{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:INGGJS77WF4CTAISAPWPGF6O5H","short_pith_number":"pith:INGGJS77","schema_version":"1.0","canonical_sha256":"434c64cbffb17829811203ecf317cee9c8ccf8a40c46ef31411e186886e63198","source":{"kind":"arxiv","id":"2508.02408","version":2},"attestation_state":"computed","paper":{"title":"GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Fuquan Wang, Kuan Shen, Tongtong Jin, Wang Liao, Yangpu Ma, Yikuang Yuluo, Yue Ma","submitted_at":"2025-08-04T13:31:42Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as a promising approach for CT reconstruction. However, existing methods rely on the average gradient magnitude of points within the view, often leading to severe needle-like artifacts under sparse-view conditions. To address this challenge, we propose GR-Gaussian, a graph-based 3D Gaussian Splatting framework that suppresses needle-like artifacts and improves reconstruction accuracy under sparse-view conditions. Our framework introduces two key innovations: (1) a Denoised Point Cloud Initialization Strategy that reduces initialization errors and accele"},"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":"2508.02408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-08-04T13:31:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f6954096faede151e31b0f7256f319b3659da025eaef7ec0bc7b31fdaa90653c","abstract_canon_sha256":"c38d06cf8ababf88f6bc7f09a3187b0498c5beb4606dc7e41830a0a5b3976371"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:34.486968Z","signature_b64":"rS33B2liUbeRbXyRdWZcJ8JoxW7RiIhfVrUNuPbZYhwJQ5Tj8C83ktVLV47dCm95pi/KPayZIz7pBSqnzrKmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"434c64cbffb17829811203ecf317cee9c8ccf8a40c46ef31411e186886e63198","last_reissued_at":"2026-07-05T11:49:34.486509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:34.486509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Fuquan Wang, Kuan Shen, Tongtong Jin, Wang Liao, Yangpu Ma, Yikuang Yuluo, Yue Ma","submitted_at":"2025-08-04T13:31:42Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as a promising approach for CT reconstruction. However, existing methods rely on the average gradient magnitude of points within the view, often leading to severe needle-like artifacts under sparse-view conditions. To address this challenge, we propose GR-Gaussian, a graph-based 3D Gaussian Splatting framework that suppresses needle-like artifacts and improves reconstruction accuracy under sparse-view conditions. Our framework introduces two key innovations: (1) a Denoised Point Cloud Initialization Strategy that reduces initialization errors and accele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02408","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/2508.02408/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":"2508.02408","created_at":"2026-07-05T11:49:34.486565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02408v2","created_at":"2026-07-05T11:49:34.486565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02408","created_at":"2026-07-05T11:49:34.486565+00:00"},{"alias_kind":"pith_short_12","alias_value":"INGGJS77WF4C","created_at":"2026-07-05T11:49:34.486565+00:00"},{"alias_kind":"pith_short_16","alias_value":"INGGJS77WF4CTAIS","created_at":"2026-07-05T11:49:34.486565+00:00"},{"alias_kind":"pith_short_8","alias_value":"INGGJS77","created_at":"2026-07-05T11:49:34.486565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06779","citing_title":"URS-Stereo: Uncertainty-Guided Residual Search for Real-Time Stereo Matching","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22525","citing_title":"Projection-Volume Fidelity Divergence: Diagnosing and Controlling Optimization Drift in Sparse-View 3D Gaussian Tomography","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06039","citing_title":"Texture-preserving implicit neural representation for Cone beam CT truncated reconstruction","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INGGJS77WF4CTAISAPWPGF6O5H","json":"https://pith.science/pith/INGGJS77WF4CTAISAPWPGF6O5H.json","graph_json":"https://pith.science/api/pith-number/INGGJS77WF4CTAISAPWPGF6O5H/graph.json","events_json":"https://pith.science/api/pith-number/INGGJS77WF4CTAISAPWPGF6O5H/events.json","paper":"https://pith.science/paper/INGGJS77"},"agent_actions":{"view_html":"https://pith.science/pith/INGGJS77WF4CTAISAPWPGF6O5H","download_json":"https://pith.science/pith/INGGJS77WF4CTAISAPWPGF6O5H.json","view_paper":"https://pith.science/paper/INGGJS77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02408&json=true","fetch_graph":"https://pith.science/api/pith-number/INGGJS77WF4CTAISAPWPGF6O5H/graph.json","fetch_events":"https://pith.science/api/pith-number/INGGJS77WF4CTAISAPWPGF6O5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INGGJS77WF4CTAISAPWPGF6O5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INGGJS77WF4CTAISAPWPGF6O5H/action/storage_attestation","attest_author":"https://pith.science/pith/INGGJS77WF4CTAISAPWPGF6O5H/action/author_attestation","sign_citation":"https://pith.science/pith/INGGJS77WF4CTAISAPWPGF6O5H/action/citation_signature","submit_replication":"https://pith.science/pith/INGGJS77WF4CTAISAPWPGF6O5H/action/replication_record"}},"created_at":"2026-07-05T11:49:34.486565+00:00","updated_at":"2026-07-05T11:49:34.486565+00:00"}