{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NO5XSNU75T4BB3AG3BBK7CPBZY","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":"5e8e37b33dd6d5891126c82f0c786994e06a0becdac70f443fdb2c046a49795f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T06:54:09Z","title_canon_sha256":"6a9d18b79c0da769f1183fec384d9f584f4fd25d91d7f40d57f21ba7830fc897"},"schema_version":"1.0","source":{"id":"2606.06967","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06967","created_at":"2026-06-08T01:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06967v1","created_at":"2026-06-08T01:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06967","created_at":"2026-06-08T01:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"NO5XSNU75T4B","created_at":"2026-06-08T01:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"NO5XSNU75T4BB3AG","created_at":"2026-06-08T01:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"NO5XSNU7","created_at":"2026-06-08T01:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:e3148b83c035c39a3d80a3bbd78fc43d608f4d7612564f12486b5f5961fb0042","target":"graph","created_at":"2026-06-08T01:04:38Z","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/2606.06967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative policies provide expressive and multimodal action distributions, making them attractive for reinforcement learning (RL) in complex continuous-control tasks. Among them, flow-based policies are especially appealing because they generate actions through deterministic transport maps. However, applying such generative policies to likelihood-based on-policy learning remains limited by the difficulty of evaluating the probability of executed actions. Existing flow RL methods either replace the true action-density ratio with approximate surrogates, which can introduce biased updates, or re","authors_text":"Jingya Wang, Ke Hu, Panxin Tao, Shutong Ding, Ye Shi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T06:54:09Z","title":"GenPO++: Generative Policy Optimization with Jacobian-free Likelihood Ratios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06967","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:ddd36f1cbed1dbf0e256c093d7692ba64de9f263ff8ee3dca82df72b8acb0b70","target":"record","created_at":"2026-06-08T01:04:38Z","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":"5e8e37b33dd6d5891126c82f0c786994e06a0becdac70f443fdb2c046a49795f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T06:54:09Z","title_canon_sha256":"6a9d18b79c0da769f1183fec384d9f584f4fd25d91d7f40d57f21ba7830fc897"},"schema_version":"1.0","source":{"id":"2606.06967","kind":"arxiv","version":1}},"canonical_sha256":"6bbb79369fecf810ec06d842af89e1ce3285dee525912e813654945be020d6ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bbb79369fecf810ec06d842af89e1ce3285dee525912e813654945be020d6ad","first_computed_at":"2026-06-08T01:04:38.634399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:38.634399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kya7p0xT36uBlNJ6s62YVZbiDmtx0mPx/G5C874SxqJtJEZ48uphTUVirZeoHEupoLJ8gTTkgmjc5P+KIX68CA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:38.635356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06967","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddd36f1cbed1dbf0e256c093d7692ba64de9f263ff8ee3dca82df72b8acb0b70","sha256:e3148b83c035c39a3d80a3bbd78fc43d608f4d7612564f12486b5f5961fb0042"],"state_sha256":"f61bac95287ce967305d97390f7046db4033ca4edaf932c53ccb692d6e0eb6ab"}