{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KHJIRD3MCPF6D7PBO2S6L2WY4O","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":"90d2b34f74ea5545143f131c09b226a57a8ad05cecf83b4826270bfc15d880ff","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-28T02:53:48Z","title_canon_sha256":"761227929c6a2ac5eaf3bd541aa7d2a7c5f328b6a45d7c778d55234625bdf5e4"},"schema_version":"1.0","source":{"id":"2501.16664","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16664","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16664v1","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16664","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"KHJIRD3MCPF6","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"KHJIRD3MCPF6D7PB","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"KHJIRD3M","created_at":"2026-07-05T10:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:e9d7976591e2f772a53b57d912d0a13890d3d04bac498a687ee30d763d991456","target":"graph","created_at":"2026-07-05T10:06:16Z","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/2501.16664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models. Although the VLA models are powerful, how to improve these large models during interaction with environments remains an open question. In this paper, we explore how to further improve these VLA models via Reinforcement Learning (RL), a commonly used fine-tuning technique for large models. However, we find that directly applying online RL to large VLA models pres","authors_text":"Jianke Zhang, Jianyu Chen, Xiang Ji, Xiaoyu Chen, Yanjiang Guo, Yen-Jen Wang, Yucheng Hu","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-28T02:53:48Z","title":"Improving Vision-Language-Action Model with Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16664","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":"sha256:374ba39cd64d34d3a1e7a694feb5680efd607476a9d97dda04f448a1096534d5","target":"record","created_at":"2026-07-05T10:06:16Z","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":"90d2b34f74ea5545143f131c09b226a57a8ad05cecf83b4826270bfc15d880ff","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-28T02:53:48Z","title_canon_sha256":"761227929c6a2ac5eaf3bd541aa7d2a7c5f328b6a45d7c778d55234625bdf5e4"},"schema_version":"1.0","source":{"id":"2501.16664","kind":"arxiv","version":1}},"canonical_sha256":"51d2888f6c13cbe1fde176a5e5ead8e3a5c2880d88c4cb8bb83387bc768b7acb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51d2888f6c13cbe1fde176a5e5ead8e3a5c2880d88c4cb8bb83387bc768b7acb","first_computed_at":"2026-07-05T10:06:16.619602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:16.619602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T7Bgl8G8Dmu6gSfA/BRMV7ZK6tho1PTlICV3YgUUtaZvhVT2f9GWhewP8g/AoC9Cfv09BEiI29SCOOkuUrkiAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:16.620055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16664","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:374ba39cd64d34d3a1e7a694feb5680efd607476a9d97dda04f448a1096534d5","sha256:e9d7976591e2f772a53b57d912d0a13890d3d04bac498a687ee30d763d991456"],"state_sha256":"7e6103d28243692b1c97c79ea9f9629211684444d52673ca36f74cc4468f807c"}