{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LF354G4HJYCRPHTVKGLLD7MWVH","short_pith_number":"pith:LF354G4H","schema_version":"1.0","canonical_sha256":"5977de1b874e05179e755196b1fd96a9ee50a1d7502b9a9717772a8988b34153","source":{"kind":"arxiv","id":"2408.05477","version":2},"attestation_state":"computed","paper":{"title":"Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fukun Yin, Gang Yu, Jiayuan Fan, Wanzhang Li, Xin Chen, Yiying Yang","submitted_at":"2024-08-10T08:09:57Z","abstract_excerpt":"As Artificial Intelligence Generated Content (AIGC) advances, a variety of methods have been developed to generate text, images, videos, and 3D objects from single or multimodal inputs, contributing efforts to emulate human-like cognitive content creation. However, generating realistic large-scale scenes from a single input presents a challenge due to the complexities involved in ensuring consistency across extrapolated views generated by models. Benefiting from recent video generation models and implicit neural representations, we propose Scene123, a 3D scene generation model, that not only e"},"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":"2408.05477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-10T08:09:57Z","cross_cats_sorted":[],"title_canon_sha256":"0bf1ebe3a2f916ee9dc8a9b429a4d26ff2953b5dc1647fccc8c4a4bb78707067","abstract_canon_sha256":"c027a359f8e45336cd5833fd72ba660612f3ae459ceb2cd87bc2aea878397529"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:06.614235Z","signature_b64":"gKcsNs5xRRBofShcyYeF95xgxxFRMRdY/8kyGMIvDaGVUoVHOmYqa1lJl1QAhqPi8RwiX1G/NIcYxfggB/ejBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5977de1b874e05179e755196b1fd96a9ee50a1d7502b9a9717772a8988b34153","last_reissued_at":"2026-07-05T08:57:06.613787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:06.613787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fukun Yin, Gang Yu, Jiayuan Fan, Wanzhang Li, Xin Chen, Yiying Yang","submitted_at":"2024-08-10T08:09:57Z","abstract_excerpt":"As Artificial Intelligence Generated Content (AIGC) advances, a variety of methods have been developed to generate text, images, videos, and 3D objects from single or multimodal inputs, contributing efforts to emulate human-like cognitive content creation. However, generating realistic large-scale scenes from a single input presents a challenge due to the complexities involved in ensuring consistency across extrapolated views generated by models. Benefiting from recent video generation models and implicit neural representations, we propose Scene123, a 3D scene generation model, that not only e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05477","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/2408.05477/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":"2408.05477","created_at":"2026-07-05T08:57:06.613843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05477v2","created_at":"2026-07-05T08:57:06.613843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05477","created_at":"2026-07-05T08:57:06.613843+00:00"},{"alias_kind":"pith_short_12","alias_value":"LF354G4HJYCR","created_at":"2026-07-05T08:57:06.613843+00:00"},{"alias_kind":"pith_short_16","alias_value":"LF354G4HJYCRPHTV","created_at":"2026-07-05T08:57:06.613843+00:00"},{"alias_kind":"pith_short_8","alias_value":"LF354G4H","created_at":"2026-07-05T08:57:06.613843+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":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":295,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LF354G4HJYCRPHTVKGLLD7MWVH","json":"https://pith.science/pith/LF354G4HJYCRPHTVKGLLD7MWVH.json","graph_json":"https://pith.science/api/pith-number/LF354G4HJYCRPHTVKGLLD7MWVH/graph.json","events_json":"https://pith.science/api/pith-number/LF354G4HJYCRPHTVKGLLD7MWVH/events.json","paper":"https://pith.science/paper/LF354G4H"},"agent_actions":{"view_html":"https://pith.science/pith/LF354G4HJYCRPHTVKGLLD7MWVH","download_json":"https://pith.science/pith/LF354G4HJYCRPHTVKGLLD7MWVH.json","view_paper":"https://pith.science/paper/LF354G4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05477&json=true","fetch_graph":"https://pith.science/api/pith-number/LF354G4HJYCRPHTVKGLLD7MWVH/graph.json","fetch_events":"https://pith.science/api/pith-number/LF354G4HJYCRPHTVKGLLD7MWVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LF354G4HJYCRPHTVKGLLD7MWVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LF354G4HJYCRPHTVKGLLD7MWVH/action/storage_attestation","attest_author":"https://pith.science/pith/LF354G4HJYCRPHTVKGLLD7MWVH/action/author_attestation","sign_citation":"https://pith.science/pith/LF354G4HJYCRPHTVKGLLD7MWVH/action/citation_signature","submit_replication":"https://pith.science/pith/LF354G4HJYCRPHTVKGLLD7MWVH/action/replication_record"}},"created_at":"2026-07-05T08:57:06.613843+00:00","updated_at":"2026-07-05T08:57:06.613843+00:00"}