{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IKUZ6IDJLB2PLOSQJWJZ2F5G7Y","short_pith_number":"pith:IKUZ6IDJ","schema_version":"1.0","canonical_sha256":"42a99f20695874f5ba504d939d17a6fe253b26eec14c89ec93bd5a245dbf3f9c","source":{"kind":"arxiv","id":"2503.18476","version":2},"attestation_state":"computed","paper":{"title":"Global-Local Tree Search in VLMs for 3D Indoor Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Huadong Ma, Mengshi Qi, Wei Deng","submitted_at":"2025-03-24T09:21:13Z","abstract_excerpt":"Large Vision-Language Models (VLMs), such as GPT-4, have achieved remarkable success across various fields. However, there are few studies on 3D indoor scene generation with VLMs. This paper considers this task as a planning problem subject to spatial and layout common sense constraints. To solve the problem with a VLM, we propose a new global-local tree search algorithm. Globally, the method places each object sequentially and explores multiple placements during each placement process, where the problem space is represented as a tree. To reduce the depth of the tree, we decompose the scene st"},"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":"2503.18476","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T09:21:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"94f06ca84d6c0d3625998c0a920dafa276c71d35b36cd8a8698f801d9217802b","abstract_canon_sha256":"521fbb13ea3f08a4bacf1eb344c29e52808c10d8f1bf7eb83448db5e8fb6628d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:46.140790Z","signature_b64":"HSPJEsH71x9p8mY5PvG0Tajj0QKBBux9pdzJ4Av23QEzRgQ1qmY4IrT3mQxN7vtkVv6h8mRW91SGAKmZ8p1hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42a99f20695874f5ba504d939d17a6fe253b26eec14c89ec93bd5a245dbf3f9c","last_reissued_at":"2026-07-05T10:38:46.140345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:46.140345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global-Local Tree Search in VLMs for 3D Indoor Scene Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Huadong Ma, Mengshi Qi, Wei Deng","submitted_at":"2025-03-24T09:21:13Z","abstract_excerpt":"Large Vision-Language Models (VLMs), such as GPT-4, have achieved remarkable success across various fields. However, there are few studies on 3D indoor scene generation with VLMs. This paper considers this task as a planning problem subject to spatial and layout common sense constraints. To solve the problem with a VLM, we propose a new global-local tree search algorithm. Globally, the method places each object sequentially and explores multiple placements during each placement process, where the problem space is represented as a tree. To reduce the depth of the tree, we decompose the scene st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18476","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/2503.18476/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":"2503.18476","created_at":"2026-07-05T10:38:46.140406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18476v2","created_at":"2026-07-05T10:38:46.140406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18476","created_at":"2026-07-05T10:38:46.140406+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKUZ6IDJLB2P","created_at":"2026-07-05T10:38:46.140406+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKUZ6IDJLB2PLOSQ","created_at":"2026-07-05T10:38:46.140406+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKUZ6IDJ","created_at":"2026-07-05T10:38:46.140406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20601","citing_title":"Video Perception Models for 3D Scene Synthesis","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y","json":"https://pith.science/pith/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y.json","graph_json":"https://pith.science/api/pith-number/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y/graph.json","events_json":"https://pith.science/api/pith-number/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y/events.json","paper":"https://pith.science/paper/IKUZ6IDJ"},"agent_actions":{"view_html":"https://pith.science/pith/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y","download_json":"https://pith.science/pith/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y.json","view_paper":"https://pith.science/paper/IKUZ6IDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18476&json=true","fetch_graph":"https://pith.science/api/pith-number/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y/action/storage_attestation","attest_author":"https://pith.science/pith/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y/action/author_attestation","sign_citation":"https://pith.science/pith/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y/action/citation_signature","submit_replication":"https://pith.science/pith/IKUZ6IDJLB2PLOSQJWJZ2F5G7Y/action/replication_record"}},"created_at":"2026-07-05T10:38:46.140406+00:00","updated_at":"2026-07-05T10:38:46.140406+00:00"}