{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S3YU4SGRTZ2DEQKBZK33L7DHW5","short_pith_number":"pith:S3YU4SGR","schema_version":"1.0","canonical_sha256":"96f14e48d19e74324141cab7b5fc67b76cea19da86a8f108d9b630e4ed6e055d","source":{"kind":"arxiv","id":"2412.02193","version":3},"attestation_state":"computed","paper":{"title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dylan Lim, Fan-Yun Sun, Federico Tombari, Goutam Bhat, Jiajun Wu, Manling Li, Nick Haber, Siyi Gu, Weiyu Liu","submitted_at":"2024-12-03T06:15:04Z","abstract_excerpt":"Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still struggle with 3D reasoning tasks like arranging objects in space according to open-ended language instructions, particularly in dense and physically constrained environments. We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs) and supports differentiable optimization to en"},"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":"2412.02193","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T06:15:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e717cdec0a9e761b4bacf91029238e7d16a222a2be469137576a7f903819950","abstract_canon_sha256":"aa06bb6948520e1a029aab513ad0471107655338fea26f7e0ccf5d7dc31bcfe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:29.260517Z","signature_b64":"XNAJl+G+TDqA6341BV0p8RjDEvWHMEsnncocW9Q0n2e821E+Nww+LH4Rtv14G5W8/nhwNU/nVMlhpMSU7zIrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96f14e48d19e74324141cab7b5fc67b76cea19da86a8f108d9b630e4ed6e055d","last_reissued_at":"2026-07-05T10:28:29.260028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:29.260028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dylan Lim, Fan-Yun Sun, Federico Tombari, Goutam Bhat, Jiajun Wu, Manling Li, Nick Haber, Siyi Gu, Weiyu Liu","submitted_at":"2024-12-03T06:15:04Z","abstract_excerpt":"Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space. While foundation models demonstrate remarkable performance on some benchmarks, they still struggle with 3D reasoning tasks like arranging objects in space according to open-ended language instructions, particularly in dense and physically constrained environments. We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs) and supports differentiable optimization to en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02193","kind":"arxiv","version":3},"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/2412.02193/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":"2412.02193","created_at":"2026-07-05T10:28:29.260086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02193v3","created_at":"2026-07-05T10:28:29.260086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02193","created_at":"2026-07-05T10:28:29.260086+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3YU4SGRTZ2D","created_at":"2026-07-05T10:28:29.260086+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3YU4SGRTZ2DEQKB","created_at":"2026-07-05T10:28:29.260086+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3YU4SGR","created_at":"2026-07-05T10:28:29.260086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05392","citing_title":"SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02407","citing_title":"Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25326","citing_title":"Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16137","citing_title":"STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26943","citing_title":"ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3YU4SGRTZ2DEQKBZK33L7DHW5","json":"https://pith.science/pith/S3YU4SGRTZ2DEQKBZK33L7DHW5.json","graph_json":"https://pith.science/api/pith-number/S3YU4SGRTZ2DEQKBZK33L7DHW5/graph.json","events_json":"https://pith.science/api/pith-number/S3YU4SGRTZ2DEQKBZK33L7DHW5/events.json","paper":"https://pith.science/paper/S3YU4SGR"},"agent_actions":{"view_html":"https://pith.science/pith/S3YU4SGRTZ2DEQKBZK33L7DHW5","download_json":"https://pith.science/pith/S3YU4SGRTZ2DEQKBZK33L7DHW5.json","view_paper":"https://pith.science/paper/S3YU4SGR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02193&json=true","fetch_graph":"https://pith.science/api/pith-number/S3YU4SGRTZ2DEQKBZK33L7DHW5/graph.json","fetch_events":"https://pith.science/api/pith-number/S3YU4SGRTZ2DEQKBZK33L7DHW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3YU4SGRTZ2DEQKBZK33L7DHW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3YU4SGRTZ2DEQKBZK33L7DHW5/action/storage_attestation","attest_author":"https://pith.science/pith/S3YU4SGRTZ2DEQKBZK33L7DHW5/action/author_attestation","sign_citation":"https://pith.science/pith/S3YU4SGRTZ2DEQKBZK33L7DHW5/action/citation_signature","submit_replication":"https://pith.science/pith/S3YU4SGRTZ2DEQKBZK33L7DHW5/action/replication_record"}},"created_at":"2026-07-05T10:28:29.260086+00:00","updated_at":"2026-07-05T10:28:29.260086+00:00"}