{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LG5OKHXJGHRS7B2ZX5RDKTUBVF","short_pith_number":"pith:LG5OKHXJ","schema_version":"1.0","canonical_sha256":"59bae51ee931e32f8759bf62354e81a9774bee397df4ab0050033e892b583ce6","source":{"kind":"arxiv","id":"2605.09883","version":2},"attestation_state":"computed","paper":{"title":"The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Current multimodal models achieve high visual reasoning scores by exploiting grid-based coordinates rather than understanding spatial relationships directly.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Brian Potetz, Chun-Ta Lu, Howard Zhou, Leonidas Guibas, Xia Hu, Zhenrui Yue, Zhicheng Wang","submitted_at":"2026-05-11T02:16:48Z","abstract_excerpt":"As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores genuinely reflect robust visual understanding? We identify a pervasive vulnerability, the Cartesian Shortcut: visual reasoning benchmarks prevalently build on orthogonal grid-based layouts that can be readily discretized into explicit textual coordinates. Models systematically exploit this property, heavily leveraging text-based deductive reasoning to assist visual problem-solving. To systematically dismantle this shortcut, we introduce Polaris-Benc"},"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":true},"canonical_record":{"source":{"id":"2605.09883","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T02:16:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cae32c8f94241fd2acec258b15935b72ecb8b85a67d2e53c2bb0a1d973c3da9c","abstract_canon_sha256":"d3ad5e1b5375361286f17b144713d09ba955fb5529b0bd13e7561262516f1bb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:48.359477Z","signature_b64":"wvTagwG7zhYYs0KtYU4yacRdqE0WwHRq2pSWrVUxaVkBVyD0/rzYwP5xxvlYwgV96D8GlavsJ0Vkw6daBtktBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59bae51ee931e32f8759bf62354e81a9774bee397df4ab0050033e892b583ce6","last_reissued_at":"2026-06-02T01:03:48.359039Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:48.359039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Current multimodal models achieve high visual reasoning scores by exploiting grid-based coordinates rather than understanding spatial relationships directly.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Brian Potetz, Chun-Ta Lu, Howard Zhou, Leonidas Guibas, Xia Hu, Zhenrui Yue, Zhicheng Wang","submitted_at":"2026-05-11T02:16:48Z","abstract_excerpt":"As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores genuinely reflect robust visual understanding? We identify a pervasive vulnerability, the Cartesian Shortcut: visual reasoning benchmarks prevalently build on orthogonal grid-based layouts that can be readily discretized into explicit textual coordinates. Models systematically exploit this property, heavily leveraging text-based deductive reasoning to assist visual problem-solving. To systematically dismantle this shortcut, we introduce Polaris-Benc"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"frontier models achieving 70--83% on Cartesian layouts collapse to 31--39% on Polar equivalents, with degradation persisting even under complete logical equivalence.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Re-formulating the 53 tasks in polar coordinates preserves identical logical constraints, task semantics, and difficulty levels without introducing unrelated visual or reasoning challenges.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MLLMs scoring 70-83% on Cartesian visual tasks drop to 31-39% on logically equivalent polar versions, exposing reliance on grid discretization shortcuts instead of topology-invariant reasoning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Current multimodal models achieve high visual reasoning scores by exploiting grid-based coordinates rather than understanding spatial relationships directly.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1d022bee5ea0b0d7c81f9907a34cec144035915baa3faf74646dfeb08409fbbd"},"source":{"id":"2605.09883","kind":"arxiv","version":2},"verdict":{"id":"f780797c-db83-4d4e-9bcd-12fd49b333ac","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T04:27:29.877728Z","strongest_claim":"frontier models achieving 70--83% on Cartesian layouts collapse to 31--39% on Polar equivalents, with degradation persisting even under complete logical equivalence.","one_line_summary":"MLLMs scoring 70-83% on Cartesian visual tasks drop to 31-39% on logically equivalent polar versions, exposing reliance on grid discretization shortcuts instead of topology-invariant reasoning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Re-formulating the 53 tasks in polar coordinates preserves identical logical constraints, task semantics, and difficulty levels without introducing unrelated visual or reasoning challenges.","pith_extraction_headline":"Current multimodal models achieve high visual reasoning scores by exploiting grid-based coordinates rather than understanding spatial relationships directly."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.09883/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T07:02:01.307430Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T16:34:30.941152Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T12:31:17.319580Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:51:27.939939Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"22823f736d95f2816c8dfba27a63b480d8dbb0cc161c220fce79e14a0e4df8da"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"73d59aaa90c4a5e5c14f1de4fcfd4a0c4c82cbc1a9f786a0ea9c9b99483cca57"},"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":"2605.09883","created_at":"2026-06-02T01:03:48.359092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.09883v2","created_at":"2026-06-02T01:03:48.359092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09883","created_at":"2026-06-02T01:03:48.359092+00:00"},{"alias_kind":"pith_short_12","alias_value":"LG5OKHXJGHRS","created_at":"2026-06-02T01:03:48.359092+00:00"},{"alias_kind":"pith_short_16","alias_value":"LG5OKHXJGHRS7B2Z","created_at":"2026-06-02T01:03:48.359092+00:00"},{"alias_kind":"pith_short_8","alias_value":"LG5OKHXJ","created_at":"2026-06-02T01:03:48.359092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF","json":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF.json","graph_json":"https://pith.science/api/pith-number/LG5OKHXJGHRS7B2ZX5RDKTUBVF/graph.json","events_json":"https://pith.science/api/pith-number/LG5OKHXJGHRS7B2ZX5RDKTUBVF/events.json","paper":"https://pith.science/paper/LG5OKHXJ"},"agent_actions":{"view_html":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF","download_json":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF.json","view_paper":"https://pith.science/paper/LG5OKHXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.09883&json=true","fetch_graph":"https://pith.science/api/pith-number/LG5OKHXJGHRS7B2ZX5RDKTUBVF/graph.json","fetch_events":"https://pith.science/api/pith-number/LG5OKHXJGHRS7B2ZX5RDKTUBVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/action/storage_attestation","attest_author":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/action/author_attestation","sign_citation":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/action/citation_signature","submit_replication":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/action/replication_record"}},"created_at":"2026-06-02T01:03:48.359092+00:00","updated_at":"2026-06-02T01:03:48.359092+00:00"}