{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:33YXYH6VUYQUBIFL4GH7JATHRF","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":"fe91732a2c660308121d3ddaccd5427e7c482338cc108707791cbd973cb2e1eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-02T09:49:26Z","title_canon_sha256":"10fc9199b84ac41b3970de659faa40036c0ee39fdf4ede49e6111721aa8547b0"},"schema_version":"1.0","source":{"id":"2512.02581","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.02581","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2512.02581v3","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02581","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"33YXYH6VUYQU","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"33YXYH6VUYQUBIFL","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"33YXYH6V","created_at":"2026-06-23T01:12:50Z"}],"graph_snapshots":[{"event_id":"sha256:977981366a5b2c7309e7738c93bc9a0e59e8cb80c88a50b69d55b4b16e765ac6","target":"graph","created_at":"2026-06-23T01:12:50Z","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/2512.02581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions required for complex control. Conversely, expressive generative policies -- such as diffusion and flow matching -- can be difficult to optimize in online RL due to intractable likelihoods and gradients propagating through long sampling chains. We address this tension with a key structural principle: decoupling optimization from generation. Building on this, we introduce GoRL (Generative Online Reinforcement Learning","authors_text":"Bo An, Chubin Zhang, Feng Chen, Fuchao Yang, Ivor Tsang, Lang Feng, Xingrui Yu, Yang You, Yaxin Zhou, Zhenglin Wan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-02T09:49:26Z","title":"Training Diffusion Policies via Prior-Mapping Co-Evolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02581","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:c072d3e7b633d9d0edae4a7bc65dc175675f023edc26ec9b47dc8bf4e12a167e","target":"record","created_at":"2026-06-23T01:12:50Z","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":"fe91732a2c660308121d3ddaccd5427e7c482338cc108707791cbd973cb2e1eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-02T09:49:26Z","title_canon_sha256":"10fc9199b84ac41b3970de659faa40036c0ee39fdf4ede49e6111721aa8547b0"},"schema_version":"1.0","source":{"id":"2512.02581","kind":"arxiv","version":3}},"canonical_sha256":"def17c1fd5a62140a0abe18ff4826789553a7ee02f7b80933f49f2655bd0c556","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"def17c1fd5a62140a0abe18ff4826789553a7ee02f7b80933f49f2655bd0c556","first_computed_at":"2026-06-23T01:12:50.259601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:50.259601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MSBJDes1v8XxIkDxJbO8+NAf7xOiT+oPyh1BCfCfpE6iBNmSSY5ar+zWjKQjml6oJlZCoP4cLV3jJKtn3LETCQ==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:50.260164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.02581","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c072d3e7b633d9d0edae4a7bc65dc175675f023edc26ec9b47dc8bf4e12a167e","sha256:977981366a5b2c7309e7738c93bc9a0e59e8cb80c88a50b69d55b4b16e765ac6"],"state_sha256":"f8d6010b279fdb538d67bbe51e404d18acd9d4cab0924e7e17b0d47f51a951f4"}