{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TSSHBSTO2F4BVXUFTV43SRZODH","short_pith_number":"pith:TSSHBSTO","schema_version":"1.0","canonical_sha256":"9ca470ca6ed1781ade859d79b9472e19fc8151eff98cb50f2ab9d070f2539958","source":{"kind":"arxiv","id":"2607.10792","version":1},"attestation_state":"computed","paper":{"title":"MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haokun Lin, Jinqian Yang, Renzhen Wang, Wanhua Li, Xiangchu Feng, Xixi Jia, Yichen Wu","submitted_at":"2026-07-12T14:50:08Z","abstract_excerpt":"Reconstructing high-fidelity 3D scenes from sparse-views remains a central problem in generalizable neural rendering. Existing generalizable 3D Gaussian Splatting (3DGS) methods often exhibit geometric artifacts in sparse-view settings, since supervision based solely on 2D photometric losses cannot resolve depth and correspondence ambiguities. To address this issue, we propose MAC-Splat, a training framework built around direct 3D consistency supervision. MAC-Splat builds on the MASt3R geometric backbone and a frozen DINOv3 encoder to obtain semantically informed 2D correspondences, which serv"},"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":"2607.10792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-12T14:50:08Z","cross_cats_sorted":[],"title_canon_sha256":"187584185727423a5ab0a460c2e2b4ce3bb237b0bba40aa3a59d011af80c9f22","abstract_canon_sha256":"440d1d4a0150575e2205ad067931e5003d5066dc5cd4e821ff3e65885b7b4e13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:40.361094Z","signature_b64":"6FQ+eV3QyjHU08+Bc+/24vvJHG+klrQeyZjQCiPsrcEa1E/f1EFH2JcCJcchQ1H4MfCAaaFdE5TlzEuwcL6xBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ca470ca6ed1781ade859d79b9472e19fc8151eff98cb50f2ab9d070f2539958","last_reissued_at":"2026-07-14T01:21:40.360273Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:40.360273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haokun Lin, Jinqian Yang, Renzhen Wang, Wanhua Li, Xiangchu Feng, Xixi Jia, Yichen Wu","submitted_at":"2026-07-12T14:50:08Z","abstract_excerpt":"Reconstructing high-fidelity 3D scenes from sparse-views remains a central problem in generalizable neural rendering. Existing generalizable 3D Gaussian Splatting (3DGS) methods often exhibit geometric artifacts in sparse-view settings, since supervision based solely on 2D photometric losses cannot resolve depth and correspondence ambiguities. To address this issue, we propose MAC-Splat, a training framework built around direct 3D consistency supervision. MAC-Splat builds on the MASt3R geometric backbone and a frozen DINOv3 encoder to obtain semantically informed 2D correspondences, which serv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10792","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/2607.10792/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":"2607.10792","created_at":"2026-07-14T01:21:40.360705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10792v1","created_at":"2026-07-14T01:21:40.360705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10792","created_at":"2026-07-14T01:21:40.360705+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSSHBSTO2F4B","created_at":"2026-07-14T01:21:40.360705+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSSHBSTO2F4BVXUF","created_at":"2026-07-14T01:21:40.360705+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSSHBSTO","created_at":"2026-07-14T01:21:40.360705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSSHBSTO2F4BVXUFTV43SRZODH","json":"https://pith.science/pith/TSSHBSTO2F4BVXUFTV43SRZODH.json","graph_json":"https://pith.science/api/pith-number/TSSHBSTO2F4BVXUFTV43SRZODH/graph.json","events_json":"https://pith.science/api/pith-number/TSSHBSTO2F4BVXUFTV43SRZODH/events.json","paper":"https://pith.science/paper/TSSHBSTO"},"agent_actions":{"view_html":"https://pith.science/pith/TSSHBSTO2F4BVXUFTV43SRZODH","download_json":"https://pith.science/pith/TSSHBSTO2F4BVXUFTV43SRZODH.json","view_paper":"https://pith.science/paper/TSSHBSTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10792&json=true","fetch_graph":"https://pith.science/api/pith-number/TSSHBSTO2F4BVXUFTV43SRZODH/graph.json","fetch_events":"https://pith.science/api/pith-number/TSSHBSTO2F4BVXUFTV43SRZODH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSSHBSTO2F4BVXUFTV43SRZODH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSSHBSTO2F4BVXUFTV43SRZODH/action/storage_attestation","attest_author":"https://pith.science/pith/TSSHBSTO2F4BVXUFTV43SRZODH/action/author_attestation","sign_citation":"https://pith.science/pith/TSSHBSTO2F4BVXUFTV43SRZODH/action/citation_signature","submit_replication":"https://pith.science/pith/TSSHBSTO2F4BVXUFTV43SRZODH/action/replication_record"}},"created_at":"2026-07-14T01:21:40.360705+00:00","updated_at":"2026-07-14T01:21:40.360705+00:00"}