{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MJW2W2HLLMCOU3GSKLULPZPKLN","short_pith_number":"pith:MJW2W2HL","schema_version":"1.0","canonical_sha256":"626dab68eb5b04ea6cd252e8b7e5ea5b765a5263437b927bba7e86169accce76","source":{"kind":"arxiv","id":"2404.06780","version":1},"attestation_state":"computed","paper":{"title":"Urban Architect: Steerable 3D Urban Scene Generation with Layout Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjun Jiang, Fan Lu, Guang Chen, Hongsheng Li, Kwan-Yee Lin, Yan Xu","submitted_at":"2024-04-10T06:41:30Z","abstract_excerpt":"Text-to-3D generation has achieved remarkable success via large-scale text-to-image diffusion models. Nevertheless, there is no paradigm for scaling up the methodology to urban scale. Urban scenes, characterized by numerous elements, intricate arrangement relationships, and vast scale, present a formidable barrier to the interpretability of ambiguous textual descriptions for effective model optimization. In this work, we surmount the limitations by introducing a compositional 3D layout representation into text-to-3D paradigm, serving as an additional prior. It comprises a set of semantic primi"},"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":"2404.06780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-10T06:41:30Z","cross_cats_sorted":[],"title_canon_sha256":"7e7b832a430ad76fa4484e5fc39b3b498b7a98f2f32bd71393ee649d4cd63bb3","abstract_canon_sha256":"2d120e4386f517746f87cba46b0903d7fe8f628d843427322d0ff3a2d7c5af13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:30.174272Z","signature_b64":"n6kzm8QxTrDn5+U+I3wkhNLtk4OFEEidPzPbnIV0VT2LydcEHDACMPSi79M9dmE4D3T9DHMKOkQ2geqrRlKjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"626dab68eb5b04ea6cd252e8b7e5ea5b765a5263437b927bba7e86169accce76","last_reissued_at":"2026-07-05T08:06:30.173794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:30.173794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Urban Architect: Steerable 3D Urban Scene Generation with Layout Prior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjun Jiang, Fan Lu, Guang Chen, Hongsheng Li, Kwan-Yee Lin, Yan Xu","submitted_at":"2024-04-10T06:41:30Z","abstract_excerpt":"Text-to-3D generation has achieved remarkable success via large-scale text-to-image diffusion models. Nevertheless, there is no paradigm for scaling up the methodology to urban scale. Urban scenes, characterized by numerous elements, intricate arrangement relationships, and vast scale, present a formidable barrier to the interpretability of ambiguous textual descriptions for effective model optimization. In this work, we surmount the limitations by introducing a compositional 3D layout representation into text-to-3D paradigm, serving as an additional prior. It comprises a set of semantic primi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06780","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/2404.06780/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":"2404.06780","created_at":"2026-07-05T08:06:30.173851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06780v1","created_at":"2026-07-05T08:06:30.173851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06780","created_at":"2026-07-05T08:06:30.173851+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJW2W2HLLMCO","created_at":"2026-07-05T08:06:30.173851+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJW2W2HLLMCOU3GS","created_at":"2026-07-05T08:06:30.173851+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJW2W2HL","created_at":"2026-07-05T08:06:30.173851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24138","citing_title":"Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06113","citing_title":"SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MJW2W2HLLMCOU3GSKLULPZPKLN","json":"https://pith.science/pith/MJW2W2HLLMCOU3GSKLULPZPKLN.json","graph_json":"https://pith.science/api/pith-number/MJW2W2HLLMCOU3GSKLULPZPKLN/graph.json","events_json":"https://pith.science/api/pith-number/MJW2W2HLLMCOU3GSKLULPZPKLN/events.json","paper":"https://pith.science/paper/MJW2W2HL"},"agent_actions":{"view_html":"https://pith.science/pith/MJW2W2HLLMCOU3GSKLULPZPKLN","download_json":"https://pith.science/pith/MJW2W2HLLMCOU3GSKLULPZPKLN.json","view_paper":"https://pith.science/paper/MJW2W2HL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06780&json=true","fetch_graph":"https://pith.science/api/pith-number/MJW2W2HLLMCOU3GSKLULPZPKLN/graph.json","fetch_events":"https://pith.science/api/pith-number/MJW2W2HLLMCOU3GSKLULPZPKLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJW2W2HLLMCOU3GSKLULPZPKLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJW2W2HLLMCOU3GSKLULPZPKLN/action/storage_attestation","attest_author":"https://pith.science/pith/MJW2W2HLLMCOU3GSKLULPZPKLN/action/author_attestation","sign_citation":"https://pith.science/pith/MJW2W2HLLMCOU3GSKLULPZPKLN/action/citation_signature","submit_replication":"https://pith.science/pith/MJW2W2HLLMCOU3GSKLULPZPKLN/action/replication_record"}},"created_at":"2026-07-05T08:06:30.173851+00:00","updated_at":"2026-07-05T08:06:30.173851+00:00"}