{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZAHYZQ7VYOBK3U5PZLO4FNLCPC","short_pith_number":"pith:ZAHYZQ7V","schema_version":"1.0","canonical_sha256":"c80f8cc3f5c382add3afcaddc2b56278a1b2bba2b2b673ba934c51c3504804b2","source":{"kind":"arxiv","id":"2607.04610","version":1},"attestation_state":"computed","paper":{"title":"RoboVista: Evaluating Vision Language Models for Diverse Robot Applications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dhruv Shah, Kaiyuan Chen, Ken Goldberg, Pannag R. Sanketi, Shuangyu Xie, Simeon Adebola, Tianshuang Qiu, Wentao Yuan, Yixuan Huang, Zehan Ma, Ziyang Chen","submitted_at":"2026-07-06T02:34:56Z","abstract_excerpt":"Diverse applications for robotics, such as industry and agriculture, require robots to operate across various embodiments, changing visual conditions, and complex planning. Vision-Language Models (VLMs) offer a promising foundation for general-purpose and interpretable robotic reasoning. Aligning VLMs with diverse robot applications requires a modular understanding of the individual decision components that underlie robotic behavior. Capturing such structure is challenging for conventional robot benchmarks that are primarily based on teleoperated, end-to-end datasets. We propose Robot Question"},"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":"2607.04610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-06T02:34:56Z","cross_cats_sorted":[],"title_canon_sha256":"c5a2917583c02cf969d70a146e2974e8fe7905e29b6caa3cd5354a29da7df356","abstract_canon_sha256":"f68bb70d02efb97923729a1f4c655b2f34111dfd91d047b00e242d913d6a8ef1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:27.430522Z","signature_b64":"uTadwePUvtexDd/tv7ufKxf3fPGRMj4RTjefsEwPy2BKrelHHR2ZraZy+/xImhqKUCw2N42RynvWWpJdDT0CDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c80f8cc3f5c382add3afcaddc2b56278a1b2bba2b2b673ba934c51c3504804b2","last_reissued_at":"2026-07-07T02:19:27.429851Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:27.429851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboVista: Evaluating Vision Language Models for Diverse Robot Applications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dhruv Shah, Kaiyuan Chen, Ken Goldberg, Pannag R. Sanketi, Shuangyu Xie, Simeon Adebola, Tianshuang Qiu, Wentao Yuan, Yixuan Huang, Zehan Ma, Ziyang Chen","submitted_at":"2026-07-06T02:34:56Z","abstract_excerpt":"Diverse applications for robotics, such as industry and agriculture, require robots to operate across various embodiments, changing visual conditions, and complex planning. Vision-Language Models (VLMs) offer a promising foundation for general-purpose and interpretable robotic reasoning. Aligning VLMs with diverse robot applications requires a modular understanding of the individual decision components that underlie robotic behavior. Capturing such structure is challenging for conventional robot benchmarks that are primarily based on teleoperated, end-to-end datasets. We propose Robot Question"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04610","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/2607.04610/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":"2607.04610","created_at":"2026-07-07T02:19:27.429944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04610v1","created_at":"2026-07-07T02:19:27.429944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04610","created_at":"2026-07-07T02:19:27.429944+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAHYZQ7VYOBK","created_at":"2026-07-07T02:19:27.429944+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAHYZQ7VYOBK3U5P","created_at":"2026-07-07T02:19:27.429944+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAHYZQ7V","created_at":"2026-07-07T02:19:27.429944+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/ZAHYZQ7VYOBK3U5PZLO4FNLCPC","json":"https://pith.science/pith/ZAHYZQ7VYOBK3U5PZLO4FNLCPC.json","graph_json":"https://pith.science/api/pith-number/ZAHYZQ7VYOBK3U5PZLO4FNLCPC/graph.json","events_json":"https://pith.science/api/pith-number/ZAHYZQ7VYOBK3U5PZLO4FNLCPC/events.json","paper":"https://pith.science/paper/ZAHYZQ7V"},"agent_actions":{"view_html":"https://pith.science/pith/ZAHYZQ7VYOBK3U5PZLO4FNLCPC","download_json":"https://pith.science/pith/ZAHYZQ7VYOBK3U5PZLO4FNLCPC.json","view_paper":"https://pith.science/paper/ZAHYZQ7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04610&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAHYZQ7VYOBK3U5PZLO4FNLCPC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAHYZQ7VYOBK3U5PZLO4FNLCPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAHYZQ7VYOBK3U5PZLO4FNLCPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAHYZQ7VYOBK3U5PZLO4FNLCPC/action/storage_attestation","attest_author":"https://pith.science/pith/ZAHYZQ7VYOBK3U5PZLO4FNLCPC/action/author_attestation","sign_citation":"https://pith.science/pith/ZAHYZQ7VYOBK3U5PZLO4FNLCPC/action/citation_signature","submit_replication":"https://pith.science/pith/ZAHYZQ7VYOBK3U5PZLO4FNLCPC/action/replication_record"}},"created_at":"2026-07-07T02:19:27.429944+00:00","updated_at":"2026-07-07T02:19:27.429944+00:00"}