{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SBRU4ZBADWRSQZLU4QLEV4MC37","short_pith_number":"pith:SBRU4ZBA","schema_version":"1.0","canonical_sha256":"90634e64201da3286574e4164af182dfdb5f527b02f55653bef742e88d9987ee","source":{"kind":"arxiv","id":"2505.04718","version":1},"attestation_state":"computed","paper":{"title":"Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenru Wen, Divyansh Srivastava, He Wen, Xiang Zhang, Zhuowen Tu","submitted_at":"2025-05-07T18:07:57Z","abstract_excerpt":"We present Lay-Your-Scene (shorthand LayouSyn), a novel text-to-layout generation pipeline for natural scenes. Prior scene layout generation methods are either closed-vocabulary or use proprietary large language models for open-vocabulary generation, limiting their modeling capabilities and broader applicability in controllable image generation. In this work, we propose to use lightweight open-source language models to obtain scene elements from text prompts and a novel aspect-aware diffusion Transformer architecture trained in an open-vocabulary manner for conditional layout generation. Exten"},"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":"2505.04718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T18:07:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dafa2c925e472b73c432cdc9770d0650b802a8e6e163743ce309c7fff386123e","abstract_canon_sha256":"8a461b1d13e6e6d71a927ef0aecc9d776ca074632813c67bf310d73a66a67313"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:12.623535Z","signature_b64":"8V/xw+Snb3tHnvAYaW0kZzR+0/cEjC0DXB5hs0WP/pPIYjULzLSAfQBMl0L3t87DVtQ7rZ9CMxkU+V/5rjAnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90634e64201da3286574e4164af182dfdb5f527b02f55653bef742e88d9987ee","last_reissued_at":"2026-07-05T11:00:12.622974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:12.622974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenru Wen, Divyansh Srivastava, He Wen, Xiang Zhang, Zhuowen Tu","submitted_at":"2025-05-07T18:07:57Z","abstract_excerpt":"We present Lay-Your-Scene (shorthand LayouSyn), a novel text-to-layout generation pipeline for natural scenes. Prior scene layout generation methods are either closed-vocabulary or use proprietary large language models for open-vocabulary generation, limiting their modeling capabilities and broader applicability in controllable image generation. In this work, we propose to use lightweight open-source language models to obtain scene elements from text prompts and a novel aspect-aware diffusion Transformer architecture trained in an open-vocabulary manner for conditional layout generation. Exten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04718","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/2505.04718/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":"2505.04718","created_at":"2026-07-05T11:00:12.623043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04718v1","created_at":"2026-07-05T11:00:12.623043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04718","created_at":"2026-07-05T11:00:12.623043+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBRU4ZBADWRS","created_at":"2026-07-05T11:00:12.623043+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBRU4ZBADWRSQZLU","created_at":"2026-07-05T11:00:12.623043+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBRU4ZBA","created_at":"2026-07-05T11:00:12.623043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.04832","citing_title":"BIM-Native Tokenization for Constraint-Aware Room Layout Synthesis","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBRU4ZBADWRSQZLU4QLEV4MC37","json":"https://pith.science/pith/SBRU4ZBADWRSQZLU4QLEV4MC37.json","graph_json":"https://pith.science/api/pith-number/SBRU4ZBADWRSQZLU4QLEV4MC37/graph.json","events_json":"https://pith.science/api/pith-number/SBRU4ZBADWRSQZLU4QLEV4MC37/events.json","paper":"https://pith.science/paper/SBRU4ZBA"},"agent_actions":{"view_html":"https://pith.science/pith/SBRU4ZBADWRSQZLU4QLEV4MC37","download_json":"https://pith.science/pith/SBRU4ZBADWRSQZLU4QLEV4MC37.json","view_paper":"https://pith.science/paper/SBRU4ZBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04718&json=true","fetch_graph":"https://pith.science/api/pith-number/SBRU4ZBADWRSQZLU4QLEV4MC37/graph.json","fetch_events":"https://pith.science/api/pith-number/SBRU4ZBADWRSQZLU4QLEV4MC37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBRU4ZBADWRSQZLU4QLEV4MC37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBRU4ZBADWRSQZLU4QLEV4MC37/action/storage_attestation","attest_author":"https://pith.science/pith/SBRU4ZBADWRSQZLU4QLEV4MC37/action/author_attestation","sign_citation":"https://pith.science/pith/SBRU4ZBADWRSQZLU4QLEV4MC37/action/citation_signature","submit_replication":"https://pith.science/pith/SBRU4ZBADWRSQZLU4QLEV4MC37/action/replication_record"}},"created_at":"2026-07-05T11:00:12.623043+00:00","updated_at":"2026-07-05T11:00:12.623043+00:00"}