{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DHDXHFTSIYFNQVDIKFKO7YSOAF","short_pith_number":"pith:DHDXHFTS","schema_version":"1.0","canonical_sha256":"19c7739672460ad854685154efe24e01647a21a716d88585bc8b5a031f2af1bb","source":{"kind":"arxiv","id":"2512.11234","version":2},"attestation_state":"computed","paper":{"title":"RoomPilot: Controllable Indoor Scene Synthesis via Multimodal Semantic Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruihui Li, Shougao Zhang, Tianhao Zhou, Wentang Chen, Yiman Zhang","submitted_at":"2025-12-12T02:33:09Z","abstract_excerpt":"Generating controllable indoor scenes is fundamental to applications in game development, architectural visualization, and embodied AI. However, existing approaches either support a limited input modalities or rely on implicit generation processes that hinder precise control over scene structure and semantics. To address these limitations, we introduce RoomPilot, a unified framework for controllable indoor scene synthesis from multi-modal inputs, including textual descriptions and CAD floor plans. RoomPilot maps heterogeneous inputs into an Indoor Domain-Specific Language (IDSL), which serves "},"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":"2512.11234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-12T02:33:09Z","cross_cats_sorted":[],"title_canon_sha256":"36ab9049d894b7225842581142918f2cb60cf7df4d99f77b7e5ce055d1bbf225","abstract_canon_sha256":"de0d3df97903b4e666ded6c3f148452c6ecb51a88d29a87488cc199cf5419cca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:03.867022Z","signature_b64":"qJjiR2gLHcBY6BDkLydwxLrTYCIrMrFHYCnm7jD+8CzYTBZFW1ty/i4Hzl1rMy+VKDSI7TIixL1ajfWrmfTPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19c7739672460ad854685154efe24e01647a21a716d88585bc8b5a031f2af1bb","last_reissued_at":"2026-05-20T01:05:03.866045Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:03.866045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoomPilot: Controllable Indoor Scene Synthesis via Multimodal Semantic Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruihui Li, Shougao Zhang, Tianhao Zhou, Wentang Chen, Yiman Zhang","submitted_at":"2025-12-12T02:33:09Z","abstract_excerpt":"Generating controllable indoor scenes is fundamental to applications in game development, architectural visualization, and embodied AI. However, existing approaches either support a limited input modalities or rely on implicit generation processes that hinder precise control over scene structure and semantics. To address these limitations, we introduce RoomPilot, a unified framework for controllable indoor scene synthesis from multi-modal inputs, including textual descriptions and CAD floor plans. RoomPilot maps heterogeneous inputs into an Indoor Domain-Specific Language (IDSL), which serves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.11234","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/2512.11234/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":"2512.11234","created_at":"2026-05-20T01:05:03.866193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.11234v2","created_at":"2026-05-20T01:05:03.866193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.11234","created_at":"2026-05-20T01:05:03.866193+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHDXHFTSIYFN","created_at":"2026-05-20T01:05:03.866193+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHDXHFTSIYFNQVDI","created_at":"2026-05-20T01:05:03.866193+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHDXHFTS","created_at":"2026-05-20T01:05:03.866193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHDXHFTSIYFNQVDIKFKO7YSOAF","json":"https://pith.science/pith/DHDXHFTSIYFNQVDIKFKO7YSOAF.json","graph_json":"https://pith.science/api/pith-number/DHDXHFTSIYFNQVDIKFKO7YSOAF/graph.json","events_json":"https://pith.science/api/pith-number/DHDXHFTSIYFNQVDIKFKO7YSOAF/events.json","paper":"https://pith.science/paper/DHDXHFTS"},"agent_actions":{"view_html":"https://pith.science/pith/DHDXHFTSIYFNQVDIKFKO7YSOAF","download_json":"https://pith.science/pith/DHDXHFTSIYFNQVDIKFKO7YSOAF.json","view_paper":"https://pith.science/paper/DHDXHFTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.11234&json=true","fetch_graph":"https://pith.science/api/pith-number/DHDXHFTSIYFNQVDIKFKO7YSOAF/graph.json","fetch_events":"https://pith.science/api/pith-number/DHDXHFTSIYFNQVDIKFKO7YSOAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHDXHFTSIYFNQVDIKFKO7YSOAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHDXHFTSIYFNQVDIKFKO7YSOAF/action/storage_attestation","attest_author":"https://pith.science/pith/DHDXHFTSIYFNQVDIKFKO7YSOAF/action/author_attestation","sign_citation":"https://pith.science/pith/DHDXHFTSIYFNQVDIKFKO7YSOAF/action/citation_signature","submit_replication":"https://pith.science/pith/DHDXHFTSIYFNQVDIKFKO7YSOAF/action/replication_record"}},"created_at":"2026-05-20T01:05:03.866193+00:00","updated_at":"2026-05-20T01:05:03.866193+00:00"}