{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6F5E4K6KXK474VPMHFR2VJFEJY","short_pith_number":"pith:6F5E4K6K","schema_version":"1.0","canonical_sha256":"f17a4e2bcabab9fe55ec3963aaa4a44e17ff87fb02c9f1a2bf46cd8c21184dea","source":{"kind":"arxiv","id":"2412.01791","version":2},"attestation_state":"computed","paper":{"title":"DextrAH-RGB: Visuomotor Policies to Grasp Anything with Dexterous Hands","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ankur Handa, Arthur Allshire, Karl Van Wyk, Nathan Ratliff, Ritvik Singh","submitted_at":"2024-11-27T23:15:06Z","abstract_excerpt":"One of the most important, yet challenging, skills for a dexterous robot is grasping a diverse range of objects. Much of the prior work has been limited by speed, generality, or reliance on depth maps and object poses. In this paper, we introduce DextrAH-RGB, a system that can perform dexterous arm-hand grasping end-to-end from RGB image input. We train a privileged fabric-guided policy (FGP) in simulation through reinforcement learning that acts on a geometric fabric controller to dexterously grasp a wide variety of objects. We then distill this privileged FGP into a RGB-based FGP strictly in"},"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":"2412.01791","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T23:15:06Z","cross_cats_sorted":[],"title_canon_sha256":"e2b183510055ff41a052d909d8124ed290fbf2f7214c3d4adbbb0223513ac5fe","abstract_canon_sha256":"4d7b91c90fd3b428627d72b2d207e87da5c0d6c61efd1f2163c46a27d8bda926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:25.652775Z","signature_b64":"eCBcF+miQAD61Oo0idtxcyQnls2M0nTOg+ksDhj8b0TKzwWvgcQ0qovn1nuKgbv3kaknkp+dkdxC2pC6TqP7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f17a4e2bcabab9fe55ec3963aaa4a44e17ff87fb02c9f1a2bf46cd8c21184dea","last_reissued_at":"2026-07-05T10:08:25.652261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:25.652261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DextrAH-RGB: Visuomotor Policies to Grasp Anything with Dexterous Hands","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ankur Handa, Arthur Allshire, Karl Van Wyk, Nathan Ratliff, Ritvik Singh","submitted_at":"2024-11-27T23:15:06Z","abstract_excerpt":"One of the most important, yet challenging, skills for a dexterous robot is grasping a diverse range of objects. Much of the prior work has been limited by speed, generality, or reliance on depth maps and object poses. In this paper, we introduce DextrAH-RGB, a system that can perform dexterous arm-hand grasping end-to-end from RGB image input. We train a privileged fabric-guided policy (FGP) in simulation through reinforcement learning that acts on a geometric fabric controller to dexterously grasp a wide variety of objects. We then distill this privileged FGP into a RGB-based FGP strictly in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01791","kind":"arxiv","version":2},"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/2412.01791/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":"2412.01791","created_at":"2026-07-05T10:08:25.652329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01791v2","created_at":"2026-07-05T10:08:25.652329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01791","created_at":"2026-07-05T10:08:25.652329+00:00"},{"alias_kind":"pith_short_12","alias_value":"6F5E4K6KXK47","created_at":"2026-07-05T10:08:25.652329+00:00"},{"alias_kind":"pith_short_16","alias_value":"6F5E4K6KXK474VPM","created_at":"2026-07-05T10:08:25.652329+00:00"},{"alias_kind":"pith_short_8","alias_value":"6F5E4K6K","created_at":"2026-07-05T10:08:25.652329+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26428","citing_title":"Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22471","citing_title":"Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17054","citing_title":"Human Universal Grasping","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13677","citing_title":"Mana: Dexterous Manipulation of Articulated Tools","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11628","citing_title":"LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24975","citing_title":"Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22471","citing_title":"Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2505.07813","citing_title":"DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03599","citing_title":"Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04531","citing_title":"PTLD: Sim-to-real Privileged Tactile Latent Distillation for Dexterous Manipulation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15759","citing_title":"Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13925","citing_title":"Towards Robotic Dexterous Hand Intelligence: A Survey","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03363","citing_title":"Learning Reactive Dexterous Grasping via Hierarchical Task-Space RL Planning and Joint-Space QP Control","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11138","citing_title":"ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04831","citing_title":"Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05544","citing_title":"Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6F5E4K6KXK474VPMHFR2VJFEJY","json":"https://pith.science/pith/6F5E4K6KXK474VPMHFR2VJFEJY.json","graph_json":"https://pith.science/api/pith-number/6F5E4K6KXK474VPMHFR2VJFEJY/graph.json","events_json":"https://pith.science/api/pith-number/6F5E4K6KXK474VPMHFR2VJFEJY/events.json","paper":"https://pith.science/paper/6F5E4K6K"},"agent_actions":{"view_html":"https://pith.science/pith/6F5E4K6KXK474VPMHFR2VJFEJY","download_json":"https://pith.science/pith/6F5E4K6KXK474VPMHFR2VJFEJY.json","view_paper":"https://pith.science/paper/6F5E4K6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01791&json=true","fetch_graph":"https://pith.science/api/pith-number/6F5E4K6KXK474VPMHFR2VJFEJY/graph.json","fetch_events":"https://pith.science/api/pith-number/6F5E4K6KXK474VPMHFR2VJFEJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6F5E4K6KXK474VPMHFR2VJFEJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6F5E4K6KXK474VPMHFR2VJFEJY/action/storage_attestation","attest_author":"https://pith.science/pith/6F5E4K6KXK474VPMHFR2VJFEJY/action/author_attestation","sign_citation":"https://pith.science/pith/6F5E4K6KXK474VPMHFR2VJFEJY/action/citation_signature","submit_replication":"https://pith.science/pith/6F5E4K6KXK474VPMHFR2VJFEJY/action/replication_record"}},"created_at":"2026-07-05T10:08:25.652329+00:00","updated_at":"2026-07-05T10:08:25.652329+00:00"}