{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YCICNK5SIXSWPVM6APYV4ZBZPT","short_pith_number":"pith:YCICNK5S","schema_version":"1.0","canonical_sha256":"c09026abb245e567d59e03f15e64397cd69655c4835ac3f8696361f651f39e26","source":{"kind":"arxiv","id":"2607.22864","version":1},"attestation_state":"computed","paper":{"title":"Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alex Wong, Ben Boudaoud, Ekta Prashnani, Jae-Hyun Jung, Joohwan Kim, Patrick Rim, Peter Xenopoulos, Ruth Rosenholtz, Tom Long","submitted_at":"2026-07-24T19:09:25Z","abstract_excerpt":"Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing benchmarks evaluate these models as black boxes, limiting their ability to identify the underlying causes of lower performance: when a model fails a spatial reasoning task, it remains difficult to ascertain whether the hurdle is perceptual, such as recognizing object boundaries, or cognitive, such as reasoning about occlusion to infer hidden geometry. We introduce Spatial-IQ, a hierarchical diagnostic framework that decomposes object counting in stack"},"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":"2607.22864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T19:09:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"399709bd25ff39bd44f944f884ae8b8dab69cc2f67cd55c1591b71af10c02895","abstract_canon_sha256":"25e12f142c4de794efc7c4632f40a44e93658878f26246905bbcfb82f5c70a09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:59.150558Z","signature_b64":"c1GxCbqdUlfPNUygVzsWq75xQqODpY0DSLxw99iEjclyxQ2XW11DrjjpbgDd1TWFWrQe0TCqYaa5RQO9RiFdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c09026abb245e567d59e03f15e64397cd69655c4835ac3f8696361f651f39e26","last_reissued_at":"2026-07-28T00:21:59.149646Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:59.149646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alex Wong, Ben Boudaoud, Ekta Prashnani, Jae-Hyun Jung, Joohwan Kim, Patrick Rim, Peter Xenopoulos, Ruth Rosenholtz, Tom Long","submitted_at":"2026-07-24T19:09:25Z","abstract_excerpt":"Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing benchmarks evaluate these models as black boxes, limiting their ability to identify the underlying causes of lower performance: when a model fails a spatial reasoning task, it remains difficult to ascertain whether the hurdle is perceptual, such as recognizing object boundaries, or cognitive, such as reasoning about occlusion to infer hidden geometry. We introduce Spatial-IQ, a hierarchical diagnostic framework that decomposes object counting in stack"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22864","kind":"arxiv","version":1},"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/2607.22864/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":"2607.22864","created_at":"2026-07-28T00:21:59.150122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22864v1","created_at":"2026-07-28T00:21:59.150122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22864","created_at":"2026-07-28T00:21:59.150122+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCICNK5SIXSW","created_at":"2026-07-28T00:21:59.150122+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCICNK5SIXSWPVM6","created_at":"2026-07-28T00:21:59.150122+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCICNK5S","created_at":"2026-07-28T00:21:59.150122+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/YCICNK5SIXSWPVM6APYV4ZBZPT","json":"https://pith.science/pith/YCICNK5SIXSWPVM6APYV4ZBZPT.json","graph_json":"https://pith.science/api/pith-number/YCICNK5SIXSWPVM6APYV4ZBZPT/graph.json","events_json":"https://pith.science/api/pith-number/YCICNK5SIXSWPVM6APYV4ZBZPT/events.json","paper":"https://pith.science/paper/YCICNK5S"},"agent_actions":{"view_html":"https://pith.science/pith/YCICNK5SIXSWPVM6APYV4ZBZPT","download_json":"https://pith.science/pith/YCICNK5SIXSWPVM6APYV4ZBZPT.json","view_paper":"https://pith.science/paper/YCICNK5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22864&json=true","fetch_graph":"https://pith.science/api/pith-number/YCICNK5SIXSWPVM6APYV4ZBZPT/graph.json","fetch_events":"https://pith.science/api/pith-number/YCICNK5SIXSWPVM6APYV4ZBZPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCICNK5SIXSWPVM6APYV4ZBZPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCICNK5SIXSWPVM6APYV4ZBZPT/action/storage_attestation","attest_author":"https://pith.science/pith/YCICNK5SIXSWPVM6APYV4ZBZPT/action/author_attestation","sign_citation":"https://pith.science/pith/YCICNK5SIXSWPVM6APYV4ZBZPT/action/citation_signature","submit_replication":"https://pith.science/pith/YCICNK5SIXSWPVM6APYV4ZBZPT/action/replication_record"}},"created_at":"2026-07-28T00:21:59.150122+00:00","updated_at":"2026-07-28T00:21:59.150122+00:00"}