{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3AXFUYQFKM7JNMLJ3MMVZL6CV","short_pith_number":"pith:P3AXFUYQ","schema_version":"1.0","canonical_sha256":"7ec172d3102a99f4b58b4ed8cae57e1573bb47df4211764b79a90adc3313f917","source":{"kind":"arxiv","id":"2603.07751","version":2},"attestation_state":"computed","paper":{"title":"3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hai Lin, Hai-Tao Zheng, Shaoxiong Zhan, Shen Li, Wen Huang, Xiaodong Cai, Yanlin Lai, Zheng Liu, Zijian Lin","submitted_at":"2026-03-08T17:57:56Z","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"},"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":"2603.07751","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-08T17:57:56Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c53eaefc306213d204965e289e3b22ad82fbbab4af4682f8cc71961ee280c6a4","abstract_canon_sha256":"523d0144abd275e04adb4a7aed7a4411769d4d753850091135b36a0242a5cc73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:51.365722Z","signature_b64":"UgO2BHqXDaGHSMGOF+0lH6cwZnVpmSmk6CIu501g19ZwjneBjUn6f8fTaQBWnQsH/fefhBK7Z/XVAlcpDcgbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec172d3102a99f4b58b4ed8cae57e1573bb47df4211764b79a90adc3313f917","last_reissued_at":"2026-06-01T01:03:51.364510Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:51.364510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hai Lin, Hai-Tao Zheng, Shaoxiong Zhan, Shen Li, Wen Huang, Xiaodong Cai, Yanlin Lai, Zheng Liu, Zijian Lin","submitted_at":"2026-03-08T17:57:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.07751","kind":"arxiv","version":2},"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/2603.07751/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":"2603.07751","created_at":"2026-06-01T01:03:51.364719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.07751v2","created_at":"2026-06-01T01:03:51.364719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07751","created_at":"2026-06-01T01:03:51.364719+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3AXFUYQFKM7","created_at":"2026-06-01T01:03:51.364719+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3AXFUYQFKM7JNML","created_at":"2026-06-01T01:03:51.364719+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3AXFUYQ","created_at":"2026-06-01T01:03:51.364719+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/P3AXFUYQFKM7JNMLJ3MMVZL6CV","json":"https://pith.science/pith/P3AXFUYQFKM7JNMLJ3MMVZL6CV.json","graph_json":"https://pith.science/api/pith-number/P3AXFUYQFKM7JNMLJ3MMVZL6CV/graph.json","events_json":"https://pith.science/api/pith-number/P3AXFUYQFKM7JNMLJ3MMVZL6CV/events.json","paper":"https://pith.science/paper/P3AXFUYQ"},"agent_actions":{"view_html":"https://pith.science/pith/P3AXFUYQFKM7JNMLJ3MMVZL6CV","download_json":"https://pith.science/pith/P3AXFUYQFKM7JNMLJ3MMVZL6CV.json","view_paper":"https://pith.science/paper/P3AXFUYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.07751&json=true","fetch_graph":"https://pith.science/api/pith-number/P3AXFUYQFKM7JNMLJ3MMVZL6CV/graph.json","fetch_events":"https://pith.science/api/pith-number/P3AXFUYQFKM7JNMLJ3MMVZL6CV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3AXFUYQFKM7JNMLJ3MMVZL6CV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3AXFUYQFKM7JNMLJ3MMVZL6CV/action/storage_attestation","attest_author":"https://pith.science/pith/P3AXFUYQFKM7JNMLJ3MMVZL6CV/action/author_attestation","sign_citation":"https://pith.science/pith/P3AXFUYQFKM7JNMLJ3MMVZL6CV/action/citation_signature","submit_replication":"https://pith.science/pith/P3AXFUYQFKM7JNMLJ3MMVZL6CV/action/replication_record"}},"created_at":"2026-06-01T01:03:51.364719+00:00","updated_at":"2026-06-01T01:03:51.364719+00:00"}