{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IJHQ73SXNYEGLTHGKOS43MFTRV","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":"d161ff94f3519917b68428f99559566745b79ac5b6941701d3a115f6e0e801ae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T16:23:18Z","title_canon_sha256":"76e962332cd73e2b8b65b9fbddad08c9eafdc9f7e484c54ceb29e0bf5c595bf6"},"schema_version":"1.0","source":{"id":"2606.26006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26006","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26006v1","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26006","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"IJHQ73SXNYEG","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"IJHQ73SXNYEGLTHG","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"IJHQ73SX","created_at":"2026-06-25T01:18:45Z"}],"graph_snapshots":[{"event_id":"sha256:6401e46986171903174177403aea190c89b765f4f5e4337937ea503eeee6b442","target":"graph","created_at":"2026-06-25T01:18:45Z","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/2606.26006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models are often constrained by the imitation ceiling imposed by sub-optimal data. While Reinforcement Learning (RL) fine-tuning can surpass this limit, it is notoriously sample inefficient. This challenge arises from two core issues: (1) catastrophic initial unlearning due to an unstable Q-function and (2) inefficient policy updates caused by low-quality exploration data, often forcing a reliance on costly human interventions. We introduce FORCE, a 3-stage framework that stabilizes fine-tuning by tackling both issues. FORCE first incorporates a Value-Calibrated Wa","authors_text":"Chuyao Fu, Haoran Li, Hongyang Cheng, Pengwei Wang, Shanghang Zhang, Shuyi Zhang, Xiaojie Zhang, Yaoxu Lyu, Yichen Guo, Yunfan Lou, Zhongyuan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T16:23:18Z","title":"FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26006","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:f9399d4bc907f6082c623ca75dda4c577393d13d87c840337d0c41b0b9ab441a","target":"record","created_at":"2026-06-25T01:18:45Z","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":"d161ff94f3519917b68428f99559566745b79ac5b6941701d3a115f6e0e801ae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T16:23:18Z","title_canon_sha256":"76e962332cd73e2b8b65b9fbddad08c9eafdc9f7e484c54ceb29e0bf5c595bf6"},"schema_version":"1.0","source":{"id":"2606.26006","kind":"arxiv","version":1}},"canonical_sha256":"424f0fee576e0865cce653a5cdb0b38d534009ea56e0f84d12499b6014ca2e81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"424f0fee576e0865cce653a5cdb0b38d534009ea56e0f84d12499b6014ca2e81","first_computed_at":"2026-06-25T01:18:45.634650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:45.634650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s8bP+JYvX6xzrp7XeQbAOmK1Ru+/+hyPUmqAUh81UBFYPFpTM5uJSogLTOwqkXtaXup27kzJI65bO911daMbAw==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:45.635028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9399d4bc907f6082c623ca75dda4c577393d13d87c840337d0c41b0b9ab441a","sha256:6401e46986171903174177403aea190c89b765f4f5e4337937ea503eeee6b442"],"state_sha256":"3c4bf8b09919d234aadd6d4ecb461c062e0fa4fcf2ea14af3138983b46de09e3"}