{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DGHQFQJB3HH5PSBMR32CAODHXK","short_pith_number":"pith:DGHQFQJB","schema_version":"1.0","canonical_sha256":"198f02c121d9cfd7c82c8ef4203867ba891c3a2b6d07986e37287ee1af04e33c","source":{"kind":"arxiv","id":"2508.08252","version":1},"attestation_state":"computed","paper":{"title":"ReferSplat: Referring Segmentation in 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changshuo Wang, Guanbin Li, Guangquan Jie, Henghui Ding, Shuming Hu, Shuting He, Yun Zhou","submitted_at":"2025-08-11T17:59:30Z","abstract_excerpt":"We introduce Referring 3D Gaussian Splatting Segmentation (R3DGS), a new task that aims to segment target objects in a 3D Gaussian scene based on natural language descriptions, which often contain spatial relationships or object attributes. This task requires the model to identify newly described objects that may be occluded or not directly visible in a novel view, posing a significant challenge for 3D multi-modal understanding. Developing this capability is crucial for advancing embodied AI. To support research in this area, we construct the first R3DGS dataset, Ref-LERF. Our analysis reveals"},"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":"2508.08252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T17:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"61b2968860e183798f7cad1889d6779165b799225cf4d325bef11153ab7a2190","abstract_canon_sha256":"909f4c520029e21a8a68b526ec1038214b03e2dd545e4226e4c5a82a4a91d22b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:10.358955Z","signature_b64":"DRPzogDF9tttkOprJtisRnmB6OH8fJ+PJ1H0jzzHZxUbzXpEcAD7bL+jG1BnubT7ESsKcKfLm28E2cTYs/jXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"198f02c121d9cfd7c82c8ef4203867ba891c3a2b6d07986e37287ee1af04e33c","last_reissued_at":"2026-07-05T11:52:10.358335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:10.358335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReferSplat: Referring Segmentation in 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changshuo Wang, Guanbin Li, Guangquan Jie, Henghui Ding, Shuming Hu, Shuting He, Yun Zhou","submitted_at":"2025-08-11T17:59:30Z","abstract_excerpt":"We introduce Referring 3D Gaussian Splatting Segmentation (R3DGS), a new task that aims to segment target objects in a 3D Gaussian scene based on natural language descriptions, which often contain spatial relationships or object attributes. This task requires the model to identify newly described objects that may be occluded or not directly visible in a novel view, posing a significant challenge for 3D multi-modal understanding. Developing this capability is crucial for advancing embodied AI. To support research in this area, we construct the first R3DGS dataset, Ref-LERF. Our analysis reveals"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08252","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/2508.08252/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":"2508.08252","created_at":"2026-07-05T11:52:10.358425+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08252v1","created_at":"2026-07-05T11:52:10.358425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08252","created_at":"2026-07-05T11:52:10.358425+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGHQFQJB3HH5","created_at":"2026-07-05T11:52:10.358425+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGHQFQJB3HH5PSBM","created_at":"2026-07-05T11:52:10.358425+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGHQFQJB","created_at":"2026-07-05T11:52:10.358425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31533","citing_title":"MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30638","citing_title":"Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08096","citing_title":"TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26238","citing_title":"EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05638","citing_title":"PanopticQuery: Unified Query-Time Reasoning for 4D Scenes","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGHQFQJB3HH5PSBMR32CAODHXK","json":"https://pith.science/pith/DGHQFQJB3HH5PSBMR32CAODHXK.json","graph_json":"https://pith.science/api/pith-number/DGHQFQJB3HH5PSBMR32CAODHXK/graph.json","events_json":"https://pith.science/api/pith-number/DGHQFQJB3HH5PSBMR32CAODHXK/events.json","paper":"https://pith.science/paper/DGHQFQJB"},"agent_actions":{"view_html":"https://pith.science/pith/DGHQFQJB3HH5PSBMR32CAODHXK","download_json":"https://pith.science/pith/DGHQFQJB3HH5PSBMR32CAODHXK.json","view_paper":"https://pith.science/paper/DGHQFQJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08252&json=true","fetch_graph":"https://pith.science/api/pith-number/DGHQFQJB3HH5PSBMR32CAODHXK/graph.json","fetch_events":"https://pith.science/api/pith-number/DGHQFQJB3HH5PSBMR32CAODHXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGHQFQJB3HH5PSBMR32CAODHXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGHQFQJB3HH5PSBMR32CAODHXK/action/storage_attestation","attest_author":"https://pith.science/pith/DGHQFQJB3HH5PSBMR32CAODHXK/action/author_attestation","sign_citation":"https://pith.science/pith/DGHQFQJB3HH5PSBMR32CAODHXK/action/citation_signature","submit_replication":"https://pith.science/pith/DGHQFQJB3HH5PSBMR32CAODHXK/action/replication_record"}},"created_at":"2026-07-05T11:52:10.358425+00:00","updated_at":"2026-07-05T11:52:10.358425+00:00"}