{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZP7ZGCLHHFZNAWF6S5CXEDJVAA","short_pith_number":"pith:ZP7ZGCLH","schema_version":"1.0","canonical_sha256":"cbff9309673972d058be9745720d35002aab19b27d18d4e010379a13a9ffe757","source":{"kind":"arxiv","id":"2505.05517","version":3},"attestation_state":"computed","paper":{"title":"Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Arthur Jakobsson, Homanga Bharadhwaj, Hongyi Chen, Jeffrey Ichnowski, Jiashun Wang, Ruihan Zhao, Shubham Tulsiani, Yufei Ye, Yunchao Yao, Zackory Erickson, Zhixuan Xu","submitted_at":"2025-05-07T16:13:17Z","abstract_excerpt":"Functional grasping is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively. Prior work largely focuses on power grasps, which only involve holding an object, or relies on in-domain demonstrations for specific objects. We propose leveraging human grasp information extracted from web images, which capture natural and functional hand-object interactions (HOI). Using a pretrained 3D reconstruction model, we recover 3D human HOI meshes from RGB images. To train on these noisy HOI data, we propose to use: (1) an interaction-centric model to learn the functiona"},"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":"2505.05517","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T16:13:17Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"bde5f0d6133a2e5345875a0996efdd0295d4585604cf40ea923782960b6ff94e","abstract_canon_sha256":"47d93175b14cc4ed459e7159de66cc4435d44f819a57e4d65183371b58c19bbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:13:59.810685Z","signature_b64":"kwWky7WJTIYvMZbJ2+i+F4SPtzlhRBA7Mb4tXtdZSRiPWs2QBasaK9BS58yBXF9Z5sLkzIZKwNm/mJiHNQs2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbff9309673972d058be9745720d35002aab19b27d18d4e010379a13a9ffe757","last_reissued_at":"2026-06-29T00:13:59.810287Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:13:59.810287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Arthur Jakobsson, Homanga Bharadhwaj, Hongyi Chen, Jeffrey Ichnowski, Jiashun Wang, Ruihan Zhao, Shubham Tulsiani, Yufei Ye, Yunchao Yao, Zackory Erickson, Zhixuan Xu","submitted_at":"2025-05-07T16:13:17Z","abstract_excerpt":"Functional grasping is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively. Prior work largely focuses on power grasps, which only involve holding an object, or relies on in-domain demonstrations for specific objects. We propose leveraging human grasp information extracted from web images, which capture natural and functional hand-object interactions (HOI). Using a pretrained 3D reconstruction model, we recover 3D human HOI meshes from RGB images. To train on these noisy HOI data, we propose to use: (1) an interaction-centric model to learn the functiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05517","kind":"arxiv","version":3},"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/2505.05517/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":"2505.05517","created_at":"2026-06-29T00:13:59.810345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05517v3","created_at":"2026-06-29T00:13:59.810345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05517","created_at":"2026-06-29T00:13:59.810345+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZP7ZGCLHHFZN","created_at":"2026-06-29T00:13:59.810345+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZP7ZGCLHHFZNAWF6","created_at":"2026-06-29T00:13:59.810345+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZP7ZGCLH","created_at":"2026-06-29T00:13:59.810345+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/ZP7ZGCLHHFZNAWF6S5CXEDJVAA","json":"https://pith.science/pith/ZP7ZGCLHHFZNAWF6S5CXEDJVAA.json","graph_json":"https://pith.science/api/pith-number/ZP7ZGCLHHFZNAWF6S5CXEDJVAA/graph.json","events_json":"https://pith.science/api/pith-number/ZP7ZGCLHHFZNAWF6S5CXEDJVAA/events.json","paper":"https://pith.science/paper/ZP7ZGCLH"},"agent_actions":{"view_html":"https://pith.science/pith/ZP7ZGCLHHFZNAWF6S5CXEDJVAA","download_json":"https://pith.science/pith/ZP7ZGCLHHFZNAWF6S5CXEDJVAA.json","view_paper":"https://pith.science/paper/ZP7ZGCLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05517&json=true","fetch_graph":"https://pith.science/api/pith-number/ZP7ZGCLHHFZNAWF6S5CXEDJVAA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZP7ZGCLHHFZNAWF6S5CXEDJVAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZP7ZGCLHHFZNAWF6S5CXEDJVAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZP7ZGCLHHFZNAWF6S5CXEDJVAA/action/storage_attestation","attest_author":"https://pith.science/pith/ZP7ZGCLHHFZNAWF6S5CXEDJVAA/action/author_attestation","sign_citation":"https://pith.science/pith/ZP7ZGCLHHFZNAWF6S5CXEDJVAA/action/citation_signature","submit_replication":"https://pith.science/pith/ZP7ZGCLHHFZNAWF6S5CXEDJVAA/action/replication_record"}},"created_at":"2026-06-29T00:13:59.810345+00:00","updated_at":"2026-06-29T00:13:59.810345+00:00"}