{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S3YU4SGRTZ2DEQKBZK33L7DHW5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aa06bb6948520e1a029aab513ad0471107655338fea26f7e0ccf5d7dc31bcfe6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T06:15:04Z","title_canon_sha256":"1e717cdec0a9e761b4bacf91029238e7d16a222a2be469137576a7f903819950"},"schema_version":"1.0","source":{"id":"2412.02193","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02193","created_at":"2026-07-05T10:28:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02193v3","created_at":"2026-07-05T10:28:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02193","created_at":"2026-07-05T10:28:29Z"},{"alias_kind":"pith_short_12","alias_value":"S3YU4SGRTZ2D","created_at":"2026-07-05T10:28:29Z"},{"alias_kind":"pith_short_16","alias_value":"S3YU4SGRTZ2DEQKB","created_at":"2026-07-05T10:28:29Z"},{"alias_kind":"pith_short_8","alias_value":"S3YU4SGR","created_at":"2026-07-05T10:28:29Z"}],"graph_snapshots":[{"event_id":"sha256:486b8d44d29039c1eb325496128ed4c17fd4294e5f28825f816f7a2cfc21df88","target":"graph","created_at":"2026-07-05T10:28:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.02193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dylan Lim, Fan-Yun Sun, Federico Tombari, Goutam Bhat, Jiajun Wu, Manling Li, Nick Haber, Siyi Gu, Weiyu Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T06:15:04Z","title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02193","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:39c909590f27d72e3643be171df6d2e8527f1ae320e5103ee4420e7d9cdf8c8c","target":"record","created_at":"2026-07-05T10:28:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aa06bb6948520e1a029aab513ad0471107655338fea26f7e0ccf5d7dc31bcfe6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T06:15:04Z","title_canon_sha256":"1e717cdec0a9e761b4bacf91029238e7d16a222a2be469137576a7f903819950"},"schema_version":"1.0","source":{"id":"2412.02193","kind":"arxiv","version":3}},"canonical_sha256":"96f14e48d19e74324141cab7b5fc67b76cea19da86a8f108d9b630e4ed6e055d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96f14e48d19e74324141cab7b5fc67b76cea19da86a8f108d9b630e4ed6e055d","first_computed_at":"2026-07-05T10:28:29.260028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:29.260028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XNAJl+G+TDqA6341BV0p8RjDEvWHMEsnncocW9Q0n2e821E+Nww+LH4Rtv14G5W8/nhwNU/nVMlhpMSU7zIrAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:29.260517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02193","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39c909590f27d72e3643be171df6d2e8527f1ae320e5103ee4420e7d9cdf8c8c","sha256:486b8d44d29039c1eb325496128ed4c17fd4294e5f28825f816f7a2cfc21df88"],"state_sha256":"fc7e4a924198ca30fe4ec92e205d3293d92803bbea5548dcf61b9d21f4c22941"}