{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ENZH4FSXH2TTRUHPRVZ54O4CCW","short_pith_number":"pith:ENZH4FSX","schema_version":"1.0","canonical_sha256":"23727e16573ea738d0ef8d73de3b8215a6f7182f891aa3998f4bf25060417812","source":{"kind":"arxiv","id":"2406.18742","version":5},"attestation_state":"computed","paper":{"title":"3D Feature Distillation with Object-Centric Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Georgios Tziafas, Hamidreza Kasaei, Yucheng Xu, Zhibin Li","submitted_at":"2024-06-26T20:16:49Z","abstract_excerpt":"Grounding natural language to the physical world is a ubiquitous topic with a wide range of applications in computer vision and robotics. Recently, 2D vision-language models such as CLIP have been widely popularized, due to their impressive capabilities for open-vocabulary grounding in 2D images. Recent works aim to elevate 2D CLIP features to 3D via feature distillation, but either learn neural fields that are scene-specific and hence lack generalization, or focus on indoor room scan data that require access to multiple camera views, which is not practical in robot manipulation scenarios. Add"},"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":"2406.18742","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-26T20:16:49Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"05c3944e95b1133e0062da00309268296674480ae8f75c0c6131decc5d35105e","abstract_canon_sha256":"213ce84f71e59b1a36e376da19271c6d523694c9ff4d1d6677081cb96ae7a726"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:19.322412Z","signature_b64":"tLOdicedw1mEdB/r851WKgW3hpriKIfiEg4svh6O7OKVwkZJx1S1iBtYnWKkplRZZ0/7okf6c+asUMg0ZbTtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23727e16573ea738d0ef8d73de3b8215a6f7182f891aa3998f4bf25060417812","last_reissued_at":"2026-07-05T11:58:19.321929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:19.321929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Feature Distillation with Object-Centric Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Georgios Tziafas, Hamidreza Kasaei, Yucheng Xu, Zhibin Li","submitted_at":"2024-06-26T20:16:49Z","abstract_excerpt":"Grounding natural language to the physical world is a ubiquitous topic with a wide range of applications in computer vision and robotics. Recently, 2D vision-language models such as CLIP have been widely popularized, due to their impressive capabilities for open-vocabulary grounding in 2D images. Recent works aim to elevate 2D CLIP features to 3D via feature distillation, but either learn neural fields that are scene-specific and hence lack generalization, or focus on indoor room scan data that require access to multiple camera views, which is not practical in robot manipulation scenarios. Add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18742","kind":"arxiv","version":5},"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/2406.18742/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":"2406.18742","created_at":"2026-07-05T11:58:19.321985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18742v5","created_at":"2026-07-05T11:58:19.321985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18742","created_at":"2026-07-05T11:58:19.321985+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENZH4FSXH2TT","created_at":"2026-07-05T11:58:19.321985+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENZH4FSXH2TTRUHP","created_at":"2026-07-05T11:58:19.321985+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENZH4FSX","created_at":"2026-07-05T11:58:19.321985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENZH4FSXH2TTRUHPRVZ54O4CCW","json":"https://pith.science/pith/ENZH4FSXH2TTRUHPRVZ54O4CCW.json","graph_json":"https://pith.science/api/pith-number/ENZH4FSXH2TTRUHPRVZ54O4CCW/graph.json","events_json":"https://pith.science/api/pith-number/ENZH4FSXH2TTRUHPRVZ54O4CCW/events.json","paper":"https://pith.science/paper/ENZH4FSX"},"agent_actions":{"view_html":"https://pith.science/pith/ENZH4FSXH2TTRUHPRVZ54O4CCW","download_json":"https://pith.science/pith/ENZH4FSXH2TTRUHPRVZ54O4CCW.json","view_paper":"https://pith.science/paper/ENZH4FSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18742&json=true","fetch_graph":"https://pith.science/api/pith-number/ENZH4FSXH2TTRUHPRVZ54O4CCW/graph.json","fetch_events":"https://pith.science/api/pith-number/ENZH4FSXH2TTRUHPRVZ54O4CCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENZH4FSXH2TTRUHPRVZ54O4CCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENZH4FSXH2TTRUHPRVZ54O4CCW/action/storage_attestation","attest_author":"https://pith.science/pith/ENZH4FSXH2TTRUHPRVZ54O4CCW/action/author_attestation","sign_citation":"https://pith.science/pith/ENZH4FSXH2TTRUHPRVZ54O4CCW/action/citation_signature","submit_replication":"https://pith.science/pith/ENZH4FSXH2TTRUHPRVZ54O4CCW/action/replication_record"}},"created_at":"2026-07-05T11:58:19.321985+00:00","updated_at":"2026-07-05T11:58:19.321985+00:00"}