{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EQZ3NK7R2FX7D4ERRUHMXGPRRY","short_pith_number":"pith:EQZ3NK7R","schema_version":"1.0","canonical_sha256":"2433b6abf1d16ff1f0918d0ecb99f18e0cd09cd44d97103bdca02e074a3ffc8d","source":{"kind":"arxiv","id":"2604.01388","version":2},"attestation_state":"computed","paper":{"title":"LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dzmitry Tsishkou, Fabien Moutarde, Fusang Wang, Luis Rold\\~ao, Moussab Bennehar, Nathan Piasco","submitted_at":"2026-04-01T20:48:06Z","abstract_excerpt":"Recent advancements in open-vocabulary 3D scene understanding heavily rely on 3D Gaussian Splatting (3DGS) to register vision-language features into 3D space. However, we identify two critical limitations in these approaches: the spatial ambiguity arising from unstructured, overlapping Gaussians which necessitates probabilistic feature registration, and the multi-level semantic ambiguity caused by pooling features over object-level masks, which dilutes fine-grained details. To address these challenges, we present a novel framework that leverages Sparse Voxel Rasterization (SVRaster) as a struc"},"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":"2604.01388","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-01T20:48:06Z","cross_cats_sorted":[],"title_canon_sha256":"1947798d84508d7972754845c1e213891ea3e2a248ae3fc048a2a1992adf0d65","abstract_canon_sha256":"24d351db3908463fe5d53a6223f480b17402399831563d9d0fd440151eb2698f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:43.283528Z","signature_b64":"vrYhU/+4mpYu/FtbvMEpdlizcTeerRdKseDseV0oN2Jfo0JN1rfmcvVXuxl8cqeCOYJLHuws4xa9dlSRKsqsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2433b6abf1d16ff1f0918d0ecb99f18e0cd09cd44d97103bdca02e074a3ffc8d","last_reissued_at":"2026-07-10T01:19:43.283024Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:43.283024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dzmitry Tsishkou, Fabien Moutarde, Fusang Wang, Luis Rold\\~ao, Moussab Bennehar, Nathan Piasco","submitted_at":"2026-04-01T20:48:06Z","abstract_excerpt":"Recent advancements in open-vocabulary 3D scene understanding heavily rely on 3D Gaussian Splatting (3DGS) to register vision-language features into 3D space. However, we identify two critical limitations in these approaches: the spatial ambiguity arising from unstructured, overlapping Gaussians which necessitates probabilistic feature registration, and the multi-level semantic ambiguity caused by pooling features over object-level masks, which dilutes fine-grained details. To address these challenges, we present a novel framework that leverages Sparse Voxel Rasterization (SVRaster) as a struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.01388","kind":"arxiv","version":2},"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/2604.01388/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":"2604.01388","created_at":"2026-07-10T01:19:43.283074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.01388v2","created_at":"2026-07-10T01:19:43.283074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01388","created_at":"2026-07-10T01:19:43.283074+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQZ3NK7R2FX7","created_at":"2026-07-10T01:19:43.283074+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQZ3NK7R2FX7D4ER","created_at":"2026-07-10T01:19:43.283074+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQZ3NK7R","created_at":"2026-07-10T01:19:43.283074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.23031","citing_title":"DrivingVoxels: Compositional Sparse Voxel Rasterization for Dynamic Driving Scene Reconstruction","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQZ3NK7R2FX7D4ERRUHMXGPRRY","json":"https://pith.science/pith/EQZ3NK7R2FX7D4ERRUHMXGPRRY.json","graph_json":"https://pith.science/api/pith-number/EQZ3NK7R2FX7D4ERRUHMXGPRRY/graph.json","events_json":"https://pith.science/api/pith-number/EQZ3NK7R2FX7D4ERRUHMXGPRRY/events.json","paper":"https://pith.science/paper/EQZ3NK7R"},"agent_actions":{"view_html":"https://pith.science/pith/EQZ3NK7R2FX7D4ERRUHMXGPRRY","download_json":"https://pith.science/pith/EQZ3NK7R2FX7D4ERRUHMXGPRRY.json","view_paper":"https://pith.science/paper/EQZ3NK7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.01388&json=true","fetch_graph":"https://pith.science/api/pith-number/EQZ3NK7R2FX7D4ERRUHMXGPRRY/graph.json","fetch_events":"https://pith.science/api/pith-number/EQZ3NK7R2FX7D4ERRUHMXGPRRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQZ3NK7R2FX7D4ERRUHMXGPRRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQZ3NK7R2FX7D4ERRUHMXGPRRY/action/storage_attestation","attest_author":"https://pith.science/pith/EQZ3NK7R2FX7D4ERRUHMXGPRRY/action/author_attestation","sign_citation":"https://pith.science/pith/EQZ3NK7R2FX7D4ERRUHMXGPRRY/action/citation_signature","submit_replication":"https://pith.science/pith/EQZ3NK7R2FX7D4ERRUHMXGPRRY/action/replication_record"}},"created_at":"2026-07-10T01:19:43.283074+00:00","updated_at":"2026-07-10T01:19:43.283074+00:00"}