{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GDR4W2TH7APWXDKEDZSDQMMJ77","short_pith_number":"pith:GDR4W2TH","schema_version":"1.0","canonical_sha256":"30e3cb6a67f81f6b8d441e64383189ffdd353364a029b69dc8a8795cea500474","source":{"kind":"arxiv","id":"2406.00687","version":2},"attestation_state":"computed","paper":{"title":"Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gal Chechik, Hilit Segev, Idan Achituve, Ohad Rahamim, Yoni Kasten, Yuval Atzmon","submitted_at":"2024-06-02T09:48:19Z","abstract_excerpt":"Generating 3D visual scenes is at the forefront of visual generative AI, but current 3D generation techniques struggle with generating scenes with multiple high-resolution objects. Here we introduce Lay-A-Scene, which solves the task of Open-set 3D Object Arrangement, effectively arranging unseen objects. Given a set of 3D objects, the task is to find a plausible arrangement of these objects in a scene. We address this task by leveraging pre-trained text-to-image models. We personalize the model and explain how to generate images of a scene that contains multiple predefined objects without neg"},"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":"2406.00687","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-02T09:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"6aeb229e0e4e1d4707072653bed3185580e4484917318ff367502e2b99209a77","abstract_canon_sha256":"99ffb5f0bb09c9812d9cbf3f893d481da1e84adcd327a41dd51f4721aee73250"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:10.157535Z","signature_b64":"zqIhFKITnzjGI/2CxKLjp0ZkTBEOTMRo/fCDDYPQa5rBr1Tgynxy/LWVig/hSdiue310CwSJ1NUtLZV7/AzgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e3cb6a67f81f6b8d441e64383189ffdd353364a029b69dc8a8795cea500474","last_reissued_at":"2026-07-05T08:27:10.157065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:10.157065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gal Chechik, Hilit Segev, Idan Achituve, Ohad Rahamim, Yoni Kasten, Yuval Atzmon","submitted_at":"2024-06-02T09:48:19Z","abstract_excerpt":"Generating 3D visual scenes is at the forefront of visual generative AI, but current 3D generation techniques struggle with generating scenes with multiple high-resolution objects. Here we introduce Lay-A-Scene, which solves the task of Open-set 3D Object Arrangement, effectively arranging unseen objects. Given a set of 3D objects, the task is to find a plausible arrangement of these objects in a scene. We address this task by leveraging pre-trained text-to-image models. We personalize the model and explain how to generate images of a scene that contains multiple predefined objects without neg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00687","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/2406.00687/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":"2406.00687","created_at":"2026-07-05T08:27:10.157121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00687v2","created_at":"2026-07-05T08:27:10.157121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00687","created_at":"2026-07-05T08:27:10.157121+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDR4W2TH7APW","created_at":"2026-07-05T08:27:10.157121+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDR4W2TH7APWXDKE","created_at":"2026-07-05T08:27:10.157121+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDR4W2TH","created_at":"2026-07-05T08:27:10.157121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06484","citing_title":"3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDR4W2TH7APWXDKEDZSDQMMJ77","json":"https://pith.science/pith/GDR4W2TH7APWXDKEDZSDQMMJ77.json","graph_json":"https://pith.science/api/pith-number/GDR4W2TH7APWXDKEDZSDQMMJ77/graph.json","events_json":"https://pith.science/api/pith-number/GDR4W2TH7APWXDKEDZSDQMMJ77/events.json","paper":"https://pith.science/paper/GDR4W2TH"},"agent_actions":{"view_html":"https://pith.science/pith/GDR4W2TH7APWXDKEDZSDQMMJ77","download_json":"https://pith.science/pith/GDR4W2TH7APWXDKEDZSDQMMJ77.json","view_paper":"https://pith.science/paper/GDR4W2TH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00687&json=true","fetch_graph":"https://pith.science/api/pith-number/GDR4W2TH7APWXDKEDZSDQMMJ77/graph.json","fetch_events":"https://pith.science/api/pith-number/GDR4W2TH7APWXDKEDZSDQMMJ77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDR4W2TH7APWXDKEDZSDQMMJ77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDR4W2TH7APWXDKEDZSDQMMJ77/action/storage_attestation","attest_author":"https://pith.science/pith/GDR4W2TH7APWXDKEDZSDQMMJ77/action/author_attestation","sign_citation":"https://pith.science/pith/GDR4W2TH7APWXDKEDZSDQMMJ77/action/citation_signature","submit_replication":"https://pith.science/pith/GDR4W2TH7APWXDKEDZSDQMMJ77/action/replication_record"}},"created_at":"2026-07-05T08:27:10.157121+00:00","updated_at":"2026-07-05T08:27:10.157121+00:00"}