{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HQSDMYTU2HN5LZUNPAVLVW72YV","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":"2c5c761972742fb38ed3e76936409a99f9bf8355787bb37a42db31989fc65dcf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T17:55:21Z","title_canon_sha256":"817776701ac7f6852343c99861c55921f70b742b8adc85321148dfd06ef7d207"},"schema_version":"1.0","source":{"id":"2305.20081","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.20081","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2305.20081v2","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.20081","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"HQSDMYTU2HN5","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"HQSDMYTU2HN5LZUN","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"HQSDMYTU","created_at":"2026-07-05T07:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:88546956b83712c95cb61df3f0e47def6518bf3153fc476ac10202df852b0109","target":"graph","created_at":"2026-07-05T07:05:31Z","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/2305.20081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to learn optimal policies from offline datasets, where the parameterization of policies is crucial but often overlooked. Recently, Diffsuion-QL significantly boosts the performance of offline RL by representing a policy with a diffusion model, whose success relies on a parametrized Markov Chain with hundreds of steps for sampling. However, Diffusion-QL suffers from two critical limitations. 1) It is computationally inefficient to forward and backward through the whole Markov chain during training. 2) It is incompatible with maximum likelihood-based RL a","authors_text":"Bingyi Kang, Chao Du, Shuicheng Yan, Tianyu Pang, Xiao Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T17:55:21Z","title":"Efficient Diffusion Policies for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.20081","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":"sha256:2c8478eaf0a85e8e62d16e850f83a343d999f7356221ddc05c4056d515aff717","target":"record","created_at":"2026-07-05T07:05:31Z","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":"2c5c761972742fb38ed3e76936409a99f9bf8355787bb37a42db31989fc65dcf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T17:55:21Z","title_canon_sha256":"817776701ac7f6852343c99861c55921f70b742b8adc85321148dfd06ef7d207"},"schema_version":"1.0","source":{"id":"2305.20081","kind":"arxiv","version":2}},"canonical_sha256":"3c24366274d1dbd5e68d782abadbfac574968cd3066aa3270acd6a6a01a71343","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c24366274d1dbd5e68d782abadbfac574968cd3066aa3270acd6a6a01a71343","first_computed_at":"2026-07-05T07:05:31.212849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:31.212849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jlB90M3vtIFhnlrOrDsqIl/yCr0j7rNgH/C00NRrfMa/UG7QYhpnVs91Co4i66J7+RF7BDH8DXlA/Dh4HL0tAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:31.213291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.20081","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c8478eaf0a85e8e62d16e850f83a343d999f7356221ddc05c4056d515aff717","sha256:88546956b83712c95cb61df3f0e47def6518bf3153fc476ac10202df852b0109"],"state_sha256":"56490b4c9fdf14da78d3e007447fd0b2906280c6cea1fc1649f01ff93b67f23f"}