{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F75ZDXRVZYGU3AGCWS3BY6Q2CI","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":"42a0839417d4a0fe92d729f0cac4b26d72d5efa2159d9d9a44b2f37a2031b599","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-01T18:59:58Z","title_canon_sha256":"1bd16195d8fcbebc445d901be461da8cbadad4fe97b943c68021d918c3005bd5"},"schema_version":"1.0","source":{"id":"2512.02019","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.02019","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2512.02019v3","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02019","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"F75ZDXRVZYGU","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"F75ZDXRVZYGU3AGC","created_at":"2026-05-28T02:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"F75ZDXRV","created_at":"2026-05-28T02:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:e402e3adb89dc0f4c97043635bcd43b3e0e96ca69b3a962c2b3acfa91e892a9c","target":"graph","created_at":"2026-05-28T02:04:44Z","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/2512.02019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models excel at sampling from complex, unnormalized distributions. In this work, we extend Maximum Entropy Reinforcement Learning (ME-RL) to diffusion processes, enabling sampling from the optimal policy trajectory distribution. By minimizing a tractable upper bound on the reverse KL divergence between the diffusion policy and the optimal policy trajectory distributions, we derive a modified surrogate objective and introduce Diffusion-Augmented Markov Decision Processes (DA-MDPs). DA-MDPs allow for seamless integration of diffusion policies into any ME-RL method with minimal modifica","authors_text":"Kaustubh Patil, Sebastian Sanokowski","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-01T18:59:58Z","title":"Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02019","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":"sha256:9ca032278b1a6795b39177cd63af027a86b71368ae913c467cbb01114c4bb915","target":"record","created_at":"2026-05-28T02:04:44Z","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":"42a0839417d4a0fe92d729f0cac4b26d72d5efa2159d9d9a44b2f37a2031b599","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-01T18:59:58Z","title_canon_sha256":"1bd16195d8fcbebc445d901be461da8cbadad4fe97b943c68021d918c3005bd5"},"schema_version":"1.0","source":{"id":"2512.02019","kind":"arxiv","version":3}},"canonical_sha256":"2ffb91de35ce0d4d80c2b4b61c7a1a120c21dc6ac6a11dcf774b9267958a11df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ffb91de35ce0d4d80c2b4b61c7a1a120c21dc6ac6a11dcf774b9267958a11df","first_computed_at":"2026-05-28T02:04:44.669599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:44.669599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hc4LiHrctZIILlRFtqQpO7tsD5QudOLLKXCQ42h30I2DQ8wytp8aXVpPs7+63+GsBzZRkdNleoWr90ciricMBA==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:44.670261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.02019","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ca032278b1a6795b39177cd63af027a86b71368ae913c467cbb01114c4bb915","sha256:e402e3adb89dc0f4c97043635bcd43b3e0e96ca69b3a962c2b3acfa91e892a9c"],"state_sha256":"81a2b54c01dfa55e13fd09b725327471bce3ea3ba23d52b2a6c4c5af7c13d529"}