{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LNAQVCJATA2UD4LFAVDTNO7DH3","short_pith_number":"pith:LNAQVCJA","schema_version":"1.0","canonical_sha256":"5b410a8920983541f165054736bbe33eeba48359954434ed24947469a5dd4b0d","source":{"kind":"arxiv","id":"2507.02747","version":1},"attestation_state":"computed","paper":{"title":"DexVLG: Dexterous Vision-Language-Grasp Model at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Danshi Li, He Wang, Jiawei He, Jiayi Chen, Li Yi, Wenyao Zhang, Xinqiang Yu, Zekun Qi, Zhaoxiang Zhang, Zhizheng Zhang","submitted_at":"2025-07-03T16:05:25Z","abstract_excerpt":"As large models gain traction, vision-language-action (VLA) systems are enabling robots to tackle increasingly complex tasks. However, limited by the difficulty of data collection, progress has mainly focused on controlling simple gripper end-effectors. There is little research on functional grasping with large models for human-like dexterous hands. In this paper, we introduce DexVLG, a large Vision-Language-Grasp model for Dexterous grasp pose prediction aligned with language instructions using single-view RGBD input. To accomplish this, we generate a dataset of 170 million dexterous grasp po"},"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":"2507.02747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T16:05:25Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a38e333ce775d917b48b5009be60fc92baff4392d9baa58d78ff6a00961b0b36","abstract_canon_sha256":"ca9feb6763a02ea751ab9bdb333cc2c1464924ac371196608bd90126a09c9c8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:34.091672Z","signature_b64":"vCW8BisfnpyCEumU9Mrhe2WXlzRxyfw6VAMYs/LDNe5jZPIeJl2Motb+KNcqWNc2vwFvtMONsH2VUD6BTOeaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b410a8920983541f165054736bbe33eeba48359954434ed24947469a5dd4b0d","last_reissued_at":"2026-07-05T11:31:34.091152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:34.091152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DexVLG: Dexterous Vision-Language-Grasp Model at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Danshi Li, He Wang, Jiawei He, Jiayi Chen, Li Yi, Wenyao Zhang, Xinqiang Yu, Zekun Qi, Zhaoxiang Zhang, Zhizheng Zhang","submitted_at":"2025-07-03T16:05:25Z","abstract_excerpt":"As large models gain traction, vision-language-action (VLA) systems are enabling robots to tackle increasingly complex tasks. However, limited by the difficulty of data collection, progress has mainly focused on controlling simple gripper end-effectors. There is little research on functional grasping with large models for human-like dexterous hands. In this paper, we introduce DexVLG, a large Vision-Language-Grasp model for Dexterous grasp pose prediction aligned with language instructions using single-view RGBD input. To accomplish this, we generate a dataset of 170 million dexterous grasp po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02747","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/2507.02747/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":"2507.02747","created_at":"2026-07-05T11:31:34.091219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02747v1","created_at":"2026-07-05T11:31:34.091219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02747","created_at":"2026-07-05T11:31:34.091219+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNAQVCJATA2U","created_at":"2026-07-05T11:31:34.091219+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNAQVCJATA2UD4LF","created_at":"2026-07-05T11:31:34.091219+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNAQVCJA","created_at":"2026-07-05T11:31:34.091219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06438","citing_title":"WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2509.18455","citing_title":"Learning Geometry-Aware Nonprehensile Pushing and Pulling with Dexterous Hands","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10698","citing_title":"AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08410","citing_title":"BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06589","citing_title":"BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNAQVCJATA2UD4LFAVDTNO7DH3","json":"https://pith.science/pith/LNAQVCJATA2UD4LFAVDTNO7DH3.json","graph_json":"https://pith.science/api/pith-number/LNAQVCJATA2UD4LFAVDTNO7DH3/graph.json","events_json":"https://pith.science/api/pith-number/LNAQVCJATA2UD4LFAVDTNO7DH3/events.json","paper":"https://pith.science/paper/LNAQVCJA"},"agent_actions":{"view_html":"https://pith.science/pith/LNAQVCJATA2UD4LFAVDTNO7DH3","download_json":"https://pith.science/pith/LNAQVCJATA2UD4LFAVDTNO7DH3.json","view_paper":"https://pith.science/paper/LNAQVCJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02747&json=true","fetch_graph":"https://pith.science/api/pith-number/LNAQVCJATA2UD4LFAVDTNO7DH3/graph.json","fetch_events":"https://pith.science/api/pith-number/LNAQVCJATA2UD4LFAVDTNO7DH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNAQVCJATA2UD4LFAVDTNO7DH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNAQVCJATA2UD4LFAVDTNO7DH3/action/storage_attestation","attest_author":"https://pith.science/pith/LNAQVCJATA2UD4LFAVDTNO7DH3/action/author_attestation","sign_citation":"https://pith.science/pith/LNAQVCJATA2UD4LFAVDTNO7DH3/action/citation_signature","submit_replication":"https://pith.science/pith/LNAQVCJATA2UD4LFAVDTNO7DH3/action/replication_record"}},"created_at":"2026-07-05T11:31:34.091219+00:00","updated_at":"2026-07-05T11:31:34.091219+00:00"}