{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BXRGR236PXZZ2YIWAKX5XLWJYL","short_pith_number":"pith:BXRGR236","canonical_record":{"source":{"id":"2508.02219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-04T09:11:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3bb91257e7db38171948eab54e8b76530d0de5c9f57eb74138eb0cefb20586f9","abstract_canon_sha256":"14438c4fed2dc0a7104190727899ab1677211fd486649db48bfadc7433764a97"},"schema_version":"1.0"},"canonical_sha256":"0de268eb7e7df39d611602afdbaec9c2fc9e23cf5de943f98a5e90602cfdff6e","source":{"kind":"arxiv","id":"2508.02219","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02219","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02219v1","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02219","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"pith_short_12","alias_value":"BXRGR236PXZZ","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"pith_short_16","alias_value":"BXRGR236PXZZ2YIW","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"pith_short_8","alias_value":"BXRGR236","created_at":"2026-07-05T11:48:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BXRGR236PXZZ2YIWAKX5XLWJYL","target":"record","payload":{"canonical_record":{"source":{"id":"2508.02219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-04T09:11:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3bb91257e7db38171948eab54e8b76530d0de5c9f57eb74138eb0cefb20586f9","abstract_canon_sha256":"14438c4fed2dc0a7104190727899ab1677211fd486649db48bfadc7433764a97"},"schema_version":"1.0"},"canonical_sha256":"0de268eb7e7df39d611602afdbaec9c2fc9e23cf5de943f98a5e90602cfdff6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:10.468379Z","signature_b64":"m7I5rxeiF2tlA1leKBrep9wMyr/1BKgx2FC3LZVvR/Pn0M98mXhwG1DbpJYZgy0ziw0QNjKHIje/eLV5G8N1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0de268eb7e7df39d611602afdbaec9c2fc9e23cf5de943f98a5e90602cfdff6e","last_reissued_at":"2026-07-05T11:48:10.467859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:10.467859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.02219","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":"2026-07-05T11:48:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gOvw1nrx4aaA20duaw7eewg7R8w6WByu8rvg0yLF1M7sg7QqMxmhibInP6vJRx0ioYcX9yH9lgNEdzODbFCxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:08:43.515577Z"},"content_sha256":"e42b11fa29a10d9e3ce06adc0bbd01dd79610bb1fa4e89818f9f18578e7fb5c2","schema_version":"1.0","event_id":"sha256:e42b11fa29a10d9e3ce06adc0bbd01dd79610bb1fa4e89818f9f18578e7fb5c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BXRGR236PXZZ2YIWAKX5XLWJYL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chunhe Xia, Dongchi Huang, Lin Zhao, Tianle Zhang, Yihang Li, Zhirui Fang","submitted_at":"2025-08-04T09:11:48Z","abstract_excerpt":"Vision-Language-Action (VLA) models demonstrate significant potential for developing generalized policies in real-world robotic control. This progress inspires researchers to explore fine-tuning these models with Reinforcement Learning (RL). However, fine-tuning VLA models with RL still faces challenges related to sample efficiency, compatibility with action chunking, and training stability. To address these challenges, we explore the fine-tuning of VLA models through offline reinforcement learning incorporating action chunking. In this work, we propose Chunked RL, a novel reinforcement learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02219","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/2508.02219/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":"2026-07-05T11:48:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NmbTUD4moafnwN4OOZtMYOgV51dP0qZP7GqHTDagO1r5Yn5zQPEoqIMaSokcaBX1jxMCvt2l6+S5kDqcg/n3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:08:43.516093Z"},"content_sha256":"d5fd4476321ad1a3aeb24fdd578eca7153fa770909f53fde08fac534317849fd","schema_version":"1.0","event_id":"sha256:d5fd4476321ad1a3aeb24fdd578eca7153fa770909f53fde08fac534317849fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BXRGR236PXZZ2YIWAKX5XLWJYL/bundle.json","state_url":"https://pith.science/pith/BXRGR236PXZZ2YIWAKX5XLWJYL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BXRGR236PXZZ2YIWAKX5XLWJYL/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":"2026-08-19T12:08:43Z","links":{"resolver":"https://pith.science/pith/BXRGR236PXZZ2YIWAKX5XLWJYL","bundle":"https://pith.science/pith/BXRGR236PXZZ2YIWAKX5XLWJYL/bundle.json","state":"https://pith.science/pith/BXRGR236PXZZ2YIWAKX5XLWJYL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BXRGR236PXZZ2YIWAKX5XLWJYL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BXRGR236PXZZ2YIWAKX5XLWJYL","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":"14438c4fed2dc0a7104190727899ab1677211fd486649db48bfadc7433764a97","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-04T09:11:48Z","title_canon_sha256":"3bb91257e7db38171948eab54e8b76530d0de5c9f57eb74138eb0cefb20586f9"},"schema_version":"1.0","source":{"id":"2508.02219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02219","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02219v1","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02219","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"pith_short_12","alias_value":"BXRGR236PXZZ","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"pith_short_16","alias_value":"BXRGR236PXZZ2YIW","created_at":"2026-07-05T11:48:10Z"},{"alias_kind":"pith_short_8","alias_value":"BXRGR236","created_at":"2026-07-05T11:48:10Z"}],"graph_snapshots":[{"event_id":"sha256:d5fd4476321ad1a3aeb24fdd578eca7153fa770909f53fde08fac534317849fd","target":"graph","created_at":"2026-07-05T11:48:10Z","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/2508.02219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models demonstrate significant potential for developing generalized policies in real-world robotic control. This progress inspires researchers to explore fine-tuning these models with Reinforcement Learning (RL). However, fine-tuning VLA models with RL still faces challenges related to sample efficiency, compatibility with action chunking, and training stability. To address these challenges, we explore the fine-tuning of VLA models through offline reinforcement learning incorporating action chunking. In this work, we propose Chunked RL, a novel reinforcement learni","authors_text":"Chunhe Xia, Dongchi Huang, Lin Zhao, Tianle Zhang, Yihang Li, Zhirui Fang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-04T09:11:48Z","title":"CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02219","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:e42b11fa29a10d9e3ce06adc0bbd01dd79610bb1fa4e89818f9f18578e7fb5c2","target":"record","created_at":"2026-07-05T11:48:10Z","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":"14438c4fed2dc0a7104190727899ab1677211fd486649db48bfadc7433764a97","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-04T09:11:48Z","title_canon_sha256":"3bb91257e7db38171948eab54e8b76530d0de5c9f57eb74138eb0cefb20586f9"},"schema_version":"1.0","source":{"id":"2508.02219","kind":"arxiv","version":1}},"canonical_sha256":"0de268eb7e7df39d611602afdbaec9c2fc9e23cf5de943f98a5e90602cfdff6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0de268eb7e7df39d611602afdbaec9c2fc9e23cf5de943f98a5e90602cfdff6e","first_computed_at":"2026-07-05T11:48:10.467859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:10.467859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m7I5rxeiF2tlA1leKBrep9wMyr/1BKgx2FC3LZVvR/Pn0M98mXhwG1DbpJYZgy0ziw0QNjKHIje/eLV5G8N1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:10.468379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02219","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e42b11fa29a10d9e3ce06adc0bbd01dd79610bb1fa4e89818f9f18578e7fb5c2","sha256:d5fd4476321ad1a3aeb24fdd578eca7153fa770909f53fde08fac534317849fd"],"state_sha256":"fcd025babc2cf3b2301b76048b1278d9dbc69d5ec23f327cdf98a3754c989220"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UT9af+Fntq9oIx4PfSW87bwQnKbY5bofeJQ4ezUDaLWn9wRnV02BE+nEhMMwa0yq7uN9ZxIHipJCJ4yk8f1gAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:08:43.521077Z","bundle_sha256":"73d86897b8ca1135b7d7d476629840c3694bf646cfbc4c1cd0ee1e1ebe6ecb5b"}}