{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2ROOKFUQ52KJIU5KI2LOLHT54Q","short_pith_number":"pith:2ROOKFUQ","canonical_record":{"source":{"id":"2510.09976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T03:11:18Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"2a35847e86d618ace73bdcad3f1cc7e78eeb3f51bf0d2d0a68eee3bf5de8b35a","abstract_canon_sha256":"736132b540ca4f6e7f88fa80e59039d30c20ecbfff006d672ac71a3637265e83"},"schema_version":"1.0"},"canonical_sha256":"d45ce51690ee949453aa4696e59e7de408866501fae28aea8789b60bd5c98137","source":{"kind":"arxiv","id":"2510.09976","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.09976","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"arxiv_version","alias_value":"2510.09976v2","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09976","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_12","alias_value":"2ROOKFUQ52KJ","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_16","alias_value":"2ROOKFUQ52KJIU5K","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_8","alias_value":"2ROOKFUQ","created_at":"2026-06-26T01:15:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2ROOKFUQ52KJIU5KI2LOLHT54Q","target":"record","payload":{"canonical_record":{"source":{"id":"2510.09976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T03:11:18Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"2a35847e86d618ace73bdcad3f1cc7e78eeb3f51bf0d2d0a68eee3bf5de8b35a","abstract_canon_sha256":"736132b540ca4f6e7f88fa80e59039d30c20ecbfff006d672ac71a3637265e83"},"schema_version":"1.0"},"canonical_sha256":"d45ce51690ee949453aa4696e59e7de408866501fae28aea8789b60bd5c98137","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:46.448699Z","signature_b64":"l9vQzUaRziZ78S9gVDnLRh38htDlL8V5o9uW1CLRslB3MhEautBRnfQi3qfcObrAmo5O7nD0CDounmha7mR3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d45ce51690ee949453aa4696e59e7de408866501fae28aea8789b60bd5c98137","last_reissued_at":"2026-06-26T01:15:46.448171Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:46.448171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.09976","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-26T01:15:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zMnyOJz/hJo8oavTxt3aDpPEnzMmXFBDyoi2VSf1KHUII7ZJJfscmMXMfCHtjJ6n1qHKh+pK6JHeZRR4L4c/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:55:25.836978Z"},"content_sha256":"fcbe72d634dc670cb44390b30ce6602d627f2449443368657bc6765b78076914","schema_version":"1.0","event_id":"sha256:fcbe72d634dc670cb44390b30ce6602d627f2449443368657bc6765b78076914"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2ROOKFUQ52KJIU5KI2LOLHT54Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Erliang Lin, Feifei Zhao, Huangrui Li, Mingyang Lyu, Ruolin Chen, Yinqian Sun, Yi Zeng","submitted_at":"2025-10-11T03:11:18Z","abstract_excerpt":"Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of supervised data. Reinforcement learning (RL) provides a promising path for improving and fine-tuning VLAs through online interaction. However, conventional policy gradient methods are computationally infeasible in the context of flow-matching based models due to the intractability of the importance sampling process, which requires explicit computation of policy ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09976","kind":"arxiv","version":2},"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/2510.09976/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":"2026-06-26T01:15:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MAJzrqxvjgQ0Pdc4AXJ8lrMUQQLljqqqTdI9qP+810JTbkGkU2Y6pbYJZEuoWjFeyh+UtfLPEsbAbdeMWAk1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:55:25.837368Z"},"content_sha256":"ce35d5196f5a551a95141419f98234d40853e3c8af2eaf02afcfab322dea11ec","schema_version":"1.0","event_id":"sha256:ce35d5196f5a551a95141419f98234d40853e3c8af2eaf02afcfab322dea11ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ROOKFUQ52KJIU5KI2LOLHT54Q/bundle.json","state_url":"https://pith.science/pith/2ROOKFUQ52KJIU5KI2LOLHT54Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ROOKFUQ52KJIU5KI2LOLHT54Q/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":"2026-06-28T04:55:25Z","links":{"resolver":"https://pith.science/pith/2ROOKFUQ52KJIU5KI2LOLHT54Q","bundle":"https://pith.science/pith/2ROOKFUQ52KJIU5KI2LOLHT54Q/bundle.json","state":"https://pith.science/pith/2ROOKFUQ52KJIU5KI2LOLHT54Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ROOKFUQ52KJIU5KI2LOLHT54Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2ROOKFUQ52KJIU5KI2LOLHT54Q","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":"736132b540ca4f6e7f88fa80e59039d30c20ecbfff006d672ac71a3637265e83","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T03:11:18Z","title_canon_sha256":"2a35847e86d618ace73bdcad3f1cc7e78eeb3f51bf0d2d0a68eee3bf5de8b35a"},"schema_version":"1.0","source":{"id":"2510.09976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.09976","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"arxiv_version","alias_value":"2510.09976v2","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09976","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_12","alias_value":"2ROOKFUQ52KJ","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_16","alias_value":"2ROOKFUQ52KJIU5K","created_at":"2026-06-26T01:15:46Z"},{"alias_kind":"pith_short_8","alias_value":"2ROOKFUQ","created_at":"2026-06-26T01:15:46Z"}],"graph_snapshots":[{"event_id":"sha256:ce35d5196f5a551a95141419f98234d40853e3c8af2eaf02afcfab322dea11ec","target":"graph","created_at":"2026-06-26T01:15:46Z","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/2510.09976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of supervised data. Reinforcement learning (RL) provides a promising path for improving and fine-tuning VLAs through online interaction. However, conventional policy gradient methods are computationally infeasible in the context of flow-matching based models due to the intractability of the importance sampling process, which requires explicit computation of policy ra","authors_text":"Erliang Lin, Feifei Zhao, Huangrui Li, Mingyang Lyu, Ruolin Chen, Yinqian Sun, Yi Zeng","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T03:11:18Z","title":"Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09976","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:fcbe72d634dc670cb44390b30ce6602d627f2449443368657bc6765b78076914","target":"record","created_at":"2026-06-26T01:15:46Z","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":"736132b540ca4f6e7f88fa80e59039d30c20ecbfff006d672ac71a3637265e83","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-11T03:11:18Z","title_canon_sha256":"2a35847e86d618ace73bdcad3f1cc7e78eeb3f51bf0d2d0a68eee3bf5de8b35a"},"schema_version":"1.0","source":{"id":"2510.09976","kind":"arxiv","version":2}},"canonical_sha256":"d45ce51690ee949453aa4696e59e7de408866501fae28aea8789b60bd5c98137","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d45ce51690ee949453aa4696e59e7de408866501fae28aea8789b60bd5c98137","first_computed_at":"2026-06-26T01:15:46.448171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:46.448171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l9vQzUaRziZ78S9gVDnLRh38htDlL8V5o9uW1CLRslB3MhEautBRnfQi3qfcObrAmo5O7nD0CDounmha7mR3Dw==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:46.448699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.09976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcbe72d634dc670cb44390b30ce6602d627f2449443368657bc6765b78076914","sha256:ce35d5196f5a551a95141419f98234d40853e3c8af2eaf02afcfab322dea11ec"],"state_sha256":"80a77f179b4e6c47f3eff6b5433c20da4b93ab3813ff52e4705ced064c996bb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bYxsX4Bw/jh9ZaN2c0cVVFrM7rlk4zi8ZXwAAiGGbxiADe1hDy2NzqJnUygtVzsnUgiJovvb08uL9WwD7QtmDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T04:55:25.839335Z","bundle_sha256":"d04c159b294408dd720f34921f639ef4e61e08a9f210bc9c4ca08126032010ec"}}