{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IZH7CDBEWLSXSVG3PMCHQHSYYP","short_pith_number":"pith:IZH7CDBE","schema_version":"1.0","canonical_sha256":"464ff10c24b2e57954db7b04781e58c3db08b6d93040bc8639954023bfe37dc9","source":{"kind":"arxiv","id":"2411.18623","version":2},"attestation_state":"computed","paper":{"title":"Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Gu, Jiaming Liu, Lily Lee, Longzan Luo, Pengwei Wang, Renrui Zhang, Shanghang Zhang, Sixiang Chen, Yueru Jia, Zhilue Wang, Zhongyuan Wang","submitted_at":"2024-11-27T18:59:52Z","abstract_excerpt":"3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has increasingly focused on the explicit extraction of 3D features, while still facing challenges such as the lack of large-scale robotic 3D data and the potential loss of spatial geometry. To address these limitations, we propose the Lift3D framework, which progressively enhances 2D foundation models with implicit and explicit 3D robotic representations to construct a robust 3D manip"},"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":"2411.18623","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T18:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"049b07cc483150461ccba207060149ce91874f82a9b63fe5fb7af8fa27426a69","abstract_canon_sha256":"b51a075552bdc3cc8e8f50bd3a8ace323cedf676bb1537ff7ea977c96df82913"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:12.827268Z","signature_b64":"5Q9B20RwZFuXm3YNSSctUVCkquR/IY8ZJ/H/V8DsGAlogwT7kD5ZVVVk1L1Qjhchs4ISGHtnHZzptlnCpV/QDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"464ff10c24b2e57954db7b04781e58c3db08b6d93040bc8639954023bfe37dc9","last_reissued_at":"2026-07-05T09:49:12.826810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:12.826810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Gu, Jiaming Liu, Lily Lee, Longzan Luo, Pengwei Wang, Renrui Zhang, Shanghang Zhang, Sixiang Chen, Yueru Jia, Zhilue Wang, Zhongyuan Wang","submitted_at":"2024-11-27T18:59:52Z","abstract_excerpt":"3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has increasingly focused on the explicit extraction of 3D features, while still facing challenges such as the lack of large-scale robotic 3D data and the potential loss of spatial geometry. To address these limitations, we propose the Lift3D framework, which progressively enhances 2D foundation models with implicit and explicit 3D robotic representations to construct a robust 3D manip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18623","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/2411.18623/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":"2411.18623","created_at":"2026-07-05T09:49:12.826871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18623v2","created_at":"2026-07-05T09:49:12.826871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18623","created_at":"2026-07-05T09:49:12.826871+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZH7CDBEWLSX","created_at":"2026-07-05T09:49:12.826871+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZH7CDBEWLSXSVG3","created_at":"2026-07-05T09:49:12.826871+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZH7CDBE","created_at":"2026-07-05T09:49:12.826871+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05396","citing_title":"From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13394","citing_title":"GeoHAT: Geometry-Adaptive Hybrid Action Transformer for Mobile Manipulation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12499","citing_title":"Action-Effect Memory Pretraining for Robot Manipulation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24642","citing_title":"Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25829","citing_title":"OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21258","citing_title":"Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10631","citing_title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23024","citing_title":"InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05126","citing_title":"ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12908","citing_title":"Robotic Manipulation is Vision-to-Geometry Mapping ($f(v) \\rightarrow G$): Vision-Geometry Backbones over Language and Video Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15281","citing_title":"R3D: Revisiting 3D Policy Learning","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IZH7CDBEWLSXSVG3PMCHQHSYYP","json":"https://pith.science/pith/IZH7CDBEWLSXSVG3PMCHQHSYYP.json","graph_json":"https://pith.science/api/pith-number/IZH7CDBEWLSXSVG3PMCHQHSYYP/graph.json","events_json":"https://pith.science/api/pith-number/IZH7CDBEWLSXSVG3PMCHQHSYYP/events.json","paper":"https://pith.science/paper/IZH7CDBE"},"agent_actions":{"view_html":"https://pith.science/pith/IZH7CDBEWLSXSVG3PMCHQHSYYP","download_json":"https://pith.science/pith/IZH7CDBEWLSXSVG3PMCHQHSYYP.json","view_paper":"https://pith.science/paper/IZH7CDBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18623&json=true","fetch_graph":"https://pith.science/api/pith-number/IZH7CDBEWLSXSVG3PMCHQHSYYP/graph.json","fetch_events":"https://pith.science/api/pith-number/IZH7CDBEWLSXSVG3PMCHQHSYYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZH7CDBEWLSXSVG3PMCHQHSYYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZH7CDBEWLSXSVG3PMCHQHSYYP/action/storage_attestation","attest_author":"https://pith.science/pith/IZH7CDBEWLSXSVG3PMCHQHSYYP/action/author_attestation","sign_citation":"https://pith.science/pith/IZH7CDBEWLSXSVG3PMCHQHSYYP/action/citation_signature","submit_replication":"https://pith.science/pith/IZH7CDBEWLSXSVG3PMCHQHSYYP/action/replication_record"}},"created_at":"2026-07-05T09:49:12.826871+00:00","updated_at":"2026-07-05T09:49:12.826871+00:00"}