{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3VZDWKKGQX7LUUZ2UYKX67HYBW","short_pith_number":"pith:3VZDWKKG","schema_version":"1.0","canonical_sha256":"dd723b294685feba533aa6157f7cf80d8281c3215f3e4bd82341f1478f8e1a2e","source":{"kind":"arxiv","id":"2410.07577","version":2},"attestation_state":"computed","paper":{"title":"3D Vision-Language Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anwesa Choudhuri, Benjamin Planche, Chen Chen, Meng Zheng, Qucheng Peng, Terrence Chen, Zhongpai Gao, Ziyan Wu","submitted_at":"2024-10-10T03:28:29Z","abstract_excerpt":"Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality. However, current multi-modal scene understanding approaches have naively embedded semantic representations into 3D reconstruction methods without striking a balance between visual and language modalities, which leads to unsatisfying semantic rasterization of translucent or reflective objects, as well as over-fitting on color modality. To alleviate these limit"},"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":"2410.07577","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T03:28:29Z","cross_cats_sorted":[],"title_canon_sha256":"622082604ce6108e7c435fdef7acdc4f235863a3582dffaf9d35e26ed12a3786","abstract_canon_sha256":"decb421e3057a783fefd0ec69669c706349791a3b9f76ca677b38db6aeca36df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:19.064851Z","signature_b64":"okCPDdgZg/3BhWYyCUEvMtA9KWAq06U+xMObLe79uDUDwZF1qvDlUk0f7EWGi5r6swROe4aVzo/vorMed043Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd723b294685feba533aa6157f7cf80d8281c3215f3e4bd82341f1478f8e1a2e","last_reissued_at":"2026-07-05T10:58:19.064322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:19.064322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Vision-Language Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anwesa Choudhuri, Benjamin Planche, Chen Chen, Meng Zheng, Qucheng Peng, Terrence Chen, Zhongpai Gao, Ziyan Wu","submitted_at":"2024-10-10T03:28:29Z","abstract_excerpt":"Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality. However, current multi-modal scene understanding approaches have naively embedded semantic representations into 3D reconstruction methods without striking a balance between visual and language modalities, which leads to unsatisfying semantic rasterization of translucent or reflective objects, as well as over-fitting on color modality. To alleviate these limit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07577","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/2410.07577/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":"2410.07577","created_at":"2026-07-05T10:58:19.064390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07577v2","created_at":"2026-07-05T10:58:19.064390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07577","created_at":"2026-07-05T10:58:19.064390+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VZDWKKGQX7L","created_at":"2026-07-05T10:58:19.064390+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VZDWKKGQX7LUUZ2","created_at":"2026-07-05T10:58:19.064390+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VZDWKKG","created_at":"2026-07-05T10:58:19.064390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01140","citing_title":"Relation-Centric Open-Vocabulary 3D Gaussian Segmentation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2601.08831","citing_title":"3AM: 3egment Anything with Geometric Consistency in Videos","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14706","citing_title":"NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21631","citing_title":"DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VZDWKKGQX7LUUZ2UYKX67HYBW","json":"https://pith.science/pith/3VZDWKKGQX7LUUZ2UYKX67HYBW.json","graph_json":"https://pith.science/api/pith-number/3VZDWKKGQX7LUUZ2UYKX67HYBW/graph.json","events_json":"https://pith.science/api/pith-number/3VZDWKKGQX7LUUZ2UYKX67HYBW/events.json","paper":"https://pith.science/paper/3VZDWKKG"},"agent_actions":{"view_html":"https://pith.science/pith/3VZDWKKGQX7LUUZ2UYKX67HYBW","download_json":"https://pith.science/pith/3VZDWKKGQX7LUUZ2UYKX67HYBW.json","view_paper":"https://pith.science/paper/3VZDWKKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07577&json=true","fetch_graph":"https://pith.science/api/pith-number/3VZDWKKGQX7LUUZ2UYKX67HYBW/graph.json","fetch_events":"https://pith.science/api/pith-number/3VZDWKKGQX7LUUZ2UYKX67HYBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VZDWKKGQX7LUUZ2UYKX67HYBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VZDWKKGQX7LUUZ2UYKX67HYBW/action/storage_attestation","attest_author":"https://pith.science/pith/3VZDWKKGQX7LUUZ2UYKX67HYBW/action/author_attestation","sign_citation":"https://pith.science/pith/3VZDWKKGQX7LUUZ2UYKX67HYBW/action/citation_signature","submit_replication":"https://pith.science/pith/3VZDWKKGQX7LUUZ2UYKX67HYBW/action/replication_record"}},"created_at":"2026-07-05T10:58:19.064390+00:00","updated_at":"2026-07-05T10:58:19.064390+00:00"}