{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RUVWHZWVSHIADJWHBI6IXPKPAO","short_pith_number":"pith:RUVWHZWV","schema_version":"1.0","canonical_sha256":"8d2b63e6d591d001a6c70a3c8bbd4f038001353da0e4ef83487c3b166dc1527d","source":{"kind":"arxiv","id":"2506.21562","version":2},"attestation_state":"computed","paper":{"title":"FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR"],"primary_cat":"cs.CL","authors_text":"Jing Zhong, Jun Yin, Miao Zhang, Peilin Li, Pengyu Zeng, Ran Luo, Shuai Lu","submitted_at":"2025-06-12T04:33:27Z","abstract_excerpt":"In the architectural design process, floor plan generation is inherently progressive and iterative. However, existing generative models for floor plans are predominantly end-to-end generation that produce an entire pixel-based layout in a single pass. This paradigm is often incompatible with the incremental workflows observed in real-world architectural practice. To address this issue, we draw inspiration from the autoregressive 'next token prediction' mechanism commonly used in large language models, and propose a novel 'next room prediction' paradigm tailored to architectural floor plan mode"},"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":"2506.21562","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T04:33:27Z","cross_cats_sorted":["cs.AI","cs.AR"],"title_canon_sha256":"a2c81d700b786c5be495a6e0549f745c9c4435ef0e46d3e49b0dd801150d7d18","abstract_canon_sha256":"317eadccf0a668a046470888183cef11ec0994291cecffa22376b6996b0d287d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:25.231198Z","signature_b64":"IYkny6/VwO2GZuwRo+qRBQGNVzH1MwwWaZMI4Wnr+Y9QWXOUeOJAWKtAd3mD+KkO8kJOlWIvUVAqITAcQNCbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d2b63e6d591d001a6c70a3c8bbd4f038001353da0e4ef83487c3b166dc1527d","last_reissued_at":"2026-07-05T11:47:25.230662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:25.230662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR"],"primary_cat":"cs.CL","authors_text":"Jing Zhong, Jun Yin, Miao Zhang, Peilin Li, Pengyu Zeng, Ran Luo, Shuai Lu","submitted_at":"2025-06-12T04:33:27Z","abstract_excerpt":"In the architectural design process, floor plan generation is inherently progressive and iterative. However, existing generative models for floor plans are predominantly end-to-end generation that produce an entire pixel-based layout in a single pass. This paradigm is often incompatible with the incremental workflows observed in real-world architectural practice. To address this issue, we draw inspiration from the autoregressive 'next token prediction' mechanism commonly used in large language models, and propose a novel 'next room prediction' paradigm tailored to architectural floor plan mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21562","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/2506.21562/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":"2506.21562","created_at":"2026-07-05T11:47:25.230719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21562v2","created_at":"2026-07-05T11:47:25.230719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21562","created_at":"2026-07-05T11:47:25.230719+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUVWHZWVSHIA","created_at":"2026-07-05T11:47:25.230719+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUVWHZWVSHIADJWH","created_at":"2026-07-05T11:47:25.230719+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUVWHZWV","created_at":"2026-07-05T11:47:25.230719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20837","citing_title":"ArchSIBench: Benchmarking the Architectural Spatial Intelligence of Vision-Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04832","citing_title":"BIM-Native Tokenization for Constraint-Aware Room Layout Synthesis","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUVWHZWVSHIADJWHBI6IXPKPAO","json":"https://pith.science/pith/RUVWHZWVSHIADJWHBI6IXPKPAO.json","graph_json":"https://pith.science/api/pith-number/RUVWHZWVSHIADJWHBI6IXPKPAO/graph.json","events_json":"https://pith.science/api/pith-number/RUVWHZWVSHIADJWHBI6IXPKPAO/events.json","paper":"https://pith.science/paper/RUVWHZWV"},"agent_actions":{"view_html":"https://pith.science/pith/RUVWHZWVSHIADJWHBI6IXPKPAO","download_json":"https://pith.science/pith/RUVWHZWVSHIADJWHBI6IXPKPAO.json","view_paper":"https://pith.science/paper/RUVWHZWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21562&json=true","fetch_graph":"https://pith.science/api/pith-number/RUVWHZWVSHIADJWHBI6IXPKPAO/graph.json","fetch_events":"https://pith.science/api/pith-number/RUVWHZWVSHIADJWHBI6IXPKPAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUVWHZWVSHIADJWHBI6IXPKPAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUVWHZWVSHIADJWHBI6IXPKPAO/action/storage_attestation","attest_author":"https://pith.science/pith/RUVWHZWVSHIADJWHBI6IXPKPAO/action/author_attestation","sign_citation":"https://pith.science/pith/RUVWHZWVSHIADJWHBI6IXPKPAO/action/citation_signature","submit_replication":"https://pith.science/pith/RUVWHZWVSHIADJWHBI6IXPKPAO/action/replication_record"}},"created_at":"2026-07-05T11:47:25.230719+00:00","updated_at":"2026-07-05T11:47:25.230719+00:00"}