{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CE4MWMQ44UMEFFDA6UE2CWEXEL","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":"c93e7569265b9c169fcb060471b8e111c4362a399ae439cd23b2d943ba91b8a4","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-13T01:58:24Z","title_canon_sha256":"958f739560d62c66dbd3ca63e2395aa27ca0c550e1d5776132e3c5ed9f631ae0"},"schema_version":"1.0","source":{"id":"2601.08136","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.08136","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2601.08136v2","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.08136","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"CE4MWMQ44UME","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"CE4MWMQ44UMEFFDA","created_at":"2026-06-11T01:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"CE4MWMQ4","created_at":"2026-06-11T01:09:26Z"}],"graph_snapshots":[{"event_id":"sha256:22f18f502100f7a2e495d180d870cd2b91e165b74e3725fcea1a9e382c070772","target":"graph","created_at":"2026-06-11T01:09:26Z","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/2601.08136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion and flow policies are gaining prominence in online reinforcement learning (RL) due to their expressive power, yet training them efficiently remains a critical challenge. A fundamental difficulty that distinguishes online RL from standard generative modeling is the lack of direct samples from the target Boltzmann distribution defined by the Q-function. To address this, two seemingly distinct families of methods have been proposed for diffusion policies: a noise-expectation family, which uses a weighted average of noise as the training target, and a gradient-expectation family, which e","authors_text":"Navid Azizan, Sunbochen Tang, Zeyang Li","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-13T01:58:24Z","title":"Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.08136","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":"sha256:9bd8843e0eecf8f8bea5a27584de6f1cd7e7ca9125d1c8e28bdeb9fd6c14b5d0","target":"record","created_at":"2026-06-11T01:09:26Z","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":"c93e7569265b9c169fcb060471b8e111c4362a399ae439cd23b2d943ba91b8a4","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-13T01:58:24Z","title_canon_sha256":"958f739560d62c66dbd3ca63e2395aa27ca0c550e1d5776132e3c5ed9f631ae0"},"schema_version":"1.0","source":{"id":"2601.08136","kind":"arxiv","version":2}},"canonical_sha256":"1138cb321ce518429460f509a1589722e7fde1c321ed3ee10963dfc01dae5231","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1138cb321ce518429460f509a1589722e7fde1c321ed3ee10963dfc01dae5231","first_computed_at":"2026-06-11T01:09:26.586045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:26.586045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ob6Luc2pqdiL+4qVrDg0RccKX9ZihEAsUniru3QVoAegNaltbdbWQcNC2vFtLF7PV4a+P8N/tUrguvFfmLVPCA==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:26.586624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.08136","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bd8843e0eecf8f8bea5a27584de6f1cd7e7ca9125d1c8e28bdeb9fd6c14b5d0","sha256:22f18f502100f7a2e495d180d870cd2b91e165b74e3725fcea1a9e382c070772"],"state_sha256":"f5634d491b07256252f196a7394429c1144125339bbb095d6b4b7a06e7752a32"}