{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JSSKR7HBG3MORRHLCYF5EJ35R5","short_pith_number":"pith:JSSKR7HB","schema_version":"1.0","canonical_sha256":"4ca4a8fce136d8e8c4eb160bd2277d8f7865c0a818d17ea5233a5051ada64378","source":{"kind":"arxiv","id":"2502.16652","version":1},"attestation_state":"computed","paper":{"title":"Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"GeonU Kim, Jaesung Choe, Kim Jun-Seong, Kim Yu-Ji, Tae-Hyun Oh, Yu-Chiang Frank Wang","submitted_at":"2025-02-23T17:01:14Z","abstract_excerpt":"We introduce Dr. Splat, a novel approach for open-vocabulary 3D scene understanding leveraging 3D Gaussian Splatting. Unlike existing language-embedded 3DGS methods, which rely on a rendering process, our method directly associates language-aligned CLIP embeddings with 3D Gaussians for holistic 3D scene understanding. The key of our method is a language feature registration technique where CLIP embeddings are assigned to the dominant Gaussians intersected by each pixel-ray. Moreover, we integrate Product Quantization (PQ) trained on general large-scale image data to compactly represent embeddi"},"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":"2502.16652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T17:01:14Z","cross_cats_sorted":[],"title_canon_sha256":"013a1585ca43948610c29363b9c2d01a2f8ca66872532801e52482d7ab6259a7","abstract_canon_sha256":"5f6e8ae144cb15304c59cde0f2e61c8e8fb9fd09bf6ab3dda99e50a221bb6248"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:57.038387Z","signature_b64":"9GGqvklUytvujS7sIxBo6CFBpbB6CzUvZ1l0t7j46bt6J2W/8/5qRp0XfXqc5Yr0gOgDKZ3+1n3W/bUU3xfeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ca4a8fce136d8e8c4eb160bd2277d8f7865c0a818d17ea5233a5051ada64378","last_reissued_at":"2026-07-05T10:18:57.037881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:57.037881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"GeonU Kim, Jaesung Choe, Kim Jun-Seong, Kim Yu-Ji, Tae-Hyun Oh, Yu-Chiang Frank Wang","submitted_at":"2025-02-23T17:01:14Z","abstract_excerpt":"We introduce Dr. Splat, a novel approach for open-vocabulary 3D scene understanding leveraging 3D Gaussian Splatting. Unlike existing language-embedded 3DGS methods, which rely on a rendering process, our method directly associates language-aligned CLIP embeddings with 3D Gaussians for holistic 3D scene understanding. The key of our method is a language feature registration technique where CLIP embeddings are assigned to the dominant Gaussians intersected by each pixel-ray. Moreover, we integrate Product Quantization (PQ) trained on general large-scale image data to compactly represent embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16652","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/2502.16652/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":"2502.16652","created_at":"2026-07-05T10:18:57.037933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16652v1","created_at":"2026-07-05T10:18:57.037933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16652","created_at":"2026-07-05T10:18:57.037933+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSSKR7HBG3MO","created_at":"2026-07-05T10:18:57.037933+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSSKR7HBG3MORRHL","created_at":"2026-07-05T10:18:57.037933+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSSKR7HB","created_at":"2026-07-05T10:18:57.037933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08980","citing_title":"EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29376","citing_title":"SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSSKR7HBG3MORRHLCYF5EJ35R5","json":"https://pith.science/pith/JSSKR7HBG3MORRHLCYF5EJ35R5.json","graph_json":"https://pith.science/api/pith-number/JSSKR7HBG3MORRHLCYF5EJ35R5/graph.json","events_json":"https://pith.science/api/pith-number/JSSKR7HBG3MORRHLCYF5EJ35R5/events.json","paper":"https://pith.science/paper/JSSKR7HB"},"agent_actions":{"view_html":"https://pith.science/pith/JSSKR7HBG3MORRHLCYF5EJ35R5","download_json":"https://pith.science/pith/JSSKR7HBG3MORRHLCYF5EJ35R5.json","view_paper":"https://pith.science/paper/JSSKR7HB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16652&json=true","fetch_graph":"https://pith.science/api/pith-number/JSSKR7HBG3MORRHLCYF5EJ35R5/graph.json","fetch_events":"https://pith.science/api/pith-number/JSSKR7HBG3MORRHLCYF5EJ35R5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSSKR7HBG3MORRHLCYF5EJ35R5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSSKR7HBG3MORRHLCYF5EJ35R5/action/storage_attestation","attest_author":"https://pith.science/pith/JSSKR7HBG3MORRHLCYF5EJ35R5/action/author_attestation","sign_citation":"https://pith.science/pith/JSSKR7HBG3MORRHLCYF5EJ35R5/action/citation_signature","submit_replication":"https://pith.science/pith/JSSKR7HBG3MORRHLCYF5EJ35R5/action/replication_record"}},"created_at":"2026-07-05T10:18:57.037933+00:00","updated_at":"2026-07-05T10:18:57.037933+00:00"}