{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KU5VYDYDG7BOALLXQRUTL5GXJD","short_pith_number":"pith:KU5VYDYD","schema_version":"1.0","canonical_sha256":"553b5c0f0337c2e02d77846935f4d748e388f042ee0f588163e3125e9ba332d2","source":{"kind":"arxiv","id":"2412.18608","version":2},"attestation_state":"computed","paper":{"title":"PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, David Novotny, Iro Laina, Jianyuan Wang, Minghao Chen, Roman Shapovalov, Tom Monnier","submitted_at":"2024-12-24T18:59:43Z","abstract_excerpt":"Text- or image-to-3D generators and 3D scanners can now produce 3D assets with high-quality shapes and textures. These assets typically consist of a single, fused representation, like an implicit neural field, a Gaussian mixture, or a mesh, without any useful structure. However, most applications and creative workflows require assets to be made of several meaningful parts that can be manipulated independently. To address this gap, we introduce PartGen, a novel approach that generates 3D objects composed of meaningful parts starting from text, an image, or an unstructured 3D object. First, give"},"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":"2412.18608","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"e046d8d309e1e06064672b00639396b0dd736060bf1720dfb9b57d559ee39566","abstract_canon_sha256":"fde70a7e940230628082d81d731512559a7d5fe887ec791acc06578263bdfcc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:15.743218Z","signature_b64":"xx2ODFTTIMyBibXTOKiOzJ5dkeXw58cCzMVcYPmcvrlvLlaMjtytXsDzxhxm7mC4vuOkzTW4SLUOb578KqT3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"553b5c0f0337c2e02d77846935f4d748e388f042ee0f588163e3125e9ba332d2","last_reissued_at":"2026-07-05T09:55:15.742774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:15.742774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, David Novotny, Iro Laina, Jianyuan Wang, Minghao Chen, Roman Shapovalov, Tom Monnier","submitted_at":"2024-12-24T18:59:43Z","abstract_excerpt":"Text- or image-to-3D generators and 3D scanners can now produce 3D assets with high-quality shapes and textures. These assets typically consist of a single, fused representation, like an implicit neural field, a Gaussian mixture, or a mesh, without any useful structure. However, most applications and creative workflows require assets to be made of several meaningful parts that can be manipulated independently. To address this gap, we introduce PartGen, a novel approach that generates 3D objects composed of meaningful parts starting from text, an image, or an unstructured 3D object. First, give"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18608","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/2412.18608/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":"2412.18608","created_at":"2026-07-05T09:55:15.742833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18608v2","created_at":"2026-07-05T09:55:15.742833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18608","created_at":"2026-07-05T09:55:15.742833+00:00"},{"alias_kind":"pith_short_12","alias_value":"KU5VYDYDG7BO","created_at":"2026-07-05T09:55:15.742833+00:00"},{"alias_kind":"pith_short_16","alias_value":"KU5VYDYDG7BOALLX","created_at":"2026-07-05T09:55:15.742833+00:00"},{"alias_kind":"pith_short_8","alias_value":"KU5VYDYD","created_at":"2026-07-05T09:55:15.742833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16990","citing_title":"DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KU5VYDYDG7BOALLXQRUTL5GXJD","json":"https://pith.science/pith/KU5VYDYDG7BOALLXQRUTL5GXJD.json","graph_json":"https://pith.science/api/pith-number/KU5VYDYDG7BOALLXQRUTL5GXJD/graph.json","events_json":"https://pith.science/api/pith-number/KU5VYDYDG7BOALLXQRUTL5GXJD/events.json","paper":"https://pith.science/paper/KU5VYDYD"},"agent_actions":{"view_html":"https://pith.science/pith/KU5VYDYDG7BOALLXQRUTL5GXJD","download_json":"https://pith.science/pith/KU5VYDYDG7BOALLXQRUTL5GXJD.json","view_paper":"https://pith.science/paper/KU5VYDYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18608&json=true","fetch_graph":"https://pith.science/api/pith-number/KU5VYDYDG7BOALLXQRUTL5GXJD/graph.json","fetch_events":"https://pith.science/api/pith-number/KU5VYDYDG7BOALLXQRUTL5GXJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KU5VYDYDG7BOALLXQRUTL5GXJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KU5VYDYDG7BOALLXQRUTL5GXJD/action/storage_attestation","attest_author":"https://pith.science/pith/KU5VYDYDG7BOALLXQRUTL5GXJD/action/author_attestation","sign_citation":"https://pith.science/pith/KU5VYDYDG7BOALLXQRUTL5GXJD/action/citation_signature","submit_replication":"https://pith.science/pith/KU5VYDYDG7BOALLXQRUTL5GXJD/action/replication_record"}},"created_at":"2026-07-05T09:55:15.742833+00:00","updated_at":"2026-07-05T09:55:15.742833+00:00"}