{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WX6JVTFUXG3USB3O36EZZHNHGS","short_pith_number":"pith:WX6JVTFU","schema_version":"1.0","canonical_sha256":"b5fc9accb4b9b749076edf899c9da73485b01a7a43b717f1db305f014c8a3e1a","source":{"kind":"arxiv","id":"2512.05354","version":2},"attestation_state":"computed","paper":{"title":"SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Gordon Wetzstein, Hao Tan, Kai Zhang, Leonidas Guibas, Peng Wang, Wang Yifan, Yang Zheng","submitted_at":"2025-12-05T01:42:22Z","abstract_excerpt":"The rise of 3D Gaussian Splatting has revolutionized photorealistic 3D asset creation, yet a critical gap remains for their interactive refinement and editing. Existing approaches based on diffusion or optimization are ill-suited for this task, as they are often prohibitively slow, destructive to the original asset's identity, or lack the precision for fine-grained control. To address this, we introduce SplatPainter, a state-aware feedforward model that enables continuous editing of 3D Gaussian assets from user-provided 2D view(s). Our method directly predicts updates to the attributes of a co"},"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":"2512.05354","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-05T01:42:22Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"0dda156c79af35fbd20f0df0829f6a2c291b4be57185a7e71f198aaf3d33706d","abstract_canon_sha256":"c3c3bbe7f529a22790107316b42fe1388224a9d3af61f70e85c8263c09a28ab7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:12.008672Z","signature_b64":"XvGw76zxfJjPEGjvE3vqfwh3QuFR3GimY1UA5T0q2cN9lxyY2UoF0L/wQXBQPZCYMg/RtZwEgIGJpcUayQa7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5fc9accb4b9b749076edf899c9da73485b01a7a43b717f1db305f014c8a3e1a","last_reissued_at":"2026-06-25T00:18:12.008222Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:12.008222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Gordon Wetzstein, Hao Tan, Kai Zhang, Leonidas Guibas, Peng Wang, Wang Yifan, Yang Zheng","submitted_at":"2025-12-05T01:42:22Z","abstract_excerpt":"The rise of 3D Gaussian Splatting has revolutionized photorealistic 3D asset creation, yet a critical gap remains for their interactive refinement and editing. Existing approaches based on diffusion or optimization are ill-suited for this task, as they are often prohibitively slow, destructive to the original asset's identity, or lack the precision for fine-grained control. To address this, we introduce SplatPainter, a state-aware feedforward model that enables continuous editing of 3D Gaussian assets from user-provided 2D view(s). Our method directly predicts updates to the attributes of a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.05354","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/2512.05354/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":"2512.05354","created_at":"2026-06-25T00:18:12.008279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.05354v2","created_at":"2026-06-25T00:18:12.008279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.05354","created_at":"2026-06-25T00:18:12.008279+00:00"},{"alias_kind":"pith_short_12","alias_value":"WX6JVTFUXG3U","created_at":"2026-06-25T00:18:12.008279+00:00"},{"alias_kind":"pith_short_16","alias_value":"WX6JVTFUXG3USB3O","created_at":"2026-06-25T00:18:12.008279+00:00"},{"alias_kind":"pith_short_8","alias_value":"WX6JVTFU","created_at":"2026-06-25T00:18:12.008279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2602.04349","citing_title":"VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02883","citing_title":"Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervision","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WX6JVTFUXG3USB3O36EZZHNHGS","json":"https://pith.science/pith/WX6JVTFUXG3USB3O36EZZHNHGS.json","graph_json":"https://pith.science/api/pith-number/WX6JVTFUXG3USB3O36EZZHNHGS/graph.json","events_json":"https://pith.science/api/pith-number/WX6JVTFUXG3USB3O36EZZHNHGS/events.json","paper":"https://pith.science/paper/WX6JVTFU"},"agent_actions":{"view_html":"https://pith.science/pith/WX6JVTFUXG3USB3O36EZZHNHGS","download_json":"https://pith.science/pith/WX6JVTFUXG3USB3O36EZZHNHGS.json","view_paper":"https://pith.science/paper/WX6JVTFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.05354&json=true","fetch_graph":"https://pith.science/api/pith-number/WX6JVTFUXG3USB3O36EZZHNHGS/graph.json","fetch_events":"https://pith.science/api/pith-number/WX6JVTFUXG3USB3O36EZZHNHGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WX6JVTFUXG3USB3O36EZZHNHGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WX6JVTFUXG3USB3O36EZZHNHGS/action/storage_attestation","attest_author":"https://pith.science/pith/WX6JVTFUXG3USB3O36EZZHNHGS/action/author_attestation","sign_citation":"https://pith.science/pith/WX6JVTFUXG3USB3O36EZZHNHGS/action/citation_signature","submit_replication":"https://pith.science/pith/WX6JVTFUXG3USB3O36EZZHNHGS/action/replication_record"}},"created_at":"2026-06-25T00:18:12.008279+00:00","updated_at":"2026-06-25T00:18:12.008279+00:00"}