{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P3AXFUYQFKM7JNMLJ3MMVZL6CV","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":"523d0144abd275e04adb4a7aed7a4411769d4d753850091135b36a0242a5cc73","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-08T17:57:56Z","title_canon_sha256":"c53eaefc306213d204965e289e3b22ad82fbbab4af4682f8cc71961ee280c6a4"},"schema_version":"1.0","source":{"id":"2603.07751","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.07751","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2603.07751v2","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07751","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"P3AXFUYQFKM7","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"P3AXFUYQFKM7JNML","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"P3AXFUYQ","created_at":"2026-06-01T01:03:51Z"}],"graph_snapshots":[{"event_id":"sha256:2f78a32a1a5455775ec179ade85aa37042faa201800150ef485115ca6d8b57d8","target":"graph","created_at":"2026-06-01T01:03:51Z","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/2603.07751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical ``spatial intelligence gap,'' where models fail to construct coherent 3D mental representations from 2D observations. We uncover this gap via diagnostic analyses showing the bottleneck is a missing view-consistent spatial interface rather than insufficient visual features or weak reasoning. To bridge this, we introduce \\textbf{3ViewSense}, a framework that grounds spatial reasoning in Ortho","authors_text":"Hai Lin, Hai-Tao Zheng, Shaoxiong Zhan, Shen Li, Wen Huang, Xiaodong Cai, Yanlin Lai, Zheng Liu, Zijian Lin","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-08T17:57:56Z","title":"3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.07751","kind":"arxiv","version":2},"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:d36fa1d4356dcda748caf819b9328886f6fd35b7cdcbf3a03572f2665682583f","target":"record","created_at":"2026-06-01T01:03:51Z","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":"523d0144abd275e04adb4a7aed7a4411769d4d753850091135b36a0242a5cc73","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-08T17:57:56Z","title_canon_sha256":"c53eaefc306213d204965e289e3b22ad82fbbab4af4682f8cc71961ee280c6a4"},"schema_version":"1.0","source":{"id":"2603.07751","kind":"arxiv","version":2}},"canonical_sha256":"7ec172d3102a99f4b58b4ed8cae57e1573bb47df4211764b79a90adc3313f917","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ec172d3102a99f4b58b4ed8cae57e1573bb47df4211764b79a90adc3313f917","first_computed_at":"2026-06-01T01:03:51.364510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:51.364510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UgO2BHqXDaGHSMGOF+0lH6cwZnVpmSmk6CIu501g19ZwjneBjUn6f8fTaQBWnQsH/fefhBK7Z/XVAlcpDcgbAQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:51.365722Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.07751","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d36fa1d4356dcda748caf819b9328886f6fd35b7cdcbf3a03572f2665682583f","sha256:2f78a32a1a5455775ec179ade85aa37042faa201800150ef485115ca6d8b57d8"],"state_sha256":"652f4c624be7fac0cac19e862cf24c360cc2e68e4036be9e839b392377ede73a"}