{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AVE6AXUSCKVSUYHN5KVHGE4W25","short_pith_number":"pith:AVE6AXUS","schema_version":"1.0","canonical_sha256":"0549e05e9212ab2a60edeaaa731396d76619b63eac6cb36a6af528669a5938b9","source":{"kind":"arxiv","id":"2605.30011","version":1},"attestation_state":"computed","paper":{"title":"VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2026-05-28T14:36:53Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.30011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T14:36:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94ecfe9e0a0e5d917aff4f6dfa0d738ad703d01671d9c95dcbdf44f4a5155750","abstract_canon_sha256":"c4d63197cce9a4fc538a0cdc14cd55d18611dbc88c24a9e9b1da35e2ae9fb6b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:06.862131Z","signature_b64":"xWkOyY1q+T2j9Qx8Q8WdBQFMQCxd8AXMudzjxu44aXB7lsq4NPbcrp7ikY6DmeH1vM0/E2XaeqoOe8LS4xcxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0549e05e9212ab2a60edeaaa731396d76619b63eac6cb36a6af528669a5938b9","last_reissued_at":"2026-05-29T02:06:06.861194Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:06.861194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2026-05-28T14:36:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30011","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/2605.30011/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.30011","created_at":"2026-05-29T02:06:06.861364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30011v1","created_at":"2026-05-29T02:06:06.861364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30011","created_at":"2026-05-29T02:06:06.861364+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVE6AXUSCKVS","created_at":"2026-05-29T02:06:06.861364+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVE6AXUSCKVSUYHN","created_at":"2026-05-29T02:06:06.861364+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVE6AXUS","created_at":"2026-05-29T02:06:06.861364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AVE6AXUSCKVSUYHN5KVHGE4W25","json":"https://pith.science/pith/AVE6AXUSCKVSUYHN5KVHGE4W25.json","graph_json":"https://pith.science/api/pith-number/AVE6AXUSCKVSUYHN5KVHGE4W25/graph.json","events_json":"https://pith.science/api/pith-number/AVE6AXUSCKVSUYHN5KVHGE4W25/events.json","paper":"https://pith.science/paper/AVE6AXUS"},"agent_actions":{"view_html":"https://pith.science/pith/AVE6AXUSCKVSUYHN5KVHGE4W25","download_json":"https://pith.science/pith/AVE6AXUSCKVSUYHN5KVHGE4W25.json","view_paper":"https://pith.science/paper/AVE6AXUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30011&json=true","fetch_graph":"https://pith.science/api/pith-number/AVE6AXUSCKVSUYHN5KVHGE4W25/graph.json","fetch_events":"https://pith.science/api/pith-number/AVE6AXUSCKVSUYHN5KVHGE4W25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVE6AXUSCKVSUYHN5KVHGE4W25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVE6AXUSCKVSUYHN5KVHGE4W25/action/storage_attestation","attest_author":"https://pith.science/pith/AVE6AXUSCKVSUYHN5KVHGE4W25/action/author_attestation","sign_citation":"https://pith.science/pith/AVE6AXUSCKVSUYHN5KVHGE4W25/action/citation_signature","submit_replication":"https://pith.science/pith/AVE6AXUSCKVSUYHN5KVHGE4W25/action/replication_record"}},"created_at":"2026-05-29T02:06:06.861364+00:00","updated_at":"2026-05-29T02:06:06.861364+00:00"}