{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IUFCKEJIYQTGMPSAZ3BESX2H32","short_pith_number":"pith:IUFCKEJI","schema_version":"1.0","canonical_sha256":"450a251128c426663e40cec2495f47dea4588d43ee13ca6995b9c1a644757d2a","source":{"kind":"arxiv","id":"2505.24746","version":1},"attestation_state":"computed","paper":{"title":"Tackling View-Dependent Semantics in 3D Language Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsong Wen, Jiazhong Cen, Jiemin Fang, Lingxi Xie, Qi Tian, Wei Shen, Xiaopeng Zhang, XuDong Zhou","submitted_at":"2025-05-30T16:06:32Z","abstract_excerpt":"Recent advancements in 3D Gaussian Splatting (3D-GS) enable high-quality 3D scene reconstruction from RGB images. Many studies extend this paradigm for language-driven open-vocabulary scene understanding. However, most of them simply project 2D semantic features onto 3D Gaussians and overlook a fundamental gap between 2D and 3D understanding: a 3D object may exhibit various semantics from different viewpoints--a phenomenon we term view-dependent semantics. To address this challenge, we propose LaGa (Language Gaussians), which establishes cross-view semantic connections by decomposing the 3D sc"},"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":"2505.24746","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T16:06:32Z","cross_cats_sorted":[],"title_canon_sha256":"f486c1757bdd65bb898cd07b97bde141662333260a4271798dab2f9ae4fa718f","abstract_canon_sha256":"36af68e92b335a0d8dfeb1ec1111582a6534a54fbd33f44fb821e749313e8960"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:55.990485Z","signature_b64":"8b7pf8l3ezXaka6qZXWGjHdbDOFuwmylsQqc1cYF+pvq4gg1VWxHQvdLGiNazQ74rg11p+IAy6JCy9AHAOjFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"450a251128c426663e40cec2495f47dea4588d43ee13ca6995b9c1a644757d2a","last_reissued_at":"2026-07-05T11:12:55.989906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:55.989906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tackling View-Dependent Semantics in 3D Language Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsong Wen, Jiazhong Cen, Jiemin Fang, Lingxi Xie, Qi Tian, Wei Shen, Xiaopeng Zhang, XuDong Zhou","submitted_at":"2025-05-30T16:06:32Z","abstract_excerpt":"Recent advancements in 3D Gaussian Splatting (3D-GS) enable high-quality 3D scene reconstruction from RGB images. Many studies extend this paradigm for language-driven open-vocabulary scene understanding. However, most of them simply project 2D semantic features onto 3D Gaussians and overlook a fundamental gap between 2D and 3D understanding: a 3D object may exhibit various semantics from different viewpoints--a phenomenon we term view-dependent semantics. To address this challenge, we propose LaGa (Language Gaussians), which establishes cross-view semantic connections by decomposing the 3D sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24746","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/2505.24746/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":"2505.24746","created_at":"2026-07-05T11:12:55.989972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24746v1","created_at":"2026-07-05T11:12:55.989972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24746","created_at":"2026-07-05T11:12:55.989972+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUFCKEJIYQTG","created_at":"2026-07-05T11:12:55.989972+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUFCKEJIYQTGMPSA","created_at":"2026-07-05T11:12:55.989972+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUFCKEJI","created_at":"2026-07-05T11:12:55.989972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30638","citing_title":"Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26238","citing_title":"EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUFCKEJIYQTGMPSAZ3BESX2H32","json":"https://pith.science/pith/IUFCKEJIYQTGMPSAZ3BESX2H32.json","graph_json":"https://pith.science/api/pith-number/IUFCKEJIYQTGMPSAZ3BESX2H32/graph.json","events_json":"https://pith.science/api/pith-number/IUFCKEJIYQTGMPSAZ3BESX2H32/events.json","paper":"https://pith.science/paper/IUFCKEJI"},"agent_actions":{"view_html":"https://pith.science/pith/IUFCKEJIYQTGMPSAZ3BESX2H32","download_json":"https://pith.science/pith/IUFCKEJIYQTGMPSAZ3BESX2H32.json","view_paper":"https://pith.science/paper/IUFCKEJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24746&json=true","fetch_graph":"https://pith.science/api/pith-number/IUFCKEJIYQTGMPSAZ3BESX2H32/graph.json","fetch_events":"https://pith.science/api/pith-number/IUFCKEJIYQTGMPSAZ3BESX2H32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUFCKEJIYQTGMPSAZ3BESX2H32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUFCKEJIYQTGMPSAZ3BESX2H32/action/storage_attestation","attest_author":"https://pith.science/pith/IUFCKEJIYQTGMPSAZ3BESX2H32/action/author_attestation","sign_citation":"https://pith.science/pith/IUFCKEJIYQTGMPSAZ3BESX2H32/action/citation_signature","submit_replication":"https://pith.science/pith/IUFCKEJIYQTGMPSAZ3BESX2H32/action/replication_record"}},"created_at":"2026-07-05T11:12:55.989972+00:00","updated_at":"2026-07-05T11:12:55.989972+00:00"}