{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WKSRT7MANFEAEVWVH7CBSESCZU","short_pith_number":"pith:WKSRT7MA","schema_version":"1.0","canonical_sha256":"b2a519fd8069480256d53fc4191242cd3711ae1a15eb51ce63dd1795711bd87c","source":{"kind":"arxiv","id":"2503.16420","version":1},"attestation_state":"computed","paper":{"title":"SynCity: Training-Free Generation of 3D Worlds","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksandar Shtedritski, Andrea Vedaldi, Christian Rupprecht, Iro Laina, Paul Engstler","submitted_at":"2025-03-20T17:59:40Z","abstract_excerpt":"We address the challenge of generating 3D worlds from textual descriptions. We propose SynCity, a training- and optimization-free approach, which leverages the geometric precision of pre-trained 3D generative models and the artistic versatility of 2D image generators to create large, high-quality 3D spaces. While most 3D generative models are object-centric and cannot generate large-scale worlds, we show how 3D and 2D generators can be combined to generate ever-expanding scenes. Through a tile-based approach, we allow fine-grained control over the layout and the appearance of scenes. The world"},"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":"2503.16420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T17:59:40Z","cross_cats_sorted":[],"title_canon_sha256":"03e30a1c050960df37e367c2573705a32241b56d86304dd0119b808dc2789449","abstract_canon_sha256":"1b591dd6d162573c60b716d375660513aa888da6e92a7624d86b2ecf65643928"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:19.079919Z","signature_b64":"oDPPDam5a6JMiBASpkgAF3YRhd+kNc9uakEUDSyxa0ThRrhyowkKSL9gBSQJbH2HxzOTl9o21GtZ4Fu4vcMPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2a519fd8069480256d53fc4191242cd3711ae1a15eb51ce63dd1795711bd87c","last_reissued_at":"2026-07-05T10:36:19.078970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:19.078970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynCity: Training-Free Generation of 3D Worlds","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksandar Shtedritski, Andrea Vedaldi, Christian Rupprecht, Iro Laina, Paul Engstler","submitted_at":"2025-03-20T17:59:40Z","abstract_excerpt":"We address the challenge of generating 3D worlds from textual descriptions. We propose SynCity, a training- and optimization-free approach, which leverages the geometric precision of pre-trained 3D generative models and the artistic versatility of 2D image generators to create large, high-quality 3D spaces. While most 3D generative models are object-centric and cannot generate large-scale worlds, we show how 3D and 2D generators can be combined to generate ever-expanding scenes. Through a tile-based approach, we allow fine-grained control over the layout and the appearance of scenes. The world"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16420","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/2503.16420/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":"2503.16420","created_at":"2026-07-05T10:36:19.079099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16420v1","created_at":"2026-07-05T10:36:19.079099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16420","created_at":"2026-07-05T10:36:19.079099+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKSRT7MANFEA","created_at":"2026-07-05T10:36:19.079099+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKSRT7MANFEAEVWV","created_at":"2026-07-05T10:36:19.079099+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKSRT7MA","created_at":"2026-07-05T10:36:19.079099+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":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00781","citing_title":"Map2World: Segment Map Conditioned Text to 3D World Generation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKSRT7MANFEAEVWVH7CBSESCZU","json":"https://pith.science/pith/WKSRT7MANFEAEVWVH7CBSESCZU.json","graph_json":"https://pith.science/api/pith-number/WKSRT7MANFEAEVWVH7CBSESCZU/graph.json","events_json":"https://pith.science/api/pith-number/WKSRT7MANFEAEVWVH7CBSESCZU/events.json","paper":"https://pith.science/paper/WKSRT7MA"},"agent_actions":{"view_html":"https://pith.science/pith/WKSRT7MANFEAEVWVH7CBSESCZU","download_json":"https://pith.science/pith/WKSRT7MANFEAEVWVH7CBSESCZU.json","view_paper":"https://pith.science/paper/WKSRT7MA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16420&json=true","fetch_graph":"https://pith.science/api/pith-number/WKSRT7MANFEAEVWVH7CBSESCZU/graph.json","fetch_events":"https://pith.science/api/pith-number/WKSRT7MANFEAEVWVH7CBSESCZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKSRT7MANFEAEVWVH7CBSESCZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKSRT7MANFEAEVWVH7CBSESCZU/action/storage_attestation","attest_author":"https://pith.science/pith/WKSRT7MANFEAEVWVH7CBSESCZU/action/author_attestation","sign_citation":"https://pith.science/pith/WKSRT7MANFEAEVWVH7CBSESCZU/action/citation_signature","submit_replication":"https://pith.science/pith/WKSRT7MANFEAEVWVH7CBSESCZU/action/replication_record"}},"created_at":"2026-07-05T10:36:19.079099+00:00","updated_at":"2026-07-05T10:36:19.079099+00:00"}