{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LG5OKHXJGHRS7B2ZX5RDKTUBVF","short_pith_number":"pith:LG5OKHXJ","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"},"canonical_sha256":"59bae51ee931e32f8759bf62354e81a9774bee397df4ab0050033e892b583ce6","source":{"kind":"arxiv","id":"2605.09883","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09883","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09883v2","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09883","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"LG5OKHXJGHRS","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"LG5OKHXJGHRS7B2Z","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"LG5OKHXJ","created_at":"2026-06-02T01:03:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LG5OKHXJGHRS7B2ZX5RDKTUBVF","target":"record","payload":{"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"},"canonical_sha256":"59bae51ee931e32f8759bf62354e81a9774bee397df4ab0050033e892b583ce6","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"},"source_kind":"arxiv","source_id":"2605.09883","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P1NdE/Tf5QuvDQ9c+Mh1peNWRhxCHQDbdcvXgIABPww1xk/eupoAbr1swEain6BIB4JKERHcjLa2lNf4fRiOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:14:51.757334Z"},"content_sha256":"953ab874d2602b5cf73a94c9c6e6a7a50fab78e25acedf1486710c167514db1b","schema_version":"1.0","event_id":"sha256:953ab874d2602b5cf73a94c9c6e6a7a50fab78e25acedf1486710c167514db1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LG5OKHXJGHRS7B2ZX5RDKTUBVF","target":"graph","payload":{"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"},"verdict_id":"f780797c-db83-4d4e-9bcd-12fd49b333ac"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDU7fTVu1dptwFV1cgambv5DpNQs+Rx5z+vBfqaxi5OG8CZJ+ZxkuA1kNzPDBdBOx71yRJyL+C37+PwVt3I4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:14:51.758675Z"},"content_sha256":"06456c4404e75b9b7d2b99beccdf80ccec1b933353e3f069c49b34ffb85b94be","schema_version":"1.0","event_id":"sha256:06456c4404e75b9b7d2b99beccdf80ccec1b933353e3f069c49b34ffb85b94be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/bundle.json","state_url":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T17:14:51Z","links":{"resolver":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF","bundle":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/bundle.json","state":"https://pith.science/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LG5OKHXJGHRS7B2ZX5RDKTUBVF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LG5OKHXJGHRS7B2ZX5RDKTUBVF","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":"d3ad5e1b5375361286f17b144713d09ba955fb5529b0bd13e7561262516f1bb1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T02:16:48Z","title_canon_sha256":"cae32c8f94241fd2acec258b15935b72ecb8b85a67d2e53c2bb0a1d973c3da9c"},"schema_version":"1.0","source":{"id":"2605.09883","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09883","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09883v2","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09883","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"LG5OKHXJGHRS","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"LG5OKHXJGHRS7B2Z","created_at":"2026-06-02T01:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"LG5OKHXJ","created_at":"2026-06-02T01:03:48Z"}],"graph_snapshots":[{"event_id":"sha256:06456c4404e75b9b7d2b99beccdf80ccec1b933353e3f069c49b34ffb85b94be","target":"graph","created_at":"2026-06-02T01:03:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"frontier models achieving 70--83% on Cartesian layouts collapse to 31--39% on Polar equivalents, with degradation persisting even under complete logical equivalence."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Current multimodal models achieve high visual reasoning scores by exploiting grid-based coordinates rather than understanding spatial relationships directly."}],"snapshot_sha256":"1d022bee5ea0b0d7c81f9907a34cec144035915baa3faf74646dfeb08409fbbd"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"73d59aaa90c4a5e5c14f1de4fcfd4a0c4c82cbc1a9f786a0ea9c9b99483cca57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.09883/integrity.json","findings":[],"snapshot_sha256":"22823f736d95f2816c8dfba27a63b480d8dbb0cc161c220fce79e14a0e4df8da","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Brian Potetz, Chun-Ta Lu, Howard Zhou, Leonidas Guibas, Xia Hu, Zhenrui Yue, Zhicheng Wang","cross_cats":["cs.AI"],"headline":"Current multimodal models achieve high visual reasoning scores by exploiting grid-based coordinates rather than understanding spatial relationships directly.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T02:16:48Z","title":"The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.09883","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T04:27:29.877728Z","id":"f780797c-db83-4d4e-9bcd-12fd49b333ac","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Current multimodal models achieve high visual reasoning scores by exploiting grid-based coordinates rather than understanding spatial relationships directly.","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.","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."}},"verdict_id":"f780797c-db83-4d4e-9bcd-12fd49b333ac"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:953ab874d2602b5cf73a94c9c6e6a7a50fab78e25acedf1486710c167514db1b","target":"record","created_at":"2026-06-02T01:03:48Z","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":"d3ad5e1b5375361286f17b144713d09ba955fb5529b0bd13e7561262516f1bb1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T02:16:48Z","title_canon_sha256":"cae32c8f94241fd2acec258b15935b72ecb8b85a67d2e53c2bb0a1d973c3da9c"},"schema_version":"1.0","source":{"id":"2605.09883","kind":"arxiv","version":2}},"canonical_sha256":"59bae51ee931e32f8759bf62354e81a9774bee397df4ab0050033e892b583ce6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59bae51ee931e32f8759bf62354e81a9774bee397df4ab0050033e892b583ce6","first_computed_at":"2026-06-02T01:03:48.359039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:48.359039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wvTagwG7zhYYs0KtYU4yacRdqE0WwHRq2pSWrVUxaVkBVyD0/rzYwP5xxvlYwgV96D8GlavsJ0Vkw6daBtktBA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:48.359477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.09883","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:953ab874d2602b5cf73a94c9c6e6a7a50fab78e25acedf1486710c167514db1b","sha256:06456c4404e75b9b7d2b99beccdf80ccec1b933353e3f069c49b34ffb85b94be"],"state_sha256":"165514428bc5dcc81248b1635151032c2ea5dc6a6b2db0b18ee3732d79a17eb9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PMYMEo6naHAa5PW8rVEwwTZ5BJfc3qYn4dlTPT+FyC5wNg0NyA8X2fga+zFsQZDZ4Q1Y42Nu5+g3GN3ZyBMYBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:14:51.834841Z","bundle_sha256":"a34b0d10f48cbca486912548fa5e1f40be2f2b4e5b88108716180be560e2920e"}}