{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O7AW2AOW6QBO5UI6UMH37B76VX","short_pith_number":"pith:O7AW2AOW","schema_version":"1.0","canonical_sha256":"77c16d01d6f402eed11ea30fbf87feade2f9683f3d14bee64dcab969e4b1c3bd","source":{"kind":"arxiv","id":"2411.12279","version":4},"attestation_state":"computed","paper":{"title":"HouseTune: Two-Stage Floorplan Generation with LLM Assistance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengcheng Yu, Guang Tan, Guanying Chen, Zhaohuan Zhan, Ziyang Zong","submitted_at":"2024-11-19T06:57:45Z","abstract_excerpt":"This paper proposes a two-stage text-to-floorplan generation framework that combines the reasoning capability of Large Language Models (LLMs) with the generative power of diffusion models. In the first stage, we leverage a Chain-of-Thought (CoT) prompting strategy to guide an LLM in generating an initial layout (Layout-Init) from natural language descriptions, which ensures a user-friendly and intuitive design process. However, Layout-Init may lack precise geometric alignment and fine-grained structural details. To address this, the second stage employs a conditional diffusion model to refine "},"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":"2411.12279","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-19T06:57:45Z","cross_cats_sorted":[],"title_canon_sha256":"85e8715b47ac69bafc039d604912e4ce5213b483aca3ab7f46f6e63afd2d55b4","abstract_canon_sha256":"7d783d3217bc8e76b1d0023fef587eb77738685a8dc911fb762bad0d3b2ce69b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:19.831685Z","signature_b64":"bM0lR80OJ+TZBXn39BIBQU7tbZ8NQLGuwNac4j9Mn46+4p2vqOBJFwFtf4DqK4KwyCCYPHhbygTZXx3eQaD3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77c16d01d6f402eed11ea30fbf87feade2f9683f3d14bee64dcab969e4b1c3bd","last_reissued_at":"2026-07-05T10:27:19.830709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:19.830709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HouseTune: Two-Stage Floorplan Generation with LLM Assistance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengcheng Yu, Guang Tan, Guanying Chen, Zhaohuan Zhan, Ziyang Zong","submitted_at":"2024-11-19T06:57:45Z","abstract_excerpt":"This paper proposes a two-stage text-to-floorplan generation framework that combines the reasoning capability of Large Language Models (LLMs) with the generative power of diffusion models. In the first stage, we leverage a Chain-of-Thought (CoT) prompting strategy to guide an LLM in generating an initial layout (Layout-Init) from natural language descriptions, which ensures a user-friendly and intuitive design process. However, Layout-Init may lack precise geometric alignment and fine-grained structural details. To address this, the second stage employs a conditional diffusion model to refine "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12279","kind":"arxiv","version":4},"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/2411.12279/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":"2411.12279","created_at":"2026-07-05T10:27:19.830840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12279v4","created_at":"2026-07-05T10:27:19.830840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12279","created_at":"2026-07-05T10:27:19.830840+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7AW2AOW6QBO","created_at":"2026-07-05T10:27:19.830840+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7AW2AOW6QBO5UI6","created_at":"2026-07-05T10:27:19.830840+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7AW2AOW","created_at":"2026-07-05T10:27:19.830840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18932","citing_title":"HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18932","citing_title":"HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7AW2AOW6QBO5UI6UMH37B76VX","json":"https://pith.science/pith/O7AW2AOW6QBO5UI6UMH37B76VX.json","graph_json":"https://pith.science/api/pith-number/O7AW2AOW6QBO5UI6UMH37B76VX/graph.json","events_json":"https://pith.science/api/pith-number/O7AW2AOW6QBO5UI6UMH37B76VX/events.json","paper":"https://pith.science/paper/O7AW2AOW"},"agent_actions":{"view_html":"https://pith.science/pith/O7AW2AOW6QBO5UI6UMH37B76VX","download_json":"https://pith.science/pith/O7AW2AOW6QBO5UI6UMH37B76VX.json","view_paper":"https://pith.science/paper/O7AW2AOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12279&json=true","fetch_graph":"https://pith.science/api/pith-number/O7AW2AOW6QBO5UI6UMH37B76VX/graph.json","fetch_events":"https://pith.science/api/pith-number/O7AW2AOW6QBO5UI6UMH37B76VX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7AW2AOW6QBO5UI6UMH37B76VX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7AW2AOW6QBO5UI6UMH37B76VX/action/storage_attestation","attest_author":"https://pith.science/pith/O7AW2AOW6QBO5UI6UMH37B76VX/action/author_attestation","sign_citation":"https://pith.science/pith/O7AW2AOW6QBO5UI6UMH37B76VX/action/citation_signature","submit_replication":"https://pith.science/pith/O7AW2AOW6QBO5UI6UMH37B76VX/action/replication_record"}},"created_at":"2026-07-05T10:27:19.830840+00:00","updated_at":"2026-07-05T10:27:19.830840+00:00"}