{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZN74JOJ3EM6BMP6IVG2QD6WPB4","short_pith_number":"pith:ZN74JOJ3","schema_version":"1.0","canonical_sha256":"cb7fc4b93b233c163fc8a9b501facf0f3859e9ceafa5f401aa2d406e4c876817","source":{"kind":"arxiv","id":"2606.06002","version":1},"attestation_state":"computed","paper":{"title":"Global-Local Monte Carlo Tree Search in Vision-Language Models for Text-to-3D Indoor Scene Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huadong Ma, Mengshi Qi, Wei Deng, Xianlin Zhang","submitted_at":"2026-06-04T10:56:21Z","abstract_excerpt":"Large Vision-Language Models have achieved significant reasoning performance in various tasks.However, there are few studies on text-to-3D indoor scene generation with LVLMs. The main challenge is that prevailing LVLM-based methods employ chain-of-thought sequential decision mechanisms that cannot revise earlier decisions, causing error propagation.In this paper, we consider the task as a planning problem constrained by spatial and layout commonsense.To solve this problem, we model it as a tree search problem with global and local trees, which differs from existing sequential decision-making a"},"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":"2606.06002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T10:56:21Z","cross_cats_sorted":[],"title_canon_sha256":"24d7c81c05c8afa9edebf24174a4d8e35ade3b3aa6aa277107139c0d62718737","abstract_canon_sha256":"e0f43300e49eba94705092cc8fc28ef1dfc5ada90072960e0f9ea41b53f7dc85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:30.117225Z","signature_b64":"NJ5MvmdEyBYhP/9RshYSfmvIRy1CEqyzPro3llULVBT8+KaB6UW8maB3sagJ/rSJvv5qOZ8J1fgb42Xu8b5KDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb7fc4b93b233c163fc8a9b501facf0f3859e9ceafa5f401aa2d406e4c876817","last_reissued_at":"2026-06-05T01:15:30.116707Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:30.116707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global-Local Monte Carlo Tree Search in Vision-Language Models for Text-to-3D Indoor Scene Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huadong Ma, Mengshi Qi, Wei Deng, Xianlin Zhang","submitted_at":"2026-06-04T10:56:21Z","abstract_excerpt":"Large Vision-Language Models have achieved significant reasoning performance in various tasks.However, there are few studies on text-to-3D indoor scene generation with LVLMs. The main challenge is that prevailing LVLM-based methods employ chain-of-thought sequential decision mechanisms that cannot revise earlier decisions, causing error propagation.In this paper, we consider the task as a planning problem constrained by spatial and layout commonsense.To solve this problem, we model it as a tree search problem with global and local trees, which differs from existing sequential decision-making a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06002","kind":"arxiv","version":1},"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/2606.06002/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":"2606.06002","created_at":"2026-06-05T01:15:30.116781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06002v1","created_at":"2026-06-05T01:15:30.116781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06002","created_at":"2026-06-05T01:15:30.116781+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZN74JOJ3EM6B","created_at":"2026-06-05T01:15:30.116781+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZN74JOJ3EM6BMP6I","created_at":"2026-06-05T01:15:30.116781+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZN74JOJ3","created_at":"2026-06-05T01:15:30.116781+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/ZN74JOJ3EM6BMP6IVG2QD6WPB4","json":"https://pith.science/pith/ZN74JOJ3EM6BMP6IVG2QD6WPB4.json","graph_json":"https://pith.science/api/pith-number/ZN74JOJ3EM6BMP6IVG2QD6WPB4/graph.json","events_json":"https://pith.science/api/pith-number/ZN74JOJ3EM6BMP6IVG2QD6WPB4/events.json","paper":"https://pith.science/paper/ZN74JOJ3"},"agent_actions":{"view_html":"https://pith.science/pith/ZN74JOJ3EM6BMP6IVG2QD6WPB4","download_json":"https://pith.science/pith/ZN74JOJ3EM6BMP6IVG2QD6WPB4.json","view_paper":"https://pith.science/paper/ZN74JOJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06002&json=true","fetch_graph":"https://pith.science/api/pith-number/ZN74JOJ3EM6BMP6IVG2QD6WPB4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZN74JOJ3EM6BMP6IVG2QD6WPB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZN74JOJ3EM6BMP6IVG2QD6WPB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZN74JOJ3EM6BMP6IVG2QD6WPB4/action/storage_attestation","attest_author":"https://pith.science/pith/ZN74JOJ3EM6BMP6IVG2QD6WPB4/action/author_attestation","sign_citation":"https://pith.science/pith/ZN74JOJ3EM6BMP6IVG2QD6WPB4/action/citation_signature","submit_replication":"https://pith.science/pith/ZN74JOJ3EM6BMP6IVG2QD6WPB4/action/replication_record"}},"created_at":"2026-06-05T01:15:30.116781+00:00","updated_at":"2026-06-05T01:15:30.116781+00:00"}