{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CSEYX2WFIB7P4EA3NASH2KGZD7","short_pith_number":"pith:CSEYX2WF","schema_version":"1.0","canonical_sha256":"14898beac5407efe101b68247d28d91fd1b50d30e41a1c26ecd607e99f810a8a","source":{"kind":"arxiv","id":"2507.13346","version":2},"attestation_state":"computed","paper":{"title":"AutoPartGen: Autogressive 3D Part Generation and Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Dilin Wang, Hyunyoung Jung, Iro Laina, Jianyuan Wang, Minghao Chen, Rakesh Ranjan, Roman Shapovalov, Tom Monnier","submitted_at":"2025-07-17T17:59:47Z","abstract_excerpt":"We introduce AutoPartGen, a model that generates objects composed of 3D parts in an autoregressive manner. This model can take as input an image of an object, 2D masks of the object's parts, or an existing 3D object, and generate a corresponding compositional 3D reconstruction. Our approach builds upon 3DShape2VecSet, a recent latent 3D representation with powerful geometric expressiveness. We observe that this latent space exhibits strong compositional properties, making it particularly well-suited for part-based generation tasks. Specifically, AutoPartGen generates object parts autoregressiv"},"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":"2507.13346","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-17T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"ab9be2507b09d158c890454f720ec153808cf49420f6a7b9954e99c16e510302","abstract_canon_sha256":"0306f90e54dfdb6e685621a2dccb94547aeb9d4dd3b339a8bc71866c6b8f76c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:01.895911Z","signature_b64":"Iw4/sfhrvJcxGUBbjmcu3dtldauCFWygDY0lY4+7cmxKaSXEhVjKqcJyLUDI3F9Q4fdJTjfNyhbTtZiPXBf5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14898beac5407efe101b68247d28d91fd1b50d30e41a1c26ecd607e99f810a8a","last_reissued_at":"2026-07-05T11:40:01.895341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:01.895341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoPartGen: Autogressive 3D Part Generation and Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Dilin Wang, Hyunyoung Jung, Iro Laina, Jianyuan Wang, Minghao Chen, Rakesh Ranjan, Roman Shapovalov, Tom Monnier","submitted_at":"2025-07-17T17:59:47Z","abstract_excerpt":"We introduce AutoPartGen, a model that generates objects composed of 3D parts in an autoregressive manner. This model can take as input an image of an object, 2D masks of the object's parts, or an existing 3D object, and generate a corresponding compositional 3D reconstruction. Our approach builds upon 3DShape2VecSet, a recent latent 3D representation with powerful geometric expressiveness. We observe that this latent space exhibits strong compositional properties, making it particularly well-suited for part-based generation tasks. Specifically, AutoPartGen generates object parts autoregressiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13346","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/2507.13346/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":"2507.13346","created_at":"2026-07-05T11:40:01.895405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13346v2","created_at":"2026-07-05T11:40:01.895405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13346","created_at":"2026-07-05T11:40:01.895405+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSEYX2WFIB7P","created_at":"2026-07-05T11:40:01.895405+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSEYX2WFIB7P4EA3","created_at":"2026-07-05T11:40:01.895405+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSEYX2WF","created_at":"2026-07-05T11:40:01.895405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12099","citing_title":"ISAP-3D: Identity-Slot Aligned Part-Aware 3D Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18801","citing_title":"PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14671","citing_title":"ART: Articulated Reconstruction Transformer","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28134","citing_title":"MeshReGen: A Unified 3D Geometry Regeneration Framework","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13862","citing_title":"Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28134","citing_title":"MeshReGen: A Unified 3D Geometry Regeneration Framework","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CSEYX2WFIB7P4EA3NASH2KGZD7","json":"https://pith.science/pith/CSEYX2WFIB7P4EA3NASH2KGZD7.json","graph_json":"https://pith.science/api/pith-number/CSEYX2WFIB7P4EA3NASH2KGZD7/graph.json","events_json":"https://pith.science/api/pith-number/CSEYX2WFIB7P4EA3NASH2KGZD7/events.json","paper":"https://pith.science/paper/CSEYX2WF"},"agent_actions":{"view_html":"https://pith.science/pith/CSEYX2WFIB7P4EA3NASH2KGZD7","download_json":"https://pith.science/pith/CSEYX2WFIB7P4EA3NASH2KGZD7.json","view_paper":"https://pith.science/paper/CSEYX2WF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13346&json=true","fetch_graph":"https://pith.science/api/pith-number/CSEYX2WFIB7P4EA3NASH2KGZD7/graph.json","fetch_events":"https://pith.science/api/pith-number/CSEYX2WFIB7P4EA3NASH2KGZD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSEYX2WFIB7P4EA3NASH2KGZD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSEYX2WFIB7P4EA3NASH2KGZD7/action/storage_attestation","attest_author":"https://pith.science/pith/CSEYX2WFIB7P4EA3NASH2KGZD7/action/author_attestation","sign_citation":"https://pith.science/pith/CSEYX2WFIB7P4EA3NASH2KGZD7/action/citation_signature","submit_replication":"https://pith.science/pith/CSEYX2WFIB7P4EA3NASH2KGZD7/action/replication_record"}},"created_at":"2026-07-05T11:40:01.895405+00:00","updated_at":"2026-07-05T11:40:01.895405+00:00"}