{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DQ24J3APVHAXNAIYF42WIETNXR","short_pith_number":"pith:DQ24J3AP","schema_version":"1.0","canonical_sha256":"1c35c4ec0fa9c17681182f3564126dbc565d82f778bbf2f3d4828174eee41b5b","source":{"kind":"arxiv","id":"2210.05663","version":3},"attestation_state":"computed","paper":{"title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Arthur Szlam, Chris Paxton, Lerrel Pinto, Nur Muhammad Mahi Shafiullah, Soumith Chintala","submitted_at":"2022-10-11T17:57:10Z","abstract_excerpt":"We propose CLIP-Fields, an implicit scene model that can be used for a variety of tasks, such as segmentation, instance identification, semantic search over space, and view localization. CLIP-Fields learns a mapping from spatial locations to semantic embedding vectors. Importantly, we show that this mapping can be trained with supervision coming only from web-image and web-text trained models such as CLIP, Detic, and Sentence-BERT; and thus uses no direct human supervision. When compared to baselines like Mask-RCNN, our method outperforms on few-shot instance identification or semantic segment"},"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":"2210.05663","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-10-11T17:57:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1829640a23f3461e38c8394b2d6677f3eaeb293d66d7f0685266651d14aaf463","abstract_canon_sha256":"44e4a9f99b7e4f5276b80eceb897ece1bd84498c34674571576d22121928e771"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:29.731027Z","signature_b64":"NmzW8fdrHyUqweo/wvLlIQ1a0dVKZ/RVA+tkfbxyJHR4oO5rwYTMKl5GNAF/ec7bnEoz/QfOBwJWnw9IqFzmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c35c4ec0fa9c17681182f3564126dbc565d82f778bbf2f3d4828174eee41b5b","last_reissued_at":"2026-07-05T09:37:29.730609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:29.730609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Arthur Szlam, Chris Paxton, Lerrel Pinto, Nur Muhammad Mahi Shafiullah, Soumith Chintala","submitted_at":"2022-10-11T17:57:10Z","abstract_excerpt":"We propose CLIP-Fields, an implicit scene model that can be used for a variety of tasks, such as segmentation, instance identification, semantic search over space, and view localization. CLIP-Fields learns a mapping from spatial locations to semantic embedding vectors. Importantly, we show that this mapping can be trained with supervision coming only from web-image and web-text trained models such as CLIP, Detic, and Sentence-BERT; and thus uses no direct human supervision. When compared to baselines like Mask-RCNN, our method outperforms on few-shot instance identification or semantic segment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05663","kind":"arxiv","version":3},"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/2210.05663/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":"2210.05663","created_at":"2026-07-05T09:37:29.730666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05663v3","created_at":"2026-07-05T09:37:29.730666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05663","created_at":"2026-07-05T09:37:29.730666+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQ24J3APVHAX","created_at":"2026-07-05T09:37:29.730666+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQ24J3APVHAXNAIY","created_at":"2026-07-05T09:37:29.730666+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQ24J3AP","created_at":"2026-07-05T09:37:29.730666+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08182","citing_title":"LEEVLA: Seeing What Matters in Latent Environment Evolution for Vision-Language-Action","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08655","citing_title":"PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28760","citing_title":"Vision-Language Models for Deployable Social Robot Navigation: Bridging Semantic Reasoning and Low-Level Control","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19420","citing_title":"Beyond Waypoints: Dual-Heatmap Grounding for Cross-Embodiment Semantic Navigation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13312","citing_title":"EL3DD: Extended Latent 3D Diffusion for Language Conditioned Multitask Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19704","citing_title":"RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08392","citing_title":"ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01907","citing_title":"Lifting Unlabeled Internet-level Data for 3D Scene Understanding","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19587","citing_title":"SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18271","citing_title":"EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17721","citing_title":"GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusion","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQ24J3APVHAXNAIYF42WIETNXR","json":"https://pith.science/pith/DQ24J3APVHAXNAIYF42WIETNXR.json","graph_json":"https://pith.science/api/pith-number/DQ24J3APVHAXNAIYF42WIETNXR/graph.json","events_json":"https://pith.science/api/pith-number/DQ24J3APVHAXNAIYF42WIETNXR/events.json","paper":"https://pith.science/paper/DQ24J3AP"},"agent_actions":{"view_html":"https://pith.science/pith/DQ24J3APVHAXNAIYF42WIETNXR","download_json":"https://pith.science/pith/DQ24J3APVHAXNAIYF42WIETNXR.json","view_paper":"https://pith.science/paper/DQ24J3AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05663&json=true","fetch_graph":"https://pith.science/api/pith-number/DQ24J3APVHAXNAIYF42WIETNXR/graph.json","fetch_events":"https://pith.science/api/pith-number/DQ24J3APVHAXNAIYF42WIETNXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQ24J3APVHAXNAIYF42WIETNXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQ24J3APVHAXNAIYF42WIETNXR/action/storage_attestation","attest_author":"https://pith.science/pith/DQ24J3APVHAXNAIYF42WIETNXR/action/author_attestation","sign_citation":"https://pith.science/pith/DQ24J3APVHAXNAIYF42WIETNXR/action/citation_signature","submit_replication":"https://pith.science/pith/DQ24J3APVHAXNAIYF42WIETNXR/action/replication_record"}},"created_at":"2026-07-05T09:37:29.730666+00:00","updated_at":"2026-07-05T09:37:29.730666+00:00"}