{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C3STQEWCGUOJGGTJ5D4S5C3KFT","short_pith_number":"pith:C3STQEWC","schema_version":"1.0","canonical_sha256":"16e53812c2351c931a69e8f92e8b6a2cc3c80d1b260d4d2e26f6e68f5bfa52ae","source":{"kind":"arxiv","id":"2405.18784","version":1},"attestation_state":"computed","paper":{"title":"LP-3DGS: Learning to Prune 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Peng, Deliang Fan, Li Yang, Rama Chellappa, Tianchen Song, Yongjae Lee, Zhaoliang Zhang","submitted_at":"2024-05-29T05:58:34Z","abstract_excerpt":"Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed. However, as a point-based scene representation, 3DGS potentially generates a large number of Gaussians to fit the scene, leading to high memory usage. Improvements that have been proposed require either an empirical and preset pruning ratio or importance score threshold to prune the point cloud. Such hyperparamter requires multiple rounds of training to optimize and achieve the maximum pruning ratio, while maintaining the renderi"},"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":"2405.18784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T05:58:34Z","cross_cats_sorted":[],"title_canon_sha256":"9360a4172d360ef5a89ead5c26fa641cd5e06e1e7c51b70cf4135e5ce78a216c","abstract_canon_sha256":"ebf6400c9ec41c3aae6aa0dfabecd72c0b3f5cb8e90d48cebcf77c765cd20229"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:30.205250Z","signature_b64":"UJjKgErobBJKhZUxn5pMAtRWhiLPPXyW/g0SEKkl/N4PvYw451Ke4a2W+uYbsqb8wMoAoFevVQYz8hIpQCjlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16e53812c2351c931a69e8f92e8b6a2cc3c80d1b260d4d2e26f6e68f5bfa52ae","last_reissued_at":"2026-07-05T08:24:30.204835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:30.204835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LP-3DGS: Learning to Prune 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Peng, Deliang Fan, Li Yang, Rama Chellappa, Tianchen Song, Yongjae Lee, Zhaoliang Zhang","submitted_at":"2024-05-29T05:58:34Z","abstract_excerpt":"Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed. However, as a point-based scene representation, 3DGS potentially generates a large number of Gaussians to fit the scene, leading to high memory usage. Improvements that have been proposed require either an empirical and preset pruning ratio or importance score threshold to prune the point cloud. Such hyperparamter requires multiple rounds of training to optimize and achieve the maximum pruning ratio, while maintaining the renderi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18784","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/2405.18784/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":"2405.18784","created_at":"2026-07-05T08:24:30.204898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18784v1","created_at":"2026-07-05T08:24:30.204898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18784","created_at":"2026-07-05T08:24:30.204898+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3STQEWCGUOJ","created_at":"2026-07-05T08:24:30.204898+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3STQEWCGUOJGGTJ","created_at":"2026-07-05T08:24:30.204898+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3STQEWC","created_at":"2026-07-05T08:24:30.204898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":11,"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":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3STQEWCGUOJGGTJ5D4S5C3KFT","json":"https://pith.science/pith/C3STQEWCGUOJGGTJ5D4S5C3KFT.json","graph_json":"https://pith.science/api/pith-number/C3STQEWCGUOJGGTJ5D4S5C3KFT/graph.json","events_json":"https://pith.science/api/pith-number/C3STQEWCGUOJGGTJ5D4S5C3KFT/events.json","paper":"https://pith.science/paper/C3STQEWC"},"agent_actions":{"view_html":"https://pith.science/pith/C3STQEWCGUOJGGTJ5D4S5C3KFT","download_json":"https://pith.science/pith/C3STQEWCGUOJGGTJ5D4S5C3KFT.json","view_paper":"https://pith.science/paper/C3STQEWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18784&json=true","fetch_graph":"https://pith.science/api/pith-number/C3STQEWCGUOJGGTJ5D4S5C3KFT/graph.json","fetch_events":"https://pith.science/api/pith-number/C3STQEWCGUOJGGTJ5D4S5C3KFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3STQEWCGUOJGGTJ5D4S5C3KFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3STQEWCGUOJGGTJ5D4S5C3KFT/action/storage_attestation","attest_author":"https://pith.science/pith/C3STQEWCGUOJGGTJ5D4S5C3KFT/action/author_attestation","sign_citation":"https://pith.science/pith/C3STQEWCGUOJGGTJ5D4S5C3KFT/action/citation_signature","submit_replication":"https://pith.science/pith/C3STQEWCGUOJGGTJ5D4S5C3KFT/action/replication_record"}},"created_at":"2026-07-05T08:24:30.204898+00:00","updated_at":"2026-07-05T08:24:30.204898+00:00"}