{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OLWTOZM52DODPU4JT7CUCTODJX","short_pith_number":"pith:OLWTOZM5","schema_version":"1.0","canonical_sha256":"72ed37659dd0dc37d3899fc5414dc34dd2071280258b23240220d4bc74478db5","source":{"kind":"arxiv","id":"2403.11461","version":2},"attestation_state":"computed","paper":{"title":"VIHE: Virtual In-Hand Eye Transformer for 3D Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gregory D. Hager, Liangjun Zhang, Shiyu Jin, Weiyao Wang, Yutian Lei","submitted_at":"2024-03-18T04:26:52Z","abstract_excerpt":"In this work, we introduce the Virtual In-Hand Eye Transformer (VIHE), a novel method designed to enhance 3D manipulation capabilities through action-aware view rendering. VIHE autoregressively refines actions in multiple stages by conditioning on rendered views posed from action predictions in the earlier stages. These virtual in-hand views provide a strong inductive bias for effectively recognizing the correct pose for the hand, especially for challenging high-precision tasks such as peg insertion. On 18 manipulation tasks in RLBench simulated environments, VIHE achieves a new state-of-the-a"},"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":"2403.11461","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-18T04:26:52Z","cross_cats_sorted":[],"title_canon_sha256":"beb7de6fcefc9b8566ddfb4858eecd0052917d3087758a85ae542cf4590b538c","abstract_canon_sha256":"9ac5d89358601f28163936bd147ca6c8d175299b1f5282a20ac8f9cc8b9c4944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:52.516687Z","signature_b64":"SDGgrbQiHeuoYTJAbubHVgZ3TeQIPWoHv7WdU0zFwGov57CRFeyuxX8/VyRiUrE8n4dw333xtMPaHhm0hPoWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72ed37659dd0dc37d3899fc5414dc34dd2071280258b23240220d4bc74478db5","last_reissued_at":"2026-07-05T07:57:52.516137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:52.516137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIHE: Virtual In-Hand Eye Transformer for 3D Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gregory D. Hager, Liangjun Zhang, Shiyu Jin, Weiyao Wang, Yutian Lei","submitted_at":"2024-03-18T04:26:52Z","abstract_excerpt":"In this work, we introduce the Virtual In-Hand Eye Transformer (VIHE), a novel method designed to enhance 3D manipulation capabilities through action-aware view rendering. VIHE autoregressively refines actions in multiple stages by conditioning on rendered views posed from action predictions in the earlier stages. These virtual in-hand views provide a strong inductive bias for effectively recognizing the correct pose for the hand, especially for challenging high-precision tasks such as peg insertion. On 18 manipulation tasks in RLBench simulated environments, VIHE achieves a new state-of-the-a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11461","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/2403.11461/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":"2403.11461","created_at":"2026-07-05T07:57:52.516210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11461v2","created_at":"2026-07-05T07:57:52.516210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11461","created_at":"2026-07-05T07:57:52.516210+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLWTOZM52DOD","created_at":"2026-07-05T07:57:52.516210+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLWTOZM52DODPU4J","created_at":"2026-07-05T07:57:52.516210+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLWTOZM5","created_at":"2026-07-05T07:57:52.516210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06564","citing_title":"Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLWTOZM52DODPU4JT7CUCTODJX","json":"https://pith.science/pith/OLWTOZM52DODPU4JT7CUCTODJX.json","graph_json":"https://pith.science/api/pith-number/OLWTOZM52DODPU4JT7CUCTODJX/graph.json","events_json":"https://pith.science/api/pith-number/OLWTOZM52DODPU4JT7CUCTODJX/events.json","paper":"https://pith.science/paper/OLWTOZM5"},"agent_actions":{"view_html":"https://pith.science/pith/OLWTOZM52DODPU4JT7CUCTODJX","download_json":"https://pith.science/pith/OLWTOZM52DODPU4JT7CUCTODJX.json","view_paper":"https://pith.science/paper/OLWTOZM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11461&json=true","fetch_graph":"https://pith.science/api/pith-number/OLWTOZM52DODPU4JT7CUCTODJX/graph.json","fetch_events":"https://pith.science/api/pith-number/OLWTOZM52DODPU4JT7CUCTODJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLWTOZM52DODPU4JT7CUCTODJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLWTOZM52DODPU4JT7CUCTODJX/action/storage_attestation","attest_author":"https://pith.science/pith/OLWTOZM52DODPU4JT7CUCTODJX/action/author_attestation","sign_citation":"https://pith.science/pith/OLWTOZM52DODPU4JT7CUCTODJX/action/citation_signature","submit_replication":"https://pith.science/pith/OLWTOZM52DODPU4JT7CUCTODJX/action/replication_record"}},"created_at":"2026-07-05T07:57:52.516210+00:00","updated_at":"2026-07-05T07:57:52.516210+00:00"}