{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6UAS3F34HUXKT5ZQ7QZRO2HLIM","short_pith_number":"pith:6UAS3F34","schema_version":"1.0","canonical_sha256":"f5012d977c3d2ea9f730fc331768eb43306586c5110ab58091df6d2a6c1a9708","source":{"kind":"arxiv","id":"2509.24421","version":5},"attestation_state":"computed","paper":{"title":"Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Dingwen Zhang, Li Jingfeng, Xiao Sun, Yanci Zhang, Yifei Liu, Yuanyuan Gao, Yuning Gong, Zhihang Zhong","submitted_at":"2025-09-29T08:10:07Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as an efficient approach for achieving photorealistic rendering. Recent MLP-based variants further improve visual fidelity but introduce substantial decoding overhead during rendering. To alleviate computation cost, several pruning strategies and level-of-detail (LOD) techniques have been introduced, aiming to effectively reduce the number of Gaussian primitives in large-scale scenes. However, our analysis reveals that significant redundancy still remains due to the lack of occlusion awareness. In this work, we propose Proxy-GS, a novel pipeline that ex"},"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":"2509.24421","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-29T08:10:07Z","cross_cats_sorted":[],"title_canon_sha256":"0ba5d30fb47f63c7d56205451702b69eff2fe8681970ce41ffd2990d71898066","abstract_canon_sha256":"97d82186f8d3ee91f9ff4329dbf28853c4328aa4afbc7f8e52f46f0083f0d641"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:11.086304Z","signature_b64":"npa91+KUJEgtmZ/U/yjAsggO0zfw6RCDlhBG8vy2m7AMaxruzyD/Ct3KkQtfujlLK2wnOTxFAjOIgW1H3B5sBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5012d977c3d2ea9f730fc331768eb43306586c5110ab58091df6d2a6c1a9708","last_reissued_at":"2026-07-01T01:17:11.085712Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:11.085712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Dingwen Zhang, Li Jingfeng, Xiao Sun, Yanci Zhang, Yifei Liu, Yuanyuan Gao, Yuning Gong, Zhihang Zhong","submitted_at":"2025-09-29T08:10:07Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as an efficient approach for achieving photorealistic rendering. Recent MLP-based variants further improve visual fidelity but introduce substantial decoding overhead during rendering. To alleviate computation cost, several pruning strategies and level-of-detail (LOD) techniques have been introduced, aiming to effectively reduce the number of Gaussian primitives in large-scale scenes. However, our analysis reveals that significant redundancy still remains due to the lack of occlusion awareness. In this work, we propose Proxy-GS, a novel pipeline that ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.24421","kind":"arxiv","version":5},"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/2509.24421/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":"2509.24421","created_at":"2026-07-01T01:17:11.085793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.24421v5","created_at":"2026-07-01T01:17:11.085793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24421","created_at":"2026-07-01T01:17:11.085793+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UAS3F34HUXK","created_at":"2026-07-01T01:17:11.085793+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UAS3F34HUXKT5ZQ","created_at":"2026-07-01T01:17:11.085793+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UAS3F34","created_at":"2026-07-01T01:17:11.085793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.22536","citing_title":"SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22536","citing_title":"SpaceDG: Benchmarking Spatial Intelligence under Visual Degradation","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6UAS3F34HUXKT5ZQ7QZRO2HLIM","json":"https://pith.science/pith/6UAS3F34HUXKT5ZQ7QZRO2HLIM.json","graph_json":"https://pith.science/api/pith-number/6UAS3F34HUXKT5ZQ7QZRO2HLIM/graph.json","events_json":"https://pith.science/api/pith-number/6UAS3F34HUXKT5ZQ7QZRO2HLIM/events.json","paper":"https://pith.science/paper/6UAS3F34"},"agent_actions":{"view_html":"https://pith.science/pith/6UAS3F34HUXKT5ZQ7QZRO2HLIM","download_json":"https://pith.science/pith/6UAS3F34HUXKT5ZQ7QZRO2HLIM.json","view_paper":"https://pith.science/paper/6UAS3F34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.24421&json=true","fetch_graph":"https://pith.science/api/pith-number/6UAS3F34HUXKT5ZQ7QZRO2HLIM/graph.json","fetch_events":"https://pith.science/api/pith-number/6UAS3F34HUXKT5ZQ7QZRO2HLIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UAS3F34HUXKT5ZQ7QZRO2HLIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UAS3F34HUXKT5ZQ7QZRO2HLIM/action/storage_attestation","attest_author":"https://pith.science/pith/6UAS3F34HUXKT5ZQ7QZRO2HLIM/action/author_attestation","sign_citation":"https://pith.science/pith/6UAS3F34HUXKT5ZQ7QZRO2HLIM/action/citation_signature","submit_replication":"https://pith.science/pith/6UAS3F34HUXKT5ZQ7QZRO2HLIM/action/replication_record"}},"created_at":"2026-07-01T01:17:11.085793+00:00","updated_at":"2026-07-01T01:17:11.085793+00:00"}