{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RQBLXCBEL5YEL4JPGT2WQOT2RQ","short_pith_number":"pith:RQBLXCBE","schema_version":"1.0","canonical_sha256":"8c02bb88245f7045f12f34f5683a7a8c0813e423bffdca9b5943ee7fb3d3eb53","source":{"kind":"arxiv","id":"2311.17245","version":6},"attestation_state":"computed","paper":{"title":"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Kairun Wen, Kevin Wang, Zehao Zhu, Zhangyang Wang, Zhiwen Fan","submitted_at":"2023-11-28T21:39:20Z","abstract_excerpt":"Recent advances in real-time neural rendering using point-based techniques have enabled broader adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting impose substantial storage overhead, as Structure-from-Motion (SfM) points can grow to millions, often requiring gigabyte-level disk space for a single unbounded scene. This growth presents scalability challenges and hinders splatting efficiency. To address this, we introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies"},"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":"2311.17245","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T21:39:20Z","cross_cats_sorted":[],"title_canon_sha256":"c9425e564ab6a0ec21ae35784cc91870526359fa01b6a0b504514e7138170c5c","abstract_canon_sha256":"bf552516ff7b7bb87fb98a8d27305a7a4cea0bd1368b86d3268409fb7ea9b3a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:10.610414Z","signature_b64":"fQXLZDewDhZSttDy+iE3Hl2GtbiBkmdOE/1Q4CeN2XE+pE23n4HhrQyE8KXg358hnZJAZbw6s+h/MNU9m5t0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c02bb88245f7045f12f34f5683a7a8c0813e423bffdca9b5943ee7fb3d3eb53","last_reissued_at":"2026-07-05T09:34:10.609973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:10.609973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Kairun Wen, Kevin Wang, Zehao Zhu, Zhangyang Wang, Zhiwen Fan","submitted_at":"2023-11-28T21:39:20Z","abstract_excerpt":"Recent advances in real-time neural rendering using point-based techniques have enabled broader adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting impose substantial storage overhead, as Structure-from-Motion (SfM) points can grow to millions, often requiring gigabyte-level disk space for a single unbounded scene. This growth presents scalability challenges and hinders splatting efficiency. To address this, we introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17245","kind":"arxiv","version":6},"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/2311.17245/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":"2311.17245","created_at":"2026-07-05T09:34:10.610028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17245v6","created_at":"2026-07-05T09:34:10.610028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17245","created_at":"2026-07-05T09:34:10.610028+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQBLXCBEL5YE","created_at":"2026-07-05T09:34:10.610028+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQBLXCBEL5YEL4JP","created_at":"2026-07-05T09:34:10.610028+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQBLXCBE","created_at":"2026-07-05T09:34:10.610028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24796","citing_title":"Pocket-SLAM: Rendering-Area-Aware Pruning for Memory-Efficient 3DGS-SLAM","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29496","citing_title":"Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29976","citing_title":"Learning Efficient 4D Gaussian Representations from Monocular Videos with Flow Splatting","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07179","citing_title":"EvoGS: Constructing Continuous-Layered Gaussian Splatting with Evolution Tree for Scalable 3D Streaming","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2403.11247","citing_title":"Compact 3D Gaussian Splatting For Dense Visual SLAM","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13547","citing_title":"Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13482","citing_title":"Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20046","citing_title":"Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08370","citing_title":"SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQBLXCBEL5YEL4JPGT2WQOT2RQ","json":"https://pith.science/pith/RQBLXCBEL5YEL4JPGT2WQOT2RQ.json","graph_json":"https://pith.science/api/pith-number/RQBLXCBEL5YEL4JPGT2WQOT2RQ/graph.json","events_json":"https://pith.science/api/pith-number/RQBLXCBEL5YEL4JPGT2WQOT2RQ/events.json","paper":"https://pith.science/paper/RQBLXCBE"},"agent_actions":{"view_html":"https://pith.science/pith/RQBLXCBEL5YEL4JPGT2WQOT2RQ","download_json":"https://pith.science/pith/RQBLXCBEL5YEL4JPGT2WQOT2RQ.json","view_paper":"https://pith.science/paper/RQBLXCBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17245&json=true","fetch_graph":"https://pith.science/api/pith-number/RQBLXCBEL5YEL4JPGT2WQOT2RQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RQBLXCBEL5YEL4JPGT2WQOT2RQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQBLXCBEL5YEL4JPGT2WQOT2RQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQBLXCBEL5YEL4JPGT2WQOT2RQ/action/storage_attestation","attest_author":"https://pith.science/pith/RQBLXCBEL5YEL4JPGT2WQOT2RQ/action/author_attestation","sign_citation":"https://pith.science/pith/RQBLXCBEL5YEL4JPGT2WQOT2RQ/action/citation_signature","submit_replication":"https://pith.science/pith/RQBLXCBEL5YEL4JPGT2WQOT2RQ/action/replication_record"}},"created_at":"2026-07-05T09:34:10.610028+00:00","updated_at":"2026-07-05T09:34:10.610028+00:00"}