{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3J525IU2WG7ORU6FZVMNWTUSOT","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":"0abaf1dfbea88eab91d9110eff16d46c8bd153eb10c97e8e1ba0c20492d9d859","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-18T13:00:20Z","title_canon_sha256":"a3067107296ff065b2860aaee2bf3a3f1c64d86ead6525086c6ee26ae97cde23"},"schema_version":"1.0","source":{"id":"2603.17685","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.17685","created_at":"2026-05-27T01:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2603.17685v3","created_at":"2026-05-27T01:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.17685","created_at":"2026-05-27T01:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"3J525IU2WG7O","created_at":"2026-05-27T01:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"3J525IU2WG7ORU6F","created_at":"2026-05-27T01:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"3J525IU2","created_at":"2026-05-27T01:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:4d0d1e518e8fdc4375c5048299cd08257379116afd6712ef46c3dfe762217e89","target":"graph","created_at":"2026-05-27T01:05:46Z","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/2603.17685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-based diffusion policies can represent complex, multimodal action distributions, they suffer from two critical limitations: their stochastic reverse processes render entropy intractable (necessitating heuristic exploration), and computing policy gradients through long denoising chains is expensive and unstable. In this work, we show that ODE-based flow matching inherently resolves these issues by enabling both simula","authors_text":"Elvin Isufi, Nan Lin, Serge Hoogendoorn, Stavros Orfanoudakis, Ting Gao, Winnie Daamen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-18T13:00:20Z","title":"Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.17685","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":"sha256:765fc9f6a01198fe4a2d783ee3d6e18d18b0495e11d0c5fa884bfb19581b8c0b","target":"record","created_at":"2026-05-27T01:05:46Z","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":"0abaf1dfbea88eab91d9110eff16d46c8bd153eb10c97e8e1ba0c20492d9d859","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-18T13:00:20Z","title_canon_sha256":"a3067107296ff065b2860aaee2bf3a3f1c64d86ead6525086c6ee26ae97cde23"},"schema_version":"1.0","source":{"id":"2603.17685","kind":"arxiv","version":3}},"canonical_sha256":"da7baea29ab1bee8d3c5cd58db4e9274fe9bda2cd067e8eb384c68cf9e6b4e24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da7baea29ab1bee8d3c5cd58db4e9274fe9bda2cd067e8eb384c68cf9e6b4e24","first_computed_at":"2026-05-27T01:05:46.969098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:46.969098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w8SyGgzh/M8InS57tYffaIBv3nc5V30idfg9hrM6I0T2UdA4QaeSjFiePWjqtfwNLMisjAyozLjlrGQi0C06BA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:46.969906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.17685","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:765fc9f6a01198fe4a2d783ee3d6e18d18b0495e11d0c5fa884bfb19581b8c0b","sha256:4d0d1e518e8fdc4375c5048299cd08257379116afd6712ef46c3dfe762217e89"],"state_sha256":"d0f395fe606cb09bb4e0863b7062c7effcfcf9555745946b6c89dd4ceec03249"}