{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AVE6AXUSCKVSUYHN5KVHGE4W25","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":"c4d63197cce9a4fc538a0cdc14cd55d18611dbc88c24a9e9b1da35e2ae9fb6b1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T14:36:53Z","title_canon_sha256":"94ecfe9e0a0e5d917aff4f6dfa0d738ad703d01671d9c95dcbdf44f4a5155750"},"schema_version":"1.0","source":{"id":"2605.30011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30011","created_at":"2026-05-29T02:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30011v1","created_at":"2026-05-29T02:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30011","created_at":"2026-05-29T02:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"AVE6AXUSCKVS","created_at":"2026-05-29T02:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"AVE6AXUSCKVSUYHN","created_at":"2026-05-29T02:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"AVE6AXUS","created_at":"2026-05-29T02:06:06Z"}],"graph_snapshots":[{"event_id":"sha256:ab5a42130e71b2b912a56e3a9c22e4d5338e7b933df523f88284ce5f076392b1","target":"graph","created_at":"2026-05-29T02:06:06Z","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/2605.30011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irrelevant or weakly textual information can interfere with action prediction, while autoregressive text decoding adds too much latency for real-time closed-loop execution. We present VISUALTHINK-VLA, a visual intermediate-reasoning framework for accurate, low-latency VLA policies. Our bootstrapping philosophy is to guide action with effective visual thinking: VISUALTHINK-VLA bootstraps action prediction through a compa","authors_text":"Binhe Yu, Haoyu Zheng, Jiaqi Zhu, Mingjian Gao, Siliang Tang, Wenqiao Zhang, Yang Dai, Yueting Zhuang, Yuqian Yuan, Zheqi Lv, Zhiqi Ge, Zixuan Wan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T14:36:53Z","title":"VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30011","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":"sha256:090264a91f889afd0a749ef6df5b42929bf87c5e2b9dc6373ba481b8c5807e80","target":"record","created_at":"2026-05-29T02:06:06Z","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":"c4d63197cce9a4fc538a0cdc14cd55d18611dbc88c24a9e9b1da35e2ae9fb6b1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T14:36:53Z","title_canon_sha256":"94ecfe9e0a0e5d917aff4f6dfa0d738ad703d01671d9c95dcbdf44f4a5155750"},"schema_version":"1.0","source":{"id":"2605.30011","kind":"arxiv","version":1}},"canonical_sha256":"0549e05e9212ab2a60edeaaa731396d76619b63eac6cb36a6af528669a5938b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0549e05e9212ab2a60edeaaa731396d76619b63eac6cb36a6af528669a5938b9","first_computed_at":"2026-05-29T02:06:06.861194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:06.861194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xWkOyY1q+T2j9Qx8Q8WdBQFMQCxd8AXMudzjxu44aXB7lsq4NPbcrp7ikY6DmeH1vM0/E2XaeqoOe8LS4xcxDg==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:06.862131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:090264a91f889afd0a749ef6df5b42929bf87c5e2b9dc6373ba481b8c5807e80","sha256:ab5a42130e71b2b912a56e3a9c22e4d5338e7b933df523f88284ce5f076392b1"],"state_sha256":"f68fda87879e6509ce7a9c6e94c6a0045cc31d4be93b2e1e2c91adf8faffefcc"}