{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LTQFTQ46PCFP3JSYMF4PD76CL5","short_pith_number":"pith:LTQFTQ46","canonical_record":{"source":{"id":"2506.07418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T04:35:02Z","cross_cats_sorted":[],"title_canon_sha256":"4da1603ced32458489c846dd1b39ec5d00db1671544c508cc9291e4613674ed8","abstract_canon_sha256":"86b7c54b86943229028b63fbae7b47fe658c907f1f82452cbb01d37ab1a08f52"},"schema_version":"1.0"},"canonical_sha256":"5ce059c39e788afda6586178f1ffc25f612e79c9edc6a1393fe9343159728eca","source":{"kind":"arxiv","id":"2506.07418","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07418","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07418v1","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07418","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"LTQFTQ46PCFP","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"LTQFTQ46PCFP3JSY","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"LTQFTQ46","created_at":"2026-07-05T11:18:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LTQFTQ46PCFP3JSYMF4PD76CL5","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T04:35:02Z","cross_cats_sorted":[],"title_canon_sha256":"4da1603ced32458489c846dd1b39ec5d00db1671544c508cc9291e4613674ed8","abstract_canon_sha256":"86b7c54b86943229028b63fbae7b47fe658c907f1f82452cbb01d37ab1a08f52"},"schema_version":"1.0"},"canonical_sha256":"5ce059c39e788afda6586178f1ffc25f612e79c9edc6a1393fe9343159728eca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:26.922922Z","signature_b64":"444AFPTI6ISpzZ6bT0MvHEU7F4/n7IR1OlejvVS+c/cpJwdX+aRqL59sG4rym7fD9QHOmjB6eWt6ZdpQJjPGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ce059c39e788afda6586178f1ffc25f612e79c9edc6a1393fe9343159728eca","last_reissued_at":"2026-07-05T11:18:26.922426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:26.922426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07418","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9kwYMdGVi/LTQxjo9SLiNJCBA0htV+aKvFJPT10RDDQmrUL7nhJoP6kzvD4LDpgfhOhB0tjV9mLbGbgaxxQSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:11:30.762202Z"},"content_sha256":"6b420852a4ae441240a304d13ee9555b4aaa51d204b257dad8361db873f535d7","schema_version":"1.0","event_id":"sha256:6b420852a4ae441240a304d13ee9555b4aaa51d204b257dad8361db873f535d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LTQFTQ46PCFP3JSYMF4PD76CL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Visual Mathematics in Multimodal LLMs: A Multilingual Benchmark Based on the Kangaroo Tests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Arnau Igualde S\\'aez, J. Alberto Conejero, Jose P. Garc\\'ia Sabater, Lamyae Rhomrasi, Marius J. Fullana i Alfonso, Ricardo Vinuesa, Sergio Hoyas, Yusef Ahsini","submitted_at":"2025-06-09T04:35:02Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) promise advanced vision language capabilities, yet their effectiveness in visually presented mathematics remains underexplored. This paper analyzes the development and evaluation of MLLMs for mathematical problem solving, focusing on diagrams, multilingual text, and symbolic notation. We then assess several models, including GPT 4o, Pixtral, Qwen VL, Llama 3.2 Vision variants, and Gemini 2.0 Flash in a multilingual Kangaroo style benchmark spanning English, French, Spanish, and Catalan. Our experiments reveal four key findings. First, overall precision "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07418","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/2506.07418/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":"2026-07-05T11:18:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HxGhHZJNqOnMGxQ3uYi2U87NfV5AlrtdrPCBGtlcppSCtrZZb0jcR2CDwud/0J+dXaSpciiZEARxtFITY3MzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:11:30.762954Z"},"content_sha256":"23c1e96e7853baa1decc1a1124e17740865f8b989d5da2aaf179158d6c8cb8f3","schema_version":"1.0","event_id":"sha256:23c1e96e7853baa1decc1a1124e17740865f8b989d5da2aaf179158d6c8cb8f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LTQFTQ46PCFP3JSYMF4PD76CL5/bundle.json","state_url":"https://pith.science/pith/LTQFTQ46PCFP3JSYMF4PD76CL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LTQFTQ46PCFP3JSYMF4PD76CL5/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":"2026-08-07T21:11:30Z","links":{"resolver":"https://pith.science/pith/LTQFTQ46PCFP3JSYMF4PD76CL5","bundle":"https://pith.science/pith/LTQFTQ46PCFP3JSYMF4PD76CL5/bundle.json","state":"https://pith.science/pith/LTQFTQ46PCFP3JSYMF4PD76CL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LTQFTQ46PCFP3JSYMF4PD76CL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LTQFTQ46PCFP3JSYMF4PD76CL5","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":"86b7c54b86943229028b63fbae7b47fe658c907f1f82452cbb01d37ab1a08f52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T04:35:02Z","title_canon_sha256":"4da1603ced32458489c846dd1b39ec5d00db1671544c508cc9291e4613674ed8"},"schema_version":"1.0","source":{"id":"2506.07418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07418","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07418v1","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07418","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"LTQFTQ46PCFP","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"LTQFTQ46PCFP3JSY","created_at":"2026-07-05T11:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"LTQFTQ46","created_at":"2026-07-05T11:18:26Z"}],"graph_snapshots":[{"event_id":"sha256:23c1e96e7853baa1decc1a1124e17740865f8b989d5da2aaf179158d6c8cb8f3","target":"graph","created_at":"2026-07-05T11:18:26Z","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/2506.07418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) promise advanced vision language capabilities, yet their effectiveness in visually presented mathematics remains underexplored. This paper analyzes the development and evaluation of MLLMs for mathematical problem solving, focusing on diagrams, multilingual text, and symbolic notation. We then assess several models, including GPT 4o, Pixtral, Qwen VL, Llama 3.2 Vision variants, and Gemini 2.0 Flash in a multilingual Kangaroo style benchmark spanning English, French, Spanish, and Catalan. Our experiments reveal four key findings. First, overall precision ","authors_text":"Arnau Igualde S\\'aez, J. Alberto Conejero, Jose P. Garc\\'ia Sabater, Lamyae Rhomrasi, Marius J. Fullana i Alfonso, Ricardo Vinuesa, Sergio Hoyas, Yusef Ahsini","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T04:35:02Z","title":"Evaluating Visual Mathematics in Multimodal LLMs: A Multilingual Benchmark Based on the Kangaroo Tests"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07418","kind":"arxiv","version":1},"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":"sha256:6b420852a4ae441240a304d13ee9555b4aaa51d204b257dad8361db873f535d7","target":"record","created_at":"2026-07-05T11:18:26Z","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":"86b7c54b86943229028b63fbae7b47fe658c907f1f82452cbb01d37ab1a08f52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-09T04:35:02Z","title_canon_sha256":"4da1603ced32458489c846dd1b39ec5d00db1671544c508cc9291e4613674ed8"},"schema_version":"1.0","source":{"id":"2506.07418","kind":"arxiv","version":1}},"canonical_sha256":"5ce059c39e788afda6586178f1ffc25f612e79c9edc6a1393fe9343159728eca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ce059c39e788afda6586178f1ffc25f612e79c9edc6a1393fe9343159728eca","first_computed_at":"2026-07-05T11:18:26.922426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:26.922426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"444AFPTI6ISpzZ6bT0MvHEU7F4/n7IR1OlejvVS+c/cpJwdX+aRqL59sG4rym7fD9QHOmjB6eWt6ZdpQJjPGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:26.922922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b420852a4ae441240a304d13ee9555b4aaa51d204b257dad8361db873f535d7","sha256:23c1e96e7853baa1decc1a1124e17740865f8b989d5da2aaf179158d6c8cb8f3"],"state_sha256":"3fb02a6afdbc8ac7f8dc4c680808d7247f27ff5442d1b5f9dbae66b97037fbdd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sAClwzGEer4xiW/egenY/APoc/R/BLQqB+AAvPc1u7hN1hU4INXzPkB6PoItdW+LhnmCyJWbiuoRluCNwq1TCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:11:30.781904Z","bundle_sha256":"8cbd6b160882b4e02f4cba0093472e159321f55424253ca3bba1f613dafed734"}}