{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HYW5UXUEU7WCFJVFOC74OFJ77H","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":"e28c0b1a520957b68a9c3499f80a4d90eb4e3b5e2c4e6323bbac4fc720a08bf1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T18:32:25Z","title_canon_sha256":"194aa3db71b87183ec928f6c97c356460fcc37e5337f464eb5c2ee2811c0bc34"},"schema_version":"1.0","source":{"id":"2606.22630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22630","created_at":"2026-06-23T02:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22630v1","created_at":"2026-06-23T02:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22630","created_at":"2026-06-23T02:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"HYW5UXUEU7WC","created_at":"2026-06-23T02:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"HYW5UXUEU7WCFJVF","created_at":"2026-06-23T02:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"HYW5UXUE","created_at":"2026-06-23T02:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:7c7a8a3b74f7da6dc3d9bd7891bb22a8a878d3f7fe840a2707713198da08416f","target":"graph","created_at":"2026-06-23T02:13:43Z","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/2606.22630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, their application to online RL remains limited by the challenge of scalable training in the absence of ground-truth data, where standard optimization techniques such as score matching are not directly applicable. In this work, we introduce a highly efficient algorithm for optimizing diffusion policies by leveraging recent advances in stochastic optimal control. Our approach is based on adjoint matching, which enables simulation-free training and","authors_text":"Denis Blessing, Emiliyan Gospodinov, Gerhard Neumann, Onur Celik, Serge Thilges","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T18:32:25Z","title":"Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22630","kind":"arxiv","version":1},"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":"sha256:72ba5f63248d81f1b3043087bf10a0cdd69a4a4c4be1550d278cd08ef5d8970c","target":"record","created_at":"2026-06-23T02:13:43Z","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":"e28c0b1a520957b68a9c3499f80a4d90eb4e3b5e2c4e6323bbac4fc720a08bf1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T18:32:25Z","title_canon_sha256":"194aa3db71b87183ec928f6c97c356460fcc37e5337f464eb5c2ee2811c0bc34"},"schema_version":"1.0","source":{"id":"2606.22630","kind":"arxiv","version":1}},"canonical_sha256":"3e2dda5e84a7ec22a6a570bfc7153ff9f1b137a40b506d05da7670d31cc1bafa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e2dda5e84a7ec22a6a570bfc7153ff9f1b137a40b506d05da7670d31cc1bafa","first_computed_at":"2026-06-23T02:13:43.543603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:43.543603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fp3nk0zUoVTCL4JPzTsLSKv63T3yboLU8XhVSOsWDtI4JtNiMn2kWqHIzwIQjASv0mCUGHANl4ybd0pRj2NlBw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:43.543990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72ba5f63248d81f1b3043087bf10a0cdd69a4a4c4be1550d278cd08ef5d8970c","sha256:7c7a8a3b74f7da6dc3d9bd7891bb22a8a878d3f7fe840a2707713198da08416f"],"state_sha256":"2c9a36fec41c2957e4cd8f65e8a74229a82840b37591808aa01681fb61199462"}