":"1.0"},"canonical_sha256":"48711986ca8cc82729d93a8d95881ddfcef69850e477f3ddc21ced9eb1ee8eba","source":{"kind":"arxiv","id":"2310.05333","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05333","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05333v2","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05333","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"pith_short_12","alias_value":"JBYRTBWKRTEC","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"pith_short_16","alias_value":"JBYRTBWKRTECOKOZ","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"pith_short_8","alias_value":"JBYRTBWK","created_at":"2026-07-05T07:50:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JBYRTBWKRTECOKOZHKGZLCA537","target":"record","payload":{"canonical_record":{"source":{"id":"2310.05333","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T01:29:17Z","cross_cats_sorted":[],"title_canon_sha256":"6062542f4a608e9c13877cc2cbd145ba89bce80dd195efa11da890c3e58a0208","abstract_canon_sha256":"8870c596e64fdf56d0c742af5129c6511e96e81f9924a496af63cf46751cda80"},"schema_version":"1.0"},"canonical_sha256":"48711986ca8cc82729d93a8d95881ddfcef69850e477f3ddc21ced9eb1ee8eba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:03.797092Z","signature_b64":"wtg4JAaPewIwKqZIOyNOTKbMxsvG1IF8hfqaauXDNXIFZYVP32tY1nPPLGWW0m8/qaUdCuLV7IOiiasZpq0pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48711986ca8cc82729d93a8d95881ddfcef69850e477f3ddc21ced9eb1ee8eba","last_reissued_at":"2026-07-05T07:50:03.796589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:03.796589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.05333","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":"2026-07-05T07:50:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cDfDhEfr9aoWvNJ+B3hTW5/2aOL+IM35wU+hEovZdJ3gMMAmjqLmEcGd9YUDx++61KShG0S8+uLX3cMpj4BUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:46:28.074862Z"},"content_sha256":"c743cfa9e826ece86b4203603ff9480614f75193fef4a806b21b949b545ac3aa","schema_version":"1.0","event_id":"sha256:c743cfa9e826ece86b4203603ff9480614f75193fef4a806b21b949b545ac3aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JBYRTBWKRTECOKOZHKGZLCA537","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junbo Tan, Linrui Zhang, Li Shen, Longxiang He, Xueqian Wang","submitted_at":"2023-10-09T01:29:17Z","abstract_excerpt":"Constrained policy search (CPS) is a fundamental problem in offline reinforcement learning, which is generally solved by advantage weighted regression (AWR). However, previous methods may still encounter out-of-distribution actions due to the limited expressivity of Gaussian-based policies. On the other hand, directly applying the state-of-the-art models with distribution expression capabilities (i.e., diffusion models) in the AWR framework is intractable since AWR requires exact policy probability densities, which is intractable in diffusion models. In this paper, we propose a novel approach,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05333","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/2310.05333/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":"2026-07-05T07:50:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"543lsg+W0/f/q34FE9i0f1IDfdRqHHVLz1dzSZEdv6z8H6CWVa30KXnHO2x8d4AfFhpVuKnfN1mLG1pVC+TwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:46:28.075243Z"},"content_sha256":"9e3b06126ca0551543861f3e32a3798f0e89c85d88536f1268bcd7a8e41e43a3","schema_version":"1.0","event_id":"sha256:9e3b06126ca0551543861f3e32a3798f0e89c85d88536f1268bcd7a8e41e43a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JBYRTBWKRTECOKOZHKGZLCA537/bundle.json","state_url":"https://pith.science/pith/JBYRTBWKRTECOKOZHKGZLCA537/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JBYRTBWKRTECOKOZHKGZLCA537/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":"2026-07-06T17:46:28Z","links":{"resolver":"https://pith.science/pith/JBYRTBWKRTECOKOZHKGZLCA537","bundle":"https://pith.science/pith/JBYRTBWKRTECOKOZHKGZLCA537/bundle.json","state":"https://pith.science/pith/JBYRTBWKRTECOKOZHKGZLCA537/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JBYRTBWKRTECOKOZHKGZLCA537/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JBYRTBWKRTECOKOZHKGZLCA537","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":"8870c596e64fdf56d0c742af5129c6511e96e81f9924a496af63cf46751cda80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T01:29:17Z","title_canon_sha256":"6062542f4a608e9c13877cc2cbd145ba89bce80dd195efa11da890c3e58a0208"},"schema_version":"1.0","source":{"id":"2310.05333","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05333","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05333v2","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05333","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"pith_short_12","alias_value":"JBYRTBWKRTEC","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"pith_short_16","alias_value":"JBYRTBWKRTECOKOZ","created_at":"2026-07-05T07:50:03Z"},{"alias_kind":"pith_short_8","alias_value":"JBYRTBWK","created_at":"2026-07-05T07:50:03Z"}],"graph_snapshots":[{"event_id":"sha256:9e3b06126ca0551543861f3e32a3798f0e89c85d88536f1268bcd7a8e41e43a3","target":"graph","created_at":"2026-07-05T07:50:03Z","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/2310.05333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Constrained policy search (CPS) is a fundamental problem in offline reinforcement learning, which is generally solved by advantage weighted regression (AWR). However, previous methods may still encounter out-of-distribution actions due to the limited expressivity of Gaussian-based policies. On the other hand, directly applying the state-of-the-art models with distribution expression capabilities (i.e., diffusion models) in the AWR framework is intractable since AWR requires exact policy probability densities, which is intractable in diffusion models. In this paper, we propose a novel approach,","authors_text":"Junbo Tan, Linrui Zhang, Li Shen, Longxiang He, Xueqian Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T01:29:17Z","title":"DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05333","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:c743cfa9e826ece86b4203603ff9480614f75193fef4a806b21b949b545ac3aa","target":"record","created_at":"2026-07-05T07:50:03Z","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":"8870c596e64fdf56d0c742af5129c6511e96e81f9924a496af63cf46751cda80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T01:29:17Z","title_canon_sha256":"6062542f4a608e9c13877cc2cbd145ba89bce80dd195efa11da890c3e58a0208"},"schema_version":"1.0","source":{"id":"2310.05333","kind":"arxiv","version":2}},"canonical_sha256":"48711986ca8cc82729d93a8d95881ddfcef69850e477f3ddc21ced9eb1ee8eba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48711986ca8cc82729d93a8d95881ddfcef69850e477f3ddc21ced9eb1ee8eba","first_computed_at":"2026-07-05T07:50:03.796589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:03.796589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wtg4JAaPewIwKqZIOyNOTKbMxsvG1IF8hfqaauXDNXIFZYVP32tY1nPPLGWW0m8/qaUdCuLV7IOiiasZpq0pDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:03.797092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05333","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c743cfa9e826ece86b4203603ff9480614f75193fef4a806b21b949b545ac3aa","sha256:9e3b06126ca0551543861f3e32a3798f0e89c85d88536f1268bcd7a8e41e43a3"],"state_sha256":"a2d90eac6cd08905312b297767d082ccaecae01f1e6c04013217405313d4c7a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGuLBpZz4aWZnJOXVGTBpUoGYiXtAADE48D4PYBj9AR2ueSFxasdsbkynuEn6z/fYoICsaVrMGOyPvRpNSZ0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:46:28.077288Z","bundle_sha256":"22d10c5fdde5a9743cf95cb0a807b9fa33eaa12ce11c37eb3f219aa15f559d5f"}}