{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5VQIKDM52WS7LK5ORBEVZUNU4U","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":"f37aba2ae58d79d24d7c4526f7ad9d7faca80cf9be6850df8fdc0a67f5ad27bf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T22:04:42Z","title_canon_sha256":"9c5160770085b63d2cad057b447f6935430d7ff2f2fa25356cd5882c8d39a390"},"schema_version":"1.0","source":{"id":"2607.03614","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03614","created_at":"2026-07-07T02:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03614v1","created_at":"2026-07-07T02:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03614","created_at":"2026-07-07T02:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"5VQIKDM52WS7","created_at":"2026-07-07T02:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"5VQIKDM52WS7LK5O","created_at":"2026-07-07T02:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"5VQIKDM5","created_at":"2026-07-07T02:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:28f008028c7d3bc5a9694d55dd297beae740855b862d080172fb3fec6b01a567","target":"graph","created_at":"2026-07-07T02:17:57Z","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/2607.03614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial question answering is the dominant paradigm for evaluating spatial intelligence in Vision-Language Models (VLMs), but it leaves a complementary axis of spatial competence under-evaluated: holistic 3D layout inference, which predicts every visible object's pose and extent from a single image in a structured form. To this end, we introduce IDEAL-Bench, an evaluation suite that requires VLMs to predict structured 3D layouts on photorealistic indoor scenes across 10 room types, scored along five numerical dimensions and a perceptual render-and-compare protocol. By operating on semantically","authors_text":"Junwei Zhou, Youran Qu, Yuening Cai, Yu-Wing Tai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T22:04:42Z","title":"IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03614","kind":"arxiv","version":1},"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:b5001e6974edf170655454ceb60ec6927c4420a30788fe4371788a290b054f12","target":"record","created_at":"2026-07-07T02:17:57Z","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":"f37aba2ae58d79d24d7c4526f7ad9d7faca80cf9be6850df8fdc0a67f5ad27bf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T22:04:42Z","title_canon_sha256":"9c5160770085b63d2cad057b447f6935430d7ff2f2fa25356cd5882c8d39a390"},"schema_version":"1.0","source":{"id":"2607.03614","kind":"arxiv","version":1}},"canonical_sha256":"ed60850d9dd5a5f5abae88495cd1b4e50cd4b99a56c91c23bf7dfab37c6315ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed60850d9dd5a5f5abae88495cd1b4e50cd4b99a56c91c23bf7dfab37c6315ae","first_computed_at":"2026-07-07T02:17:57.515869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:57.515869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y0DyKylBC/Q8iqmXMAvPR4HBTWoIN2BdQSvHmds2x/JCaZT2t7IffyssUrdLWsaQNPaGpV77buMvvy4esWw/CQ==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:57.516697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03614","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5001e6974edf170655454ceb60ec6927c4420a30788fe4371788a290b054f12","sha256:28f008028c7d3bc5a9694d55dd297beae740855b862d080172fb3fec6b01a567"],"state_sha256":"b8060a6759cac1b578cf556e5683917d80c37c8f787cbdca46d64e7e3883ebbf"}