{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:75V4SDB2NZUURZ5ESUK7HE2BV4","short_pith_number":"pith:75V4SDB2","schema_version":"1.0","canonical_sha256":"ff6bc90c3a6e6948e7a49515f39341af15438e12fa16b4f056aabd077ae42148","source":{"kind":"arxiv","id":"2306.14896","version":1},"attestation_state":"computed","paper":{"title":"RVT: Robotic View Transformer for 3D Object Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Ankit Goyal, Dieter Fox, Jie Xu, Valts Blukis, Yijie Guo, Yu-Wei Chao","submitted_at":"2023-06-26T17:59:31Z","abstract_excerpt":"For 3D object manipulation, methods that build an explicit 3D representation perform better than those relying only on camera images. But using explicit 3D representations like voxels comes at large computing cost, adversely affecting scalability. In this work, we propose RVT, a multi-view transformer for 3D manipulation that is both scalable and accurate. Some key features of RVT are an attention mechanism to aggregate information across views and re-rendering of the camera input from virtual views around the robot workspace. In simulations, we find that a single RVT model works well across 1"},"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":"2306.14896","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-06-26T17:59:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2a60e60d363f5f7c855425530381cf7a2fd68ba7dcec3e9fac86e33227f0cea5","abstract_canon_sha256":"4705ca045106facd327e87f61810f3d91da290bb01cdf43bebde01c9a6f92b64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:41.896225Z","signature_b64":"MbwxpaFJXLI2iLebZtrDgdfRMpdSG1OsBxFB2jPTLT+gMiV9vAtZiiT+XtyXeOxGcRGvpWw9aJ0CYaoCqIy5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff6bc90c3a6e6948e7a49515f39341af15438e12fa16b4f056aabd077ae42148","last_reissued_at":"2026-07-05T06:24:41.895822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:41.895822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RVT: Robotic View Transformer for 3D Object Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Ankit Goyal, Dieter Fox, Jie Xu, Valts Blukis, Yijie Guo, Yu-Wei Chao","submitted_at":"2023-06-26T17:59:31Z","abstract_excerpt":"For 3D object manipulation, methods that build an explicit 3D representation perform better than those relying only on camera images. But using explicit 3D representations like voxels comes at large computing cost, adversely affecting scalability. In this work, we propose RVT, a multi-view transformer for 3D manipulation that is both scalable and accurate. Some key features of RVT are an attention mechanism to aggregate information across views and re-rendering of the camera input from virtual views around the robot workspace. In simulations, we find that a single RVT model works well across 1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14896","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/2306.14896/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":"2306.14896","created_at":"2026-07-05T06:24:41.895875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14896v1","created_at":"2026-07-05T06:24:41.895875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14896","created_at":"2026-07-05T06:24:41.895875+00:00"},{"alias_kind":"pith_short_12","alias_value":"75V4SDB2NZUU","created_at":"2026-07-05T06:24:41.895875+00:00"},{"alias_kind":"pith_short_16","alias_value":"75V4SDB2NZUURZ5E","created_at":"2026-07-05T06:24:41.895875+00:00"},{"alias_kind":"pith_short_8","alias_value":"75V4SDB2","created_at":"2026-07-05T06:24:41.895875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08751","citing_title":"DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03240","citing_title":"GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":259,"is_internal_anchor":false},{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05672","citing_title":"A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75V4SDB2NZUURZ5ESUK7HE2BV4","json":"https://pith.science/pith/75V4SDB2NZUURZ5ESUK7HE2BV4.json","graph_json":"https://pith.science/api/pith-number/75V4SDB2NZUURZ5ESUK7HE2BV4/graph.json","events_json":"https://pith.science/api/pith-number/75V4SDB2NZUURZ5ESUK7HE2BV4/events.json","paper":"https://pith.science/paper/75V4SDB2"},"agent_actions":{"view_html":"https://pith.science/pith/75V4SDB2NZUURZ5ESUK7HE2BV4","download_json":"https://pith.science/pith/75V4SDB2NZUURZ5ESUK7HE2BV4.json","view_paper":"https://pith.science/paper/75V4SDB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14896&json=true","fetch_graph":"https://pith.science/api/pith-number/75V4SDB2NZUURZ5ESUK7HE2BV4/graph.json","fetch_events":"https://pith.science/api/pith-number/75V4SDB2NZUURZ5ESUK7HE2BV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75V4SDB2NZUURZ5ESUK7HE2BV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75V4SDB2NZUURZ5ESUK7HE2BV4/action/storage_attestation","attest_author":"https://pith.science/pith/75V4SDB2NZUURZ5ESUK7HE2BV4/action/author_attestation","sign_citation":"https://pith.science/pith/75V4SDB2NZUURZ5ESUK7HE2BV4/action/citation_signature","submit_replication":"https://pith.science/pith/75V4SDB2NZUURZ5ESUK7HE2BV4/action/replication_record"}},"created_at":"2026-07-05T06:24:41.895875+00:00","updated_at":"2026-07-05T06:24:41.895875+00:00"}