{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O2HCJ6MQEYIBJBYQGMHPOG7DDB","short_pith_number":"pith:O2HCJ6MQ","canonical_record":{"source":{"id":"2507.15073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T18:15:18Z","cross_cats_sorted":[],"title_canon_sha256":"8d9535c01d71904a4c71ff3f9a64ef3f6b997d5c07c18ff973f6557820afa56e","abstract_canon_sha256":"d58a3ccb3321071d2ebb8452487cd2bf26176c7a58e206e9bf657579aae00c7e"},"schema_version":"1.0"},"canonical_sha256":"768e24f9902610148710330ef71be31859eda9c26f23efbe0fd212d41aea8026","source":{"kind":"arxiv","id":"2507.15073","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15073","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15073v1","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15073","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"O2HCJ6MQEYIB","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_16","alias_value":"O2HCJ6MQEYIBJBYQ","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_8","alias_value":"O2HCJ6MQ","created_at":"2026-07-05T11:40:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O2HCJ6MQEYIBJBYQGMHPOG7DDB","target":"record","payload":{"canonical_record":{"source":{"id":"2507.15073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T18:15:18Z","cross_cats_sorted":[],"title_canon_sha256":"8d9535c01d71904a4c71ff3f9a64ef3f6b997d5c07c18ff973f6557820afa56e","abstract_canon_sha256":"d58a3ccb3321071d2ebb8452487cd2bf26176c7a58e206e9bf657579aae00c7e"},"schema_version":"1.0"},"canonical_sha256":"768e24f9902610148710330ef71be31859eda9c26f23efbe0fd212d41aea8026","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:18.118249Z","signature_b64":"AtOmqHm+2UaZBvPIG8XyXLhWW32oefm8kegYWIBx6I9/CsqoKmC6k+GAP+AtPne7/PCARmzupEXEMNTB9FfCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"768e24f9902610148710330ef71be31859eda9c26f23efbe0fd212d41aea8026","last_reissued_at":"2026-07-05T11:40:18.117783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:18.117783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.15073","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ww7xuou180fvQgKsiFJIMjasaPTDsVotkOP1ADuTpfx9fumiS6S6ZtLN418iEFlCzR7PH7r3iaHMu/f39E3PCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:39:53.782690Z"},"content_sha256":"bb01be524b17920898db63cc472bfbc278ce40865ebb3c566bd69ec147878c3e","schema_version":"1.0","event_id":"sha256:bb01be524b17920898db63cc472bfbc278ce40865ebb3c566bd69ec147878c3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O2HCJ6MQEYIBJBYQGMHPOG7DDB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Flow-Matching Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Samuel Pfrommer, Somayeh Sojoudi, Yixiao Huang","submitted_at":"2025-07-20T18:15:18Z","abstract_excerpt":"Flow-matching policies have emerged as a powerful paradigm for generalist robotics. These models are trained to imitate an action chunk, conditioned on sensor observations and textual instructions. Often, training demonstrations are generated by a suboptimal policy, such as a human operator. This work explores training flow-matching policies via reinforcement learning to surpass the original demonstration policy performance. We particularly note minimum-time control as a key application and present a simple scheme for variable-horizon flow-matching planning. We then introduce two families of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15073","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.15073/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rA0XQ+vilqaEn4LOcZp38jtMgCICYm38celjPwtYEaa6cBFV739p6WKNdXAuyZk1+uHqYTJgyRucLzwD30f6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:39:53.783268Z"},"content_sha256":"71bc56fb10e383b75c0cd4ca5681e88f27449b1db0f7ffe73b984558eeec39b5","schema_version":"1.0","event_id":"sha256:71bc56fb10e383b75c0cd4ca5681e88f27449b1db0f7ffe73b984558eeec39b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O2HCJ6MQEYIBJBYQGMHPOG7DDB/bundle.json","state_url":"https://pith.science/pith/O2HCJ6MQEYIBJBYQGMHPOG7DDB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O2HCJ6MQEYIBJBYQGMHPOG7DDB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T23:39:53Z","links":{"resolver":"https://pith.science/pith/O2HCJ6MQEYIBJBYQGMHPOG7DDB","bundle":"https://pith.science/pith/O2HCJ6MQEYIBJBYQGMHPOG7DDB/bundle.json","state":"https://pith.science/pith/O2HCJ6MQEYIBJBYQGMHPOG7DDB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O2HCJ6MQEYIBJBYQGMHPOG7DDB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O2HCJ6MQEYIBJBYQGMHPOG7DDB","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":"d58a3ccb3321071d2ebb8452487cd2bf26176c7a58e206e9bf657579aae00c7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T18:15:18Z","title_canon_sha256":"8d9535c01d71904a4c71ff3f9a64ef3f6b997d5c07c18ff973f6557820afa56e"},"schema_version":"1.0","source":{"id":"2507.15073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15073","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15073v1","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15073","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"O2HCJ6MQEYIB","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_16","alias_value":"O2HCJ6MQEYIBJBYQ","created_at":"2026-07-05T11:40:18Z"},{"alias_kind":"pith_short_8","alias_value":"O2HCJ6MQ","created_at":"2026-07-05T11:40:18Z"}],"graph_snapshots":[{"event_id":"sha256:71bc56fb10e383b75c0cd4ca5681e88f27449b1db0f7ffe73b984558eeec39b5","target":"graph","created_at":"2026-07-05T11:40:18Z","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/2507.15073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Flow-matching policies have emerged as a powerful paradigm for generalist robotics. These models are trained to imitate an action chunk, conditioned on sensor observations and textual instructions. Often, training demonstrations are generated by a suboptimal policy, such as a human operator. This work explores training flow-matching policies via reinforcement learning to surpass the original demonstration policy performance. We particularly note minimum-time control as a key application and present a simple scheme for variable-horizon flow-matching planning. We then introduce two families of a","authors_text":"Samuel Pfrommer, Somayeh Sojoudi, Yixiao Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T18:15:18Z","title":"Reinforcement Learning for Flow-Matching Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15073","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:bb01be524b17920898db63cc472bfbc278ce40865ebb3c566bd69ec147878c3e","target":"record","created_at":"2026-07-05T11:40:18Z","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":"d58a3ccb3321071d2ebb8452487cd2bf26176c7a58e206e9bf657579aae00c7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T18:15:18Z","title_canon_sha256":"8d9535c01d71904a4c71ff3f9a64ef3f6b997d5c07c18ff973f6557820afa56e"},"schema_version":"1.0","source":{"id":"2507.15073","kind":"arxiv","version":1}},"canonical_sha256":"768e24f9902610148710330ef71be31859eda9c26f23efbe0fd212d41aea8026","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"768e24f9902610148710330ef71be31859eda9c26f23efbe0fd212d41aea8026","first_computed_at":"2026-07-05T11:40:18.117783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:18.117783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AtOmqHm+2UaZBvPIG8XyXLhWW32oefm8kegYWIBx6I9/CsqoKmC6k+GAP+AtPne7/PCARmzupEXEMNTB9FfCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:18.118249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb01be524b17920898db63cc472bfbc278ce40865ebb3c566bd69ec147878c3e","sha256:71bc56fb10e383b75c0cd4ca5681e88f27449b1db0f7ffe73b984558eeec39b5"],"state_sha256":"460bb4d07f74d081fc0dd10a7aa9b6f2ff8ee1471a609828cf290274c1e4a470"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aec8erfbV88f8lPu/LiA3v2cnUGgSslQGRhYX8IxVmes5nbvpjMLyx3+EwWtZQIewlYPsx+9VvGzxiJDQMdNDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T23:39:53.786807Z","bundle_sha256":"0fbaab5dc9a83f7bb4d4e6faf24c7da488ef831970cdb6004bd8a5db9c11325e"}}