{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PYNKQX6UTILPKIXSFILCXP466Z","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":"4be3001d065804074a2300272b7a1f4d17c35b42bd1467d813946e20634ad39a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-03T20:47:24Z","title_canon_sha256":"1ba313632cfd637a60b2c81faf4a1722775b3a161ee425ffaffc17a4eb21a8a3"},"schema_version":"1.0","source":{"id":"2510.03508","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.03508","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2510.03508v3","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03508","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"PYNKQX6UTILP","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"PYNKQX6UTILPKIXS","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"PYNKQX6U","created_at":"2026-05-25T02:01:07Z"}],"graph_snapshots":[{"event_id":"sha256:565a244083fcda9d937e4e992b114889ce2a4cd3fb47c3525ebc7fe540f5a210","target":"graph","created_at":"2026-05-25T02:01:07Z","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/2510.03508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement objective that avoids the high variance of typical policy gradients and the complexity of backpropagation through time. This stable learning process is critically enabled by our second contribution: a robust distributional critic, which we design through a fusion of distributional RL and clipped double Q-learning. The resulting algorithm is highly effective, achieving state-of-the-art performance on a benchmark of eigh","authors_text":"Bradly C Stadie, Hanrui Lyu, Lunjun Zhang, Shuo Han","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-03T20:47:24Z","title":"D2 Actor Critic: Diffusion Actor Meets Distributional Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03508","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":"sha256:955b68e49725d41e3595cf8334bcdd38da71ae7985f8b9e19757e573d9acb456","target":"record","created_at":"2026-05-25T02:01:07Z","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":"4be3001d065804074a2300272b7a1f4d17c35b42bd1467d813946e20634ad39a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-03T20:47:24Z","title_canon_sha256":"1ba313632cfd637a60b2c81faf4a1722775b3a161ee425ffaffc17a4eb21a8a3"},"schema_version":"1.0","source":{"id":"2510.03508","kind":"arxiv","version":3}},"canonical_sha256":"7e1aa85fd49a16f522f22a162bbf9ef66c0b4795c8a6174d115ad1af82d68e7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e1aa85fd49a16f522f22a162bbf9ef66c0b4795c8a6174d115ad1af82d68e7a","first_computed_at":"2026-05-25T02:01:07.819997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:07.819997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cyyIqgt86B23anTNg+VrJtfS4A8emQKc7CRVyd4WyzWPJ3hnEPczh4adu8USYzCqIJqfrz1reP4xKeINt2YECg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:07.820945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.03508","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:955b68e49725d41e3595cf8334bcdd38da71ae7985f8b9e19757e573d9acb456","sha256:565a244083fcda9d937e4e992b114889ce2a4cd3fb47c3525ebc7fe540f5a210"],"state_sha256":"d06e4365ae647670fdc258ac8a8a81f9c01f5df8f49d073eb0802e85b9f0abc6"}