{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EGHBCSEXTSCSEWAM3EZRZ2MELE","short_pith_number":"pith:EGHBCSEX","schema_version":"1.0","canonical_sha256":"218e1148979c8522580cd9331ce984593faa61e094c001577b21f724dcd1d309","source":{"kind":"arxiv","id":"2403.09675","version":1},"attestation_state":"computed","paper":{"title":"Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Aditya Ganeshan, Daniel Ritchie, Do Heon Han, Kailiang Fu, Maxim Gumin, Qiuhong Anna Wei, Rio Aguina-Kang, R. Kenny Jones, Seung Jean Yoo, Stewart Morris","submitted_at":"2024-02-05T01:59:31Z","abstract_excerpt":"We present a system for generating indoor scenes in response to text prompts. The prompts are not limited to a fixed vocabulary of scene descriptions, and the objects in generated scenes are not restricted to a fixed set of object categories -- we call this setting indoor scene generation. Unlike most prior work on indoor scene generation, our system does not require a large training dataset of existing 3D scenes. Instead, it leverages the world knowledge encoded in pre-trained large language models (LLMs) to synthesize programs in a domain-specific layout language that describe objects and sp"},"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":"2403.09675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-05T01:59:31Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"aa1144c54bb43687161b7cb2b840091d5e22522e5bd763420e680bc9a7896330","abstract_canon_sha256":"8da9571d007bc3eee84bac4e64f7d99ad2e1f44c1e76d1f3b20eacbdf981f996"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:23.269536Z","signature_b64":"ur/JVPUETkjO3FUJ9Wz2IGZztS0+liqnohCzgvglAtsDs9lB11wp1V0cd7JzNGSeRUWXq2eBV4mfeDUaFZ2pBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"218e1148979c8522580cd9331ce984593faa61e094c001577b21f724dcd1d309","last_reissued_at":"2026-07-05T07:56:23.269158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:23.269158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Aditya Ganeshan, Daniel Ritchie, Do Heon Han, Kailiang Fu, Maxim Gumin, Qiuhong Anna Wei, Rio Aguina-Kang, R. Kenny Jones, Seung Jean Yoo, Stewart Morris","submitted_at":"2024-02-05T01:59:31Z","abstract_excerpt":"We present a system for generating indoor scenes in response to text prompts. The prompts are not limited to a fixed vocabulary of scene descriptions, and the objects in generated scenes are not restricted to a fixed set of object categories -- we call this setting indoor scene generation. Unlike most prior work on indoor scene generation, our system does not require a large training dataset of existing 3D scenes. Instead, it leverages the world knowledge encoded in pre-trained large language models (LLMs) to synthesize programs in a domain-specific layout language that describe objects and sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09675","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/2403.09675/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":"2403.09675","created_at":"2026-07-05T07:56:23.269208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09675v1","created_at":"2026-07-05T07:56:23.269208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09675","created_at":"2026-07-05T07:56:23.269208+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGHBCSEXTSCS","created_at":"2026-07-05T07:56:23.269208+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGHBCSEXTSCSEWAM","created_at":"2026-07-05T07:56:23.269208+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGHBCSEX","created_at":"2026-07-05T07:56:23.269208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02407","citing_title":"Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04496","citing_title":"Learning to Place Objects with Programs and Iterative Self Training","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11109","citing_title":"Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01972","citing_title":"SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27555","citing_title":"SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11808","citing_title":"Pair2Scene: Learning Local Object Relations for Procedural Scene Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11808","citing_title":"Pair2Scene: Learning Local Object Relations for Procedural Scene Generation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGHBCSEXTSCSEWAM3EZRZ2MELE","json":"https://pith.science/pith/EGHBCSEXTSCSEWAM3EZRZ2MELE.json","graph_json":"https://pith.science/api/pith-number/EGHBCSEXTSCSEWAM3EZRZ2MELE/graph.json","events_json":"https://pith.science/api/pith-number/EGHBCSEXTSCSEWAM3EZRZ2MELE/events.json","paper":"https://pith.science/paper/EGHBCSEX"},"agent_actions":{"view_html":"https://pith.science/pith/EGHBCSEXTSCSEWAM3EZRZ2MELE","download_json":"https://pith.science/pith/EGHBCSEXTSCSEWAM3EZRZ2MELE.json","view_paper":"https://pith.science/paper/EGHBCSEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09675&json=true","fetch_graph":"https://pith.science/api/pith-number/EGHBCSEXTSCSEWAM3EZRZ2MELE/graph.json","fetch_events":"https://pith.science/api/pith-number/EGHBCSEXTSCSEWAM3EZRZ2MELE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGHBCSEXTSCSEWAM3EZRZ2MELE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGHBCSEXTSCSEWAM3EZRZ2MELE/action/storage_attestation","attest_author":"https://pith.science/pith/EGHBCSEXTSCSEWAM3EZRZ2MELE/action/author_attestation","sign_citation":"https://pith.science/pith/EGHBCSEXTSCSEWAM3EZRZ2MELE/action/citation_signature","submit_replication":"https://pith.science/pith/EGHBCSEXTSCSEWAM3EZRZ2MELE/action/replication_record"}},"created_at":"2026-07-05T07:56:23.269208+00:00","updated_at":"2026-07-05T07:56:23.269208+00:00"}