{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JAYHGPVXRAO3C5V2DYFBUNGCSK","short_pith_number":"pith:JAYHGPVX","canonical_record":{"source":{"id":"2502.11492","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T06:54:49Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"76ba7081a4fe8a265de959299de502bfdea8bdc7f20269718a3df397b4812198","abstract_canon_sha256":"6a0d2202eaf38450efa9053fc29830832d411eec725629831c971be42ba65761"},"schema_version":"1.0"},"canonical_sha256":"4830733eb7881db176ba1e0a1a34c292a0aa0e4872cd808302d7e2bd9708cb34","source":{"kind":"arxiv","id":"2502.11492","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11492","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11492v3","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11492","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"JAYHGPVXRAO3","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"JAYHGPVXRAO3C5V2","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"JAYHGPVX","created_at":"2026-07-05T11:09:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JAYHGPVXRAO3C5V2DYFBUNGCSK","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11492","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T06:54:49Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"76ba7081a4fe8a265de959299de502bfdea8bdc7f20269718a3df397b4812198","abstract_canon_sha256":"6a0d2202eaf38450efa9053fc29830832d411eec725629831c971be42ba65761"},"schema_version":"1.0"},"canonical_sha256":"4830733eb7881db176ba1e0a1a34c292a0aa0e4872cd808302d7e2bd9708cb34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:08.505880Z","signature_b64":"gkoGD019isC3HkDljTALP2+CmDAmWK8FUeR6/NTD9tF3QFs+RpK/Ka7NN+aVfco2BjMH9rgPrq8ZVKVhDQ15Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4830733eb7881db176ba1e0a1a34c292a0aa0e4872cd808302d7e2bd9708cb34","last_reissued_at":"2026-07-05T11:09:08.505448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:08.505448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11492","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZIHgzSjIJ4vRzdpw799fRF6bP+G03wZf84JF3+7IByGLRUB0+0qXoWkTSb0FKlu9S3k7Qnp8+2rngClGDXIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:51:12.440678Z"},"content_sha256":"6107cb45ce2a8d78ad6228717d3f1fea51b37cb8d5329e6d4a47cee04c0fb4d3","schema_version":"1.0","event_id":"sha256:6107cb45ce2a8d78ad6228717d3f1fea51b37cb8d5329e6d4a47cee04c0fb4d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JAYHGPVXRAO3C5V2DYFBUNGCSK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Caiming Xiong, Can Qin, Chien-Sheng Wu, Haoyi Qiu, Kung-Hsiang Huang, Philippe Laban, Shafiq Joty","submitted_at":"2025-02-17T06:54:49Z","abstract_excerpt":"Vision Language Models (VLMs) have achieved remarkable progress in multimodal tasks, yet they often struggle with visual arithmetic, seemingly simple capabilities like object counting or length comparison, which are essential for relevant complex tasks like chart understanding and geometric reasoning. In this work, we first investigate the root causes of this deficiency through a suite of probing tasks focusing on basic visual arithmetic. Our analysis reveals that while pre-trained vision encoders typically capture sufficient information, the text decoder often fails to decode it correctly for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11492","kind":"arxiv","version":3},"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/2502.11492/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qdSTKOw2q4PpZoukEuPFeZwBXCQEYZHTKMg73LhYMJXOeUaUOTjBfh7FqkEszk5bHtmbwH5CAPLpagVWZkHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:51:12.441193Z"},"content_sha256":"e2ab20422bb5716dfeadcae26300de6d1902bd530c1ee94b206a2fe34df5a571","schema_version":"1.0","event_id":"sha256:e2ab20422bb5716dfeadcae26300de6d1902bd530c1ee94b206a2fe34df5a571"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JAYHGPVXRAO3C5V2DYFBUNGCSK/bundle.json","state_url":"https://pith.science/pith/JAYHGPVXRAO3C5V2DYFBUNGCSK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JAYHGPVXRAO3C5V2DYFBUNGCSK/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":"2026-08-08T13:51:12Z","links":{"resolver":"https://pith.science/pith/JAYHGPVXRAO3C5V2DYFBUNGCSK","bundle":"https://pith.science/pith/JAYHGPVXRAO3C5V2DYFBUNGCSK/bundle.json","state":"https://pith.science/pith/JAYHGPVXRAO3C5V2DYFBUNGCSK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JAYHGPVXRAO3C5V2DYFBUNGCSK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JAYHGPVXRAO3C5V2DYFBUNGCSK","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":"6a0d2202eaf38450efa9053fc29830832d411eec725629831c971be42ba65761","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T06:54:49Z","title_canon_sha256":"76ba7081a4fe8a265de959299de502bfdea8bdc7f20269718a3df397b4812198"},"schema_version":"1.0","source":{"id":"2502.11492","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11492","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11492v3","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11492","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"JAYHGPVXRAO3","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"JAYHGPVXRAO3C5V2","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"JAYHGPVX","created_at":"2026-07-05T11:09:08Z"}],"graph_snapshots":[{"event_id":"sha256:e2ab20422bb5716dfeadcae26300de6d1902bd530c1ee94b206a2fe34df5a571","target":"graph","created_at":"2026-07-05T11:09:08Z","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/2502.11492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) have achieved remarkable progress in multimodal tasks, yet they often struggle with visual arithmetic, seemingly simple capabilities like object counting or length comparison, which are essential for relevant complex tasks like chart understanding and geometric reasoning. In this work, we first investigate the root causes of this deficiency through a suite of probing tasks focusing on basic visual arithmetic. Our analysis reveals that while pre-trained vision encoders typically capture sufficient information, the text decoder often fails to decode it correctly for","authors_text":"Caiming Xiong, Can Qin, Chien-Sheng Wu, Haoyi Qiu, Kung-Hsiang Huang, Philippe Laban, Shafiq Joty","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T06:54:49Z","title":"Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11492","kind":"arxiv","version":3},"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":"sha256:6107cb45ce2a8d78ad6228717d3f1fea51b37cb8d5329e6d4a47cee04c0fb4d3","target":"record","created_at":"2026-07-05T11:09:08Z","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":"6a0d2202eaf38450efa9053fc29830832d411eec725629831c971be42ba65761","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T06:54:49Z","title_canon_sha256":"76ba7081a4fe8a265de959299de502bfdea8bdc7f20269718a3df397b4812198"},"schema_version":"1.0","source":{"id":"2502.11492","kind":"arxiv","version":3}},"canonical_sha256":"4830733eb7881db176ba1e0a1a34c292a0aa0e4872cd808302d7e2bd9708cb34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4830733eb7881db176ba1e0a1a34c292a0aa0e4872cd808302d7e2bd9708cb34","first_computed_at":"2026-07-05T11:09:08.505448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:08.505448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gkoGD019isC3HkDljTALP2+CmDAmWK8FUeR6/NTD9tF3QFs+RpK/Ka7NN+aVfco2BjMH9rgPrq8ZVKVhDQ15Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:08.505880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11492","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6107cb45ce2a8d78ad6228717d3f1fea51b37cb8d5329e6d4a47cee04c0fb4d3","sha256:e2ab20422bb5716dfeadcae26300de6d1902bd530c1ee94b206a2fe34df5a571"],"state_sha256":"61c74c28c481db817a46fe3c599636b4748d69e57893fbfeaa9b11bfe29058b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RTy8KSZwYdSYT28ooMKrgWn3ywhvXxAnDc/S9IicVdR1qa+LjTWBj2Gkct9Neb0D/1KZU0i1VC9ahkWru1PGDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:51:12.446284Z","bundle_sha256":"c44e9718dcd8f46d3ecb4232eda01258c79d8b96a50afdbb2003f9bdb732b390"}}