{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AX6BYDSZLZXECNV4HUU5M74K6W","short_pith_number":"pith:AX6BYDSZ","schema_version":"1.0","canonical_sha256":"05fc1c0e595e6e4136bc3d29d67f8af5b473a37dc5d23138f0db7d98310b6f78","source":{"kind":"arxiv","id":"2309.15596","version":1},"attestation_state":"computed","paper":{"title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Cordelia Schmid, Ivan Laptev, Ricardo Garcia, Shizhe Chen","submitted_at":"2023-09-27T11:50:43Z","abstract_excerpt":"The ability for robots to comprehend and execute manipulation tasks based on natural language instructions is a long-term goal in robotics. The dominant approaches for language-guided manipulation use 2D image representations, which face difficulties in combining multi-view cameras and inferring precise 3D positions and relationships. To address these limitations, we propose a 3D point cloud based policy called PolarNet for language-guided manipulation. It leverages carefully designed point cloud inputs, efficient point cloud encoders, and multimodal transformers to learn 3D point cloud repres"},"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":"2309.15596","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-09-27T11:50:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"095bff72a6b24b525910b1299d60194be18eca9ff44ae837b24ad54abc28b4ce","abstract_canon_sha256":"a84f8d6e0fe8fe170ff477b25d3459b626898a8208109ffc3bf5a64b1384f6ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:48.023710Z","signature_b64":"aIyD9qFIHnW45Gqj2WAdMjB9db3Sepx7IlfABtibjD1xaUtDxE7AdYfW0hjZ918IXyXzxlnv1bPvEk9EYi9KAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05fc1c0e595e6e4136bc3d29d67f8af5b473a37dc5d23138f0db7d98310b6f78","last_reissued_at":"2026-07-05T06:54:48.023221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:48.023221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Cordelia Schmid, Ivan Laptev, Ricardo Garcia, Shizhe Chen","submitted_at":"2023-09-27T11:50:43Z","abstract_excerpt":"The ability for robots to comprehend and execute manipulation tasks based on natural language instructions is a long-term goal in robotics. The dominant approaches for language-guided manipulation use 2D image representations, which face difficulties in combining multi-view cameras and inferring precise 3D positions and relationships. To address these limitations, we propose a 3D point cloud based policy called PolarNet for language-guided manipulation. It leverages carefully designed point cloud inputs, efficient point cloud encoders, and multimodal transformers to learn 3D point cloud repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15596","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/2309.15596/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":"2309.15596","created_at":"2026-07-05T06:54:48.023287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15596v1","created_at":"2026-07-05T06:54:48.023287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15596","created_at":"2026-07-05T06:54:48.023287+00:00"},{"alias_kind":"pith_short_12","alias_value":"AX6BYDSZLZXE","created_at":"2026-07-05T06:54:48.023287+00:00"},{"alias_kind":"pith_short_16","alias_value":"AX6BYDSZLZXECNV4","created_at":"2026-07-05T06:54:48.023287+00:00"},{"alias_kind":"pith_short_8","alias_value":"AX6BYDSZ","created_at":"2026-07-05T06:54:48.023287+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26800","citing_title":"SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21788","citing_title":"Rotation-Aware Point-Cloud Embeddings for Vision-Based In-Hand Reorientation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26800","citing_title":"SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14135","citing_title":"GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":70,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10573","citing_title":"Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AX6BYDSZLZXECNV4HUU5M74K6W","json":"https://pith.science/pith/AX6BYDSZLZXECNV4HUU5M74K6W.json","graph_json":"https://pith.science/api/pith-number/AX6BYDSZLZXECNV4HUU5M74K6W/graph.json","events_json":"https://pith.science/api/pith-number/AX6BYDSZLZXECNV4HUU5M74K6W/events.json","paper":"https://pith.science/paper/AX6BYDSZ"},"agent_actions":{"view_html":"https://pith.science/pith/AX6BYDSZLZXECNV4HUU5M74K6W","download_json":"https://pith.science/pith/AX6BYDSZLZXECNV4HUU5M74K6W.json","view_paper":"https://pith.science/paper/AX6BYDSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15596&json=true","fetch_graph":"https://pith.science/api/pith-number/AX6BYDSZLZXECNV4HUU5M74K6W/graph.json","fetch_events":"https://pith.science/api/pith-number/AX6BYDSZLZXECNV4HUU5M74K6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AX6BYDSZLZXECNV4HUU5M74K6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AX6BYDSZLZXECNV4HUU5M74K6W/action/storage_attestation","attest_author":"https://pith.science/pith/AX6BYDSZLZXECNV4HUU5M74K6W/action/author_attestation","sign_citation":"https://pith.science/pith/AX6BYDSZLZXECNV4HUU5M74K6W/action/citation_signature","submit_replication":"https://pith.science/pith/AX6BYDSZLZXECNV4HUU5M74K6W/action/replication_record"}},"created_at":"2026-07-05T06:54:48.023287+00:00","updated_at":"2026-07-05T06:54:48.023287+00:00"}