{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZJQTJ6DGFBCKIDAYDQJZKJ53RO","short_pith_number":"pith:ZJQTJ6DG","schema_version":"1.0","canonical_sha256":"ca6134f8662844a40c181c139527bb8bb6aa5f726135b1b3accbcdb01a4fd88f","source":{"kind":"arxiv","id":"2308.07931","version":2},"attestation_state":"computed","paper":{"title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alan Yu, Ge Yang, Jansen Wong, Leslie Pack Kaelbling, Phillip Isola, William Shen","submitted_at":"2023-07-27T17:59:14Z","abstract_excerpt":"Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image features. This work bridges this 2D-to-3D gap for robotic manipulation by leveraging distilled feature fields to combine accurate 3D geometry with rich semantics from 2D foundation models. We present a few-shot learning method for 6-DOF grasping and placing that harnesses these strong spatial and semantic priors to achieve in-the-wild generalization to unsee"},"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":"2308.07931","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-27T17:59:14Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"6fdeea86cdc721a91a54a61e7dd3c028d018665e2c361ac972b7dc6d5eb2e638","abstract_canon_sha256":"c42631600bad076d54bf8a1b0bb0344481d04215e72c39b8ba5b00e175d24441"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:58.101235Z","signature_b64":"u05zQTZAEpGyt5tcFgy+nqdCoCEKecU7VFir0yssTXbO7zDdBaB8x6WBIuCP5FhLvXO5uylUXINJFk81u73DBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca6134f8662844a40c181c139527bb8bb6aa5f726135b1b3accbcdb01a4fd88f","last_reissued_at":"2026-07-05T07:28:58.100784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:58.100784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alan Yu, Ge Yang, Jansen Wong, Leslie Pack Kaelbling, Phillip Isola, William Shen","submitted_at":"2023-07-27T17:59:14Z","abstract_excerpt":"Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image features. This work bridges this 2D-to-3D gap for robotic manipulation by leveraging distilled feature fields to combine accurate 3D geometry with rich semantics from 2D foundation models. We present a few-shot learning method for 6-DOF grasping and placing that harnesses these strong spatial and semantic priors to achieve in-the-wild generalization to unsee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07931","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/2308.07931/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":"2308.07931","created_at":"2026-07-05T07:28:58.100848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07931v2","created_at":"2026-07-05T07:28:58.100848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07931","created_at":"2026-07-05T07:28:58.100848+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJQTJ6DGFBCK","created_at":"2026-07-05T07:28:58.100848+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJQTJ6DGFBCKIDAY","created_at":"2026-07-05T07:28:58.100848+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJQTJ6DG","created_at":"2026-07-05T07:28:58.100848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08655","citing_title":"PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04021","citing_title":"C3G: Learning Compact 3D Representations with 2K Gaussians","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03181","citing_title":"Robotic Grasping and Placement Controlled by EEG-Based Hybrid Visual and Motor Imagery","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2403.03954","citing_title":"3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11809","citing_title":"Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27106","citing_title":"Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06168","citing_title":"Action Images: End-to-End Policy Learning via Multiview Video Generation","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJQTJ6DGFBCKIDAYDQJZKJ53RO","json":"https://pith.science/pith/ZJQTJ6DGFBCKIDAYDQJZKJ53RO.json","graph_json":"https://pith.science/api/pith-number/ZJQTJ6DGFBCKIDAYDQJZKJ53RO/graph.json","events_json":"https://pith.science/api/pith-number/ZJQTJ6DGFBCKIDAYDQJZKJ53RO/events.json","paper":"https://pith.science/paper/ZJQTJ6DG"},"agent_actions":{"view_html":"https://pith.science/pith/ZJQTJ6DGFBCKIDAYDQJZKJ53RO","download_json":"https://pith.science/pith/ZJQTJ6DGFBCKIDAYDQJZKJ53RO.json","view_paper":"https://pith.science/paper/ZJQTJ6DG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07931&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJQTJ6DGFBCKIDAYDQJZKJ53RO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJQTJ6DGFBCKIDAYDQJZKJ53RO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJQTJ6DGFBCKIDAYDQJZKJ53RO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJQTJ6DGFBCKIDAYDQJZKJ53RO/action/storage_attestation","attest_author":"https://pith.science/pith/ZJQTJ6DGFBCKIDAYDQJZKJ53RO/action/author_attestation","sign_citation":"https://pith.science/pith/ZJQTJ6DGFBCKIDAYDQJZKJ53RO/action/citation_signature","submit_replication":"https://pith.science/pith/ZJQTJ6DGFBCKIDAYDQJZKJ53RO/action/replication_record"}},"created_at":"2026-07-05T07:28:58.100848+00:00","updated_at":"2026-07-05T07:28:58.100848+00:00"}