{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QZ75OLBBFRU7N5BVH2HRE3VH47","short_pith_number":"pith:QZ75OLBB","schema_version":"1.0","canonical_sha256":"867fd72c212c69f6f4353e8f126ea7e7f7da3b3c9d3b4dd05aa7104d276d862d","source":{"kind":"arxiv","id":"2608.05738","version":1},"attestation_state":"computed","paper":{"title":"In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hang Guo, Jiale Zhang, Jiarui Yang, Maowei Hu, Wen Huang","submitted_at":"2026-08-06T08:21:02Z","abstract_excerpt":"Vision-Language-Action (VLA) models have become the dominant recipe for generalist manipulation, yet they are almost universally trained by behavior cloning: a policy imitates expert action chunks conditioned on a static image and a fixed instruction. A natural remedy is to inject explicit reasoning through textual chain-of-thought (CoT). We show, both empirically and analytically, that free-form textual CoT degrades low-level control: the reasoning it produces is ungrounded, its latency breaks closed-loop timing, and, crucially, the reasoning and action tokens are optimized against conflictin"},"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":"2608.05738","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-06T08:21:02Z","cross_cats_sorted":[],"title_canon_sha256":"37e1a68135efc829086193195bbcf36fa5c45ea285994a04e2b10d7d49d3ebe7","abstract_canon_sha256":"e2515dd8d3d40e8a3c02d63d0dc3a5790922906b5abdb91056ebf9624980a5b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:27.009362Z","signature_b64":"qinbPaO50iOdJ3ui5v4Hl4BfDHrz332lQVSfTV6VlOy/Kv/pwaINP261eafVusJWyyd1Zv9zlxJmJ+JJE6yyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"867fd72c212c69f6f4353e8f126ea7e7f7da3b3c9d3b4dd05aa7104d276d862d","last_reissued_at":"2026-08-07T00:52:27.007880Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:27.007880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hang Guo, Jiale Zhang, Jiarui Yang, Maowei Hu, Wen Huang","submitted_at":"2026-08-06T08:21:02Z","abstract_excerpt":"Vision-Language-Action (VLA) models have become the dominant recipe for generalist manipulation, yet they are almost universally trained by behavior cloning: a policy imitates expert action chunks conditioned on a static image and a fixed instruction. A natural remedy is to inject explicit reasoning through textual chain-of-thought (CoT). We show, both empirically and analytically, that free-form textual CoT degrades low-level control: the reasoning it produces is ungrounded, its latency breaks closed-loop timing, and, crucially, the reasoning and action tokens are optimized against conflictin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05738","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/2608.05738/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":"2608.05738","created_at":"2026-08-07T00:52:27.009360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05738v1","created_at":"2026-08-07T00:52:27.009360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05738","created_at":"2026-08-07T00:52:27.009360+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZ75OLBBFRU7","created_at":"2026-08-07T00:52:27.009360+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZ75OLBBFRU7N5BV","created_at":"2026-08-07T00:52:27.009360+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZ75OLBB","created_at":"2026-08-07T00:52:27.009360+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/QZ75OLBBFRU7N5BVH2HRE3VH47","json":"https://pith.science/pith/QZ75OLBBFRU7N5BVH2HRE3VH47.json","graph_json":"https://pith.science/api/pith-number/QZ75OLBBFRU7N5BVH2HRE3VH47/graph.json","events_json":"https://pith.science/api/pith-number/QZ75OLBBFRU7N5BVH2HRE3VH47/events.json","paper":"https://pith.science/paper/QZ75OLBB"},"agent_actions":{"view_html":"https://pith.science/pith/QZ75OLBBFRU7N5BVH2HRE3VH47","download_json":"https://pith.science/pith/QZ75OLBBFRU7N5BVH2HRE3VH47.json","view_paper":"https://pith.science/paper/QZ75OLBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05738&json=true","fetch_graph":"https://pith.science/api/pith-number/QZ75OLBBFRU7N5BVH2HRE3VH47/graph.json","fetch_events":"https://pith.science/api/pith-number/QZ75OLBBFRU7N5BVH2HRE3VH47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZ75OLBBFRU7N5BVH2HRE3VH47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZ75OLBBFRU7N5BVH2HRE3VH47/action/storage_attestation","attest_author":"https://pith.science/pith/QZ75OLBBFRU7N5BVH2HRE3VH47/action/author_attestation","sign_citation":"https://pith.science/pith/QZ75OLBBFRU7N5BVH2HRE3VH47/action/citation_signature","submit_replication":"https://pith.science/pith/QZ75OLBBFRU7N5BVH2HRE3VH47/action/replication_record"}},"created_at":"2026-08-07T00:52:27.009360+00:00","updated_at":"2026-08-07T00:52:27.009360+00:00"}