{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KGLBDZPINQCQUJZWLKA7QOPUJO","short_pith_number":"pith:KGLBDZPI","schema_version":"1.0","canonical_sha256":"519611e5e86c050a27365a81f839f44b9dd561072c298c5474f17571812dd833","source":{"kind":"arxiv","id":"2512.17547","version":2},"attestation_state":"computed","paper":{"title":"G3Splat: Geometrically Consistent Generalizable Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ian Reid, Mehdi Hosseinzadeh, Ravi Garg, Shin-Fang Chng, Simon Lucey, Yi Xu","submitted_at":"2025-12-19T13:11:55Z","abstract_excerpt":"3D Gaussians have become a powerful scene representation for real-time splatting and high-quality novel-view synthesis. This has motivated generalizable splatting -- methods that adapt feed-forward geometry prediction networks to produce per-pixel Gaussians from a set of images. However, most generalizable splatting pipelines are supervised primarily through a view-synthesis loss to predict Gaussian orientation, anisotropic scale, opacity, and appearance in addition to their locations. We show that this learning objective is under-constrained. Models trained with view synthesis alone produce s"},"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":"2512.17547","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-19T13:11:55Z","cross_cats_sorted":[],"title_canon_sha256":"8a95eb85039da3b4fafb72a4da550df573fbe3591e1608c12cbbb4adf2bb6ff2","abstract_canon_sha256":"0744ad3ef9afd96ba0d21634b6a67f4aae9db36ed47669206465370a57af0a0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:43.878650Z","signature_b64":"P6UaRCRfkwx1TwipjLLfdIVajVfS5lkWPR4kMD4XiR7QbMiNfPdsaKKhwZ5qTeGASmOKDE58fxrRk1u+aZ4aAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"519611e5e86c050a27365a81f839f44b9dd561072c298c5474f17571812dd833","last_reissued_at":"2026-07-07T02:19:43.877726Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:43.877726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"G3Splat: Geometrically Consistent Generalizable Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ian Reid, Mehdi Hosseinzadeh, Ravi Garg, Shin-Fang Chng, Simon Lucey, Yi Xu","submitted_at":"2025-12-19T13:11:55Z","abstract_excerpt":"3D Gaussians have become a powerful scene representation for real-time splatting and high-quality novel-view synthesis. This has motivated generalizable splatting -- methods that adapt feed-forward geometry prediction networks to produce per-pixel Gaussians from a set of images. However, most generalizable splatting pipelines are supervised primarily through a view-synthesis loss to predict Gaussian orientation, anisotropic scale, opacity, and appearance in addition to their locations. We show that this learning objective is under-constrained. Models trained with view synthesis alone produce s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.17547","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/2512.17547/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":"2512.17547","created_at":"2026-07-07T02:19:43.877836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.17547v2","created_at":"2026-07-07T02:19:43.877836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.17547","created_at":"2026-07-07T02:19:43.877836+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGLBDZPINQCQ","created_at":"2026-07-07T02:19:43.877836+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGLBDZPINQCQUJZW","created_at":"2026-07-07T02:19:43.877836+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGLBDZPI","created_at":"2026-07-07T02:19:43.877836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.19019","citing_title":"FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12942","citing_title":"RMGS-SLAM: Real-time Multi-sensor Gaussian Splatting SLAM","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13416","citing_title":"DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGLBDZPINQCQUJZWLKA7QOPUJO","json":"https://pith.science/pith/KGLBDZPINQCQUJZWLKA7QOPUJO.json","graph_json":"https://pith.science/api/pith-number/KGLBDZPINQCQUJZWLKA7QOPUJO/graph.json","events_json":"https://pith.science/api/pith-number/KGLBDZPINQCQUJZWLKA7QOPUJO/events.json","paper":"https://pith.science/paper/KGLBDZPI"},"agent_actions":{"view_html":"https://pith.science/pith/KGLBDZPINQCQUJZWLKA7QOPUJO","download_json":"https://pith.science/pith/KGLBDZPINQCQUJZWLKA7QOPUJO.json","view_paper":"https://pith.science/paper/KGLBDZPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.17547&json=true","fetch_graph":"https://pith.science/api/pith-number/KGLBDZPINQCQUJZWLKA7QOPUJO/graph.json","fetch_events":"https://pith.science/api/pith-number/KGLBDZPINQCQUJZWLKA7QOPUJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGLBDZPINQCQUJZWLKA7QOPUJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGLBDZPINQCQUJZWLKA7QOPUJO/action/storage_attestation","attest_author":"https://pith.science/pith/KGLBDZPINQCQUJZWLKA7QOPUJO/action/author_attestation","sign_citation":"https://pith.science/pith/KGLBDZPINQCQUJZWLKA7QOPUJO/action/citation_signature","submit_replication":"https://pith.science/pith/KGLBDZPINQCQUJZWLKA7QOPUJO/action/replication_record"}},"created_at":"2026-07-07T02:19:43.877836+00:00","updated_at":"2026-07-07T02:19:43.877836+00:00"}