{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BOHQYEEU3AC7BTWGBEQBKCYOY4","short_pith_number":"pith:BOHQYEEU","schema_version":"1.0","canonical_sha256":"0b8f0c1094d805f0cec60920150b0ec70b1f78f01c13e6704774b067bb1c3732","source":{"kind":"arxiv","id":"2506.02459","version":6},"attestation_state":"computed","paper":{"title":"ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Iro Armeni, Martin JJ. Bucher","submitted_at":"2025-06-03T05:22:04Z","abstract_excerpt":"Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scene generation either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or 'table'), require masked diffusion for editing, ignore room boundaries, or rely on floor plan renderings that fail to capture complex layouts. LLM-based methods enable richer semantics via natural language, but lack editing functionality, are limited to rectangular layouts, or rely on weak spatial reasoning from implicit world models. We introduce ReSpace, a generat"},"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":"2506.02459","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T05:22:04Z","cross_cats_sorted":[],"title_canon_sha256":"07b5de80c37e0c3a042d28ed160bdc6c0b261f8a4a3435219968985eee844c30","abstract_canon_sha256":"8bfa0ac8ac748420859c65f60207d11202320dd0f1d20ac745669aef4bb5b6bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:16:52.191424Z","signature_b64":"v7fucqbVH2QGyWZ/jPYRs+H4RFelup8hNIS0qP3nlhtlNhgsBDbr28BTNoLvoEG2RbmftkKoGeg39KNzk7CpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b8f0c1094d805f0cec60920150b0ec70b1f78f01c13e6704774b067bb1c3732","last_reissued_at":"2026-06-30T02:16:52.190760Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:16:52.190760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Iro Armeni, Martin JJ. Bucher","submitted_at":"2025-06-03T05:22:04Z","abstract_excerpt":"Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scene generation either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or 'table'), require masked diffusion for editing, ignore room boundaries, or rely on floor plan renderings that fail to capture complex layouts. LLM-based methods enable richer semantics via natural language, but lack editing functionality, are limited to rectangular layouts, or rely on weak spatial reasoning from implicit world models. We introduce ReSpace, a generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02459","kind":"arxiv","version":6},"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/2506.02459/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":"2506.02459","created_at":"2026-06-30T02:16:52.190841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02459v6","created_at":"2026-06-30T02:16:52.190841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02459","created_at":"2026-06-30T02:16:52.190841+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOHQYEEU3AC7","created_at":"2026-06-30T02:16:52.190841+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOHQYEEU3AC7BTWG","created_at":"2026-06-30T02:16:52.190841+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOHQYEEU","created_at":"2026-06-30T02:16:52.190841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2607.02407","citing_title":"Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09738","citing_title":"HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06390","citing_title":"HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27555","citing_title":"SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOHQYEEU3AC7BTWGBEQBKCYOY4","json":"https://pith.science/pith/BOHQYEEU3AC7BTWGBEQBKCYOY4.json","graph_json":"https://pith.science/api/pith-number/BOHQYEEU3AC7BTWGBEQBKCYOY4/graph.json","events_json":"https://pith.science/api/pith-number/BOHQYEEU3AC7BTWGBEQBKCYOY4/events.json","paper":"https://pith.science/paper/BOHQYEEU"},"agent_actions":{"view_html":"https://pith.science/pith/BOHQYEEU3AC7BTWGBEQBKCYOY4","download_json":"https://pith.science/pith/BOHQYEEU3AC7BTWGBEQBKCYOY4.json","view_paper":"https://pith.science/paper/BOHQYEEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02459&json=true","fetch_graph":"https://pith.science/api/pith-number/BOHQYEEU3AC7BTWGBEQBKCYOY4/graph.json","fetch_events":"https://pith.science/api/pith-number/BOHQYEEU3AC7BTWGBEQBKCYOY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOHQYEEU3AC7BTWGBEQBKCYOY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOHQYEEU3AC7BTWGBEQBKCYOY4/action/storage_attestation","attest_author":"https://pith.science/pith/BOHQYEEU3AC7BTWGBEQBKCYOY4/action/author_attestation","sign_citation":"https://pith.science/pith/BOHQYEEU3AC7BTWGBEQBKCYOY4/action/citation_signature","submit_replication":"https://pith.science/pith/BOHQYEEU3AC7BTWGBEQBKCYOY4/action/replication_record"}},"created_at":"2026-06-30T02:16:52.190841+00:00","updated_at":"2026-06-30T02:16:52.190841+00:00"}