{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KG4OSIOH2EWC7NVDSRO6UMNDJQ","short_pith_number":"pith:KG4OSIOH","schema_version":"1.0","canonical_sha256":"51b8e921c7d12c2fb6a3945dea31a34c2d794d703158f8f5ef1cf40e2889b2cc","source":{"kind":"arxiv","id":"2311.18482","version":1},"attestation_state":"computed","paper":{"title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Hao-Bin Duan, Jin-Chuan Shi, Miao Wang, Shao-Hua Guan","submitted_at":"2023-11-30T11:50:07Z","abstract_excerpt":"Open-vocabulary querying in 3D space is challenging but essential for scene understanding tasks such as object localization and segmentation. Language-embedded scene representations have made progress by incorporating language features into 3D spaces. However, their efficacy heavily depends on neural networks that are resource-intensive in training and rendering. Although recent 3D Gaussians offer efficient and high-quality novel view synthesis, directly embedding language features in them leads to prohibitive memory usage and decreased performance. In this work, we introduce Language Embedded"},"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":"2311.18482","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T11:50:07Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"752cf7a0c3359d67571cbe9b6f0b8ffd1eb83f71b6bbfdcd8d6c409cff0c1805","abstract_canon_sha256":"0c9826f14668eb103877da24ca66f9401b8a02ee5bfa2b09a8f87dd0b0a275a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:42.911197Z","signature_b64":"Ocyb6gLxw5Dqa1YG4iDUOgaSy4IiwtCdcQBqo/mgbZDtnTHROH0Hu33iaG486z2cG+sBiW+OdTAf+GYMxueTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51b8e921c7d12c2fb6a3945dea31a34c2d794d703158f8f5ef1cf40e2889b2cc","last_reissued_at":"2026-07-05T07:18:42.910766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:42.910766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Hao-Bin Duan, Jin-Chuan Shi, Miao Wang, Shao-Hua Guan","submitted_at":"2023-11-30T11:50:07Z","abstract_excerpt":"Open-vocabulary querying in 3D space is challenging but essential for scene understanding tasks such as object localization and segmentation. Language-embedded scene representations have made progress by incorporating language features into 3D spaces. However, their efficacy heavily depends on neural networks that are resource-intensive in training and rendering. Although recent 3D Gaussians offer efficient and high-quality novel view synthesis, directly embedding language features in them leads to prohibitive memory usage and decreased performance. In this work, we introduce Language Embedded"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18482","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/2311.18482/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":"2311.18482","created_at":"2026-07-05T07:18:42.910824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18482v1","created_at":"2026-07-05T07:18:42.910824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18482","created_at":"2026-07-05T07:18:42.910824+00:00"},{"alias_kind":"pith_short_12","alias_value":"KG4OSIOH2EWC","created_at":"2026-07-05T07:18:42.910824+00:00"},{"alias_kind":"pith_short_16","alias_value":"KG4OSIOH2EWC7NVD","created_at":"2026-07-05T07:18:42.910824+00:00"},{"alias_kind":"pith_short_8","alias_value":"KG4OSIOH","created_at":"2026-07-05T07:18:42.910824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.22667","citing_title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08925","citing_title":"ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2602.14199","citing_title":"Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08096","citing_title":"TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08925","citing_title":"ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KG4OSIOH2EWC7NVDSRO6UMNDJQ","json":"https://pith.science/pith/KG4OSIOH2EWC7NVDSRO6UMNDJQ.json","graph_json":"https://pith.science/api/pith-number/KG4OSIOH2EWC7NVDSRO6UMNDJQ/graph.json","events_json":"https://pith.science/api/pith-number/KG4OSIOH2EWC7NVDSRO6UMNDJQ/events.json","paper":"https://pith.science/paper/KG4OSIOH"},"agent_actions":{"view_html":"https://pith.science/pith/KG4OSIOH2EWC7NVDSRO6UMNDJQ","download_json":"https://pith.science/pith/KG4OSIOH2EWC7NVDSRO6UMNDJQ.json","view_paper":"https://pith.science/paper/KG4OSIOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18482&json=true","fetch_graph":"https://pith.science/api/pith-number/KG4OSIOH2EWC7NVDSRO6UMNDJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KG4OSIOH2EWC7NVDSRO6UMNDJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KG4OSIOH2EWC7NVDSRO6UMNDJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KG4OSIOH2EWC7NVDSRO6UMNDJQ/action/storage_attestation","attest_author":"https://pith.science/pith/KG4OSIOH2EWC7NVDSRO6UMNDJQ/action/author_attestation","sign_citation":"https://pith.science/pith/KG4OSIOH2EWC7NVDSRO6UMNDJQ/action/citation_signature","submit_replication":"https://pith.science/pith/KG4OSIOH2EWC7NVDSRO6UMNDJQ/action/replication_record"}},"created_at":"2026-07-05T07:18:42.910824+00:00","updated_at":"2026-07-05T07:18:42.910824+00:00"}