{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F46KBAIMDMQM32E7AWC3TLGJZ5","short_pith_number":"pith:F46KBAIM","schema_version":"1.0","canonical_sha256":"2f3ca0810c1b20cde89f0585b9acc9cf743cdeb82794ad34fd00422cf23e93cf","source":{"kind":"arxiv","id":"2312.03203","version":3},"attestation_state":"computed","paper":{"title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achuta Kadambi, Dejia Xu, Haoran Chang, Pradyumna Chari, Shijie Zhou, Sicheng Jiang, Suya You, Zehao Zhu, Zhangyang Wang, Zhiwen Fan","submitted_at":"2023-12-06T00:46:30Z","abstract_excerpt":"3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times, some work has emerged that aims to extend the functionality of NeRF beyond view synthesis, for semantically aware tasks such as editing and segmentation using 3D feature field distillation from 2D foundation models. However, these methods have two major limitations: (a) they are limited by the rendering speed of NeRF pipelines, and (b) implicitly represented feature fields suffer from continuity artif"},"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":"2312.03203","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T00:46:30Z","cross_cats_sorted":[],"title_canon_sha256":"7cba79044f3d2bd484e1193e55cdee99beeb69295c6dd245f7342133d7e3a059","abstract_canon_sha256":"c7fa52ed4cc9d7ec2971ca31b9082d9979bf56c9782079498783a03e56e3f395"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:06.539797Z","signature_b64":"rJ12WYK7+1KXcqW7TCFKTsqYTqt7SI1gBkSYhKXOlY8ay5QGQhTK8pqi4uyjRygq/ehtOdMmHQg7E88Ub1qnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f3ca0810c1b20cde89f0585b9acc9cf743cdeb82794ad34fd00422cf23e93cf","last_reissued_at":"2026-07-05T08:05:06.539354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:06.539354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achuta Kadambi, Dejia Xu, Haoran Chang, Pradyumna Chari, Shijie Zhou, Sicheng Jiang, Suya You, Zehao Zhu, Zhangyang Wang, Zhiwen Fan","submitted_at":"2023-12-06T00:46:30Z","abstract_excerpt":"3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times, some work has emerged that aims to extend the functionality of NeRF beyond view synthesis, for semantically aware tasks such as editing and segmentation using 3D feature field distillation from 2D foundation models. However, these methods have two major limitations: (a) they are limited by the rendering speed of NeRF pipelines, and (b) implicitly represented feature fields suffer from continuity artif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03203","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/2312.03203/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":"2312.03203","created_at":"2026-07-05T08:05:06.539408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03203v3","created_at":"2026-07-05T08:05:06.539408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03203","created_at":"2026-07-05T08:05:06.539408+00:00"},{"alias_kind":"pith_short_12","alias_value":"F46KBAIMDMQM","created_at":"2026-07-05T08:05:06.539408+00:00"},{"alias_kind":"pith_short_16","alias_value":"F46KBAIMDMQM32E7","created_at":"2026-07-05T08:05:06.539408+00:00"},{"alias_kind":"pith_short_8","alias_value":"F46KBAIM","created_at":"2026-07-05T08:05:06.539408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30065","citing_title":"Boosting Zero-Shot 3D Style Transfer with 2D Pre-trained Priors","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11144","citing_title":"Forecast-aware Gaussian Splatting for Predictive 3D Representation in Language-Guided Pick-and-Place Manipulation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F46KBAIMDMQM32E7AWC3TLGJZ5","json":"https://pith.science/pith/F46KBAIMDMQM32E7AWC3TLGJZ5.json","graph_json":"https://pith.science/api/pith-number/F46KBAIMDMQM32E7AWC3TLGJZ5/graph.json","events_json":"https://pith.science/api/pith-number/F46KBAIMDMQM32E7AWC3TLGJZ5/events.json","paper":"https://pith.science/paper/F46KBAIM"},"agent_actions":{"view_html":"https://pith.science/pith/F46KBAIMDMQM32E7AWC3TLGJZ5","download_json":"https://pith.science/pith/F46KBAIMDMQM32E7AWC3TLGJZ5.json","view_paper":"https://pith.science/paper/F46KBAIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03203&json=true","fetch_graph":"https://pith.science/api/pith-number/F46KBAIMDMQM32E7AWC3TLGJZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/F46KBAIMDMQM32E7AWC3TLGJZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F46KBAIMDMQM32E7AWC3TLGJZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F46KBAIMDMQM32E7AWC3TLGJZ5/action/storage_attestation","attest_author":"https://pith.science/pith/F46KBAIMDMQM32E7AWC3TLGJZ5/action/author_attestation","sign_citation":"https://pith.science/pith/F46KBAIMDMQM32E7AWC3TLGJZ5/action/citation_signature","submit_replication":"https://pith.science/pith/F46KBAIMDMQM32E7AWC3TLGJZ5/action/replication_record"}},"created_at":"2026-07-05T08:05:06.539408+00:00","updated_at":"2026-07-05T08:05:06.539408+00:00"}