{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6K7QBDM4OT3MPBCHOMDJBOFJXS","short_pith_number":"pith:6K7QBDM4","schema_version":"1.0","canonical_sha256":"f2bf008d9c74f6c78447730690b8a9bc984e64f5be1a6c7a8f0c75822ba8ace9","source":{"kind":"arxiv","id":"2406.15736","version":2},"attestation_state":"computed","paper":{"title":"Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Anoop Cherian, Joanna Matthiesen, Joshua B. Tenenbaum, Kevin Smith, Kuan-Chuan Peng, Suhas Lohit","submitted_at":"2024-06-22T05:04:39Z","abstract_excerpt":"Recent years have seen a significant progress in the general-purpose problem solving abilities of large vision and language models (LVLMs), such as ChatGPT, Gemini, etc.; some of these breakthroughs even seem to enable AI models to outperform human abilities in varied tasks that demand higher-order cognitive skills. Are the current large AI models indeed capable of generalized problem solving as humans do? A systematic analysis of AI capabilities for joint vision and text reasoning, however, is missing in the current scientific literature. In this paper, we make an effort towards filling this "},"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":"2406.15736","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-22T05:04:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"dfcdef1322a586f16890d71bc869b663b1e3818983c6072fe4a7e6cedff4d29c","abstract_canon_sha256":"672da25757460424df8282ce187aad4cb29d68981ffef28140e78567b1f0f309"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:11.144758Z","signature_b64":"NPJHxCuQRFyiI767uG9GqcACLo41Ch2l+HxdQ9xStzSozg/19os0oK73t1c1rbEUBiuAlsvmu7j3PMXYbsRiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2bf008d9c74f6c78447730690b8a9bc984e64f5be1a6c7a8f0c75822ba8ace9","last_reissued_at":"2026-07-05T09:45:11.144270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:11.144270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Anoop Cherian, Joanna Matthiesen, Joshua B. Tenenbaum, Kevin Smith, Kuan-Chuan Peng, Suhas Lohit","submitted_at":"2024-06-22T05:04:39Z","abstract_excerpt":"Recent years have seen a significant progress in the general-purpose problem solving abilities of large vision and language models (LVLMs), such as ChatGPT, Gemini, etc.; some of these breakthroughs even seem to enable AI models to outperform human abilities in varied tasks that demand higher-order cognitive skills. Are the current large AI models indeed capable of generalized problem solving as humans do? A systematic analysis of AI capabilities for joint vision and text reasoning, however, is missing in the current scientific literature. In this paper, we make an effort towards filling this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15736","kind":"arxiv","version":2},"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/2406.15736/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":"2406.15736","created_at":"2026-07-05T09:45:11.144332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15736v2","created_at":"2026-07-05T09:45:11.144332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15736","created_at":"2026-07-05T09:45:11.144332+00:00"},{"alias_kind":"pith_short_12","alias_value":"6K7QBDM4OT3M","created_at":"2026-07-05T09:45:11.144332+00:00"},{"alias_kind":"pith_short_16","alias_value":"6K7QBDM4OT3MPBCH","created_at":"2026-07-05T09:45:11.144332+00:00"},{"alias_kind":"pith_short_8","alias_value":"6K7QBDM4","created_at":"2026-07-05T09:45:11.144332+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11936","citing_title":"A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6K7QBDM4OT3MPBCHOMDJBOFJXS","json":"https://pith.science/pith/6K7QBDM4OT3MPBCHOMDJBOFJXS.json","graph_json":"https://pith.science/api/pith-number/6K7QBDM4OT3MPBCHOMDJBOFJXS/graph.json","events_json":"https://pith.science/api/pith-number/6K7QBDM4OT3MPBCHOMDJBOFJXS/events.json","paper":"https://pith.science/paper/6K7QBDM4"},"agent_actions":{"view_html":"https://pith.science/pith/6K7QBDM4OT3MPBCHOMDJBOFJXS","download_json":"https://pith.science/pith/6K7QBDM4OT3MPBCHOMDJBOFJXS.json","view_paper":"https://pith.science/paper/6K7QBDM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15736&json=true","fetch_graph":"https://pith.science/api/pith-number/6K7QBDM4OT3MPBCHOMDJBOFJXS/graph.json","fetch_events":"https://pith.science/api/pith-number/6K7QBDM4OT3MPBCHOMDJBOFJXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6K7QBDM4OT3MPBCHOMDJBOFJXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6K7QBDM4OT3MPBCHOMDJBOFJXS/action/storage_attestation","attest_author":"https://pith.science/pith/6K7QBDM4OT3MPBCHOMDJBOFJXS/action/author_attestation","sign_citation":"https://pith.science/pith/6K7QBDM4OT3MPBCHOMDJBOFJXS/action/citation_signature","submit_replication":"https://pith.science/pith/6K7QBDM4OT3MPBCHOMDJBOFJXS/action/replication_record"}},"created_at":"2026-07-05T09:45:11.144332+00:00","updated_at":"2026-07-05T09:45:11.144332+00:00"}