{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6V423DPMMSJ3WFZR53KGSKLCUI","short_pith_number":"pith:6V423DPM","schema_version":"1.0","canonical_sha256":"f579ad8dec6493bb1731eed4692962a20caeede96786552f40e96236ee4d2552","source":{"kind":"arxiv","id":"2202.00164","version":1},"attestation_state":"computed","paper":{"title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Kristen Grauman, Priyanka Mandikal","submitted_at":"2022-02-01T00:45:57Z","abstract_excerpt":"Dexterous multi-fingered robotic hands have a formidable action space, yet their morphological similarity to the human hand holds immense potential to accelerate robot learning. We propose DexVIP, an approach to learn dexterous robotic grasping from human-object interactions present in in-the-wild YouTube videos. We do this by curating grasp images from human-object interaction videos and imposing a prior over the agent's hand pose when learning to grasp with deep reinforcement learning. A key advantage of our method is that the learned policy is able to leverage free-form in-the-wild visual d"},"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":"2202.00164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-02-01T00:45:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"94362baf185de238cab06a84f619e35c9caf26ffd8617ca74a51d72fae471113","abstract_canon_sha256":"00ad71b36295a3dc9e4e682a62c20f3ce4e7ec0fc40e398e634e55b4455825ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:19.222819Z","signature_b64":"ghdJ8LJ/K6xbfruxazp0aXiPrOtOK1K+Rh5cBjPeExEPQZGMkQ/swbGjT1KSST1U4Fu7tIzmqMdaXdH/kEyjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f579ad8dec6493bb1731eed4692962a20caeede96786552f40e96236ee4d2552","last_reissued_at":"2026-07-05T03:53:19.222348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:19.222348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Kristen Grauman, Priyanka Mandikal","submitted_at":"2022-02-01T00:45:57Z","abstract_excerpt":"Dexterous multi-fingered robotic hands have a formidable action space, yet their morphological similarity to the human hand holds immense potential to accelerate robot learning. We propose DexVIP, an approach to learn dexterous robotic grasping from human-object interactions present in in-the-wild YouTube videos. We do this by curating grasp images from human-object interaction videos and imposing a prior over the agent's hand pose when learning to grasp with deep reinforcement learning. A key advantage of our method is that the learned policy is able to leverage free-form in-the-wild visual d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00164","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/2202.00164/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":"2202.00164","created_at":"2026-07-05T03:53:19.222410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00164v1","created_at":"2026-07-05T03:53:19.222410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00164","created_at":"2026-07-05T03:53:19.222410+00:00"},{"alias_kind":"pith_short_12","alias_value":"6V423DPMMSJ3","created_at":"2026-07-05T03:53:19.222410+00:00"},{"alias_kind":"pith_short_16","alias_value":"6V423DPMMSJ3WFZR","created_at":"2026-07-05T03:53:19.222410+00:00"},{"alias_kind":"pith_short_8","alias_value":"6V423DPM","created_at":"2026-07-05T03:53:19.222410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31200","citing_title":"Agentic RAG-VLM: Affordance-Aware Retrieval-Augmented Generation with Self-Reflective Planning for Robotic Grasping","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6V423DPMMSJ3WFZR53KGSKLCUI","json":"https://pith.science/pith/6V423DPMMSJ3WFZR53KGSKLCUI.json","graph_json":"https://pith.science/api/pith-number/6V423DPMMSJ3WFZR53KGSKLCUI/graph.json","events_json":"https://pith.science/api/pith-number/6V423DPMMSJ3WFZR53KGSKLCUI/events.json","paper":"https://pith.science/paper/6V423DPM"},"agent_actions":{"view_html":"https://pith.science/pith/6V423DPMMSJ3WFZR53KGSKLCUI","download_json":"https://pith.science/pith/6V423DPMMSJ3WFZR53KGSKLCUI.json","view_paper":"https://pith.science/paper/6V423DPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00164&json=true","fetch_graph":"https://pith.science/api/pith-number/6V423DPMMSJ3WFZR53KGSKLCUI/graph.json","fetch_events":"https://pith.science/api/pith-number/6V423DPMMSJ3WFZR53KGSKLCUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6V423DPMMSJ3WFZR53KGSKLCUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6V423DPMMSJ3WFZR53KGSKLCUI/action/storage_attestation","attest_author":"https://pith.science/pith/6V423DPMMSJ3WFZR53KGSKLCUI/action/author_attestation","sign_citation":"https://pith.science/pith/6V423DPMMSJ3WFZR53KGSKLCUI/action/citation_signature","submit_replication":"https://pith.science/pith/6V423DPMMSJ3WFZR53KGSKLCUI/action/replication_record"}},"created_at":"2026-07-05T03:53:19.222410+00:00","updated_at":"2026-07-05T03:53:19.222410+00:00"}