{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TFMNSCFJ4QMLNV5FGG4IQQGL5H","short_pith_number":"pith:TFMNSCFJ","schema_version":"1.0","canonical_sha256":"9958d908a9e418b6d7a531b88840cbe9cbd6707e993ae4a15f8b59b710c17879","source":{"kind":"arxiv","id":"2505.15623","version":1},"attestation_state":"computed","paper":{"title":"Can LLMs $\\textit{understand}$ Math? -- Exploring the Pitfalls in Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditeya Baral, Ayush Rajesh Jhaveri, Tiasa Singha Roy, Yusuf Baig","submitted_at":"2025-05-21T15:12:20Z","abstract_excerpt":"Large language models (LLMs) demonstrate considerable potential in various natural language tasks but face significant challenges in mathematical reasoning, particularly in executing precise, multi-step logic. However, current evaluation frameworks judge their performance solely based on accuracy, which only accounts for the final answer. This study explores these pitfalls by employing a novel evaluation framework. We propose an evaluation metric called the MAPLE score, which holistically quantifies reasoning misalignment by integrating error rates, redundancy, and validity."},"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":"2505.15623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:12:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2ebdb8d024fea0b2e7365c18d5d7e0a7a088578750a62b10603f7c94095ea0c1","abstract_canon_sha256":"6d781c43874044d48cf7e27adcf27b02f29fc13537b19c4be9537d740adab68b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:48.589793Z","signature_b64":"3vpB/XLCL378DfQpoc3l5niae3pGJAg5brhkHCDzPQBAeoFT7+xI9QghHNc0H9sCXnLNNO15fckhquKQ/D5CAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9958d908a9e418b6d7a531b88840cbe9cbd6707e993ae4a15f8b59b710c17879","last_reissued_at":"2026-07-05T11:06:48.589310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:48.589310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs $\\textit{understand}$ Math? -- Exploring the Pitfalls in Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditeya Baral, Ayush Rajesh Jhaveri, Tiasa Singha Roy, Yusuf Baig","submitted_at":"2025-05-21T15:12:20Z","abstract_excerpt":"Large language models (LLMs) demonstrate considerable potential in various natural language tasks but face significant challenges in mathematical reasoning, particularly in executing precise, multi-step logic. However, current evaluation frameworks judge their performance solely based on accuracy, which only accounts for the final answer. This study explores these pitfalls by employing a novel evaluation framework. We propose an evaluation metric called the MAPLE score, which holistically quantifies reasoning misalignment by integrating error rates, redundancy, and validity."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15623","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/2505.15623/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":"2505.15623","created_at":"2026-07-05T11:06:48.589377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15623v1","created_at":"2026-07-05T11:06:48.589377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15623","created_at":"2026-07-05T11:06:48.589377+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFMNSCFJ4QML","created_at":"2026-07-05T11:06:48.589377+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFMNSCFJ4QMLNV5F","created_at":"2026-07-05T11:06:48.589377+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFMNSCFJ","created_at":"2026-07-05T11:06:48.589377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFMNSCFJ4QMLNV5FGG4IQQGL5H","json":"https://pith.science/pith/TFMNSCFJ4QMLNV5FGG4IQQGL5H.json","graph_json":"https://pith.science/api/pith-number/TFMNSCFJ4QMLNV5FGG4IQQGL5H/graph.json","events_json":"https://pith.science/api/pith-number/TFMNSCFJ4QMLNV5FGG4IQQGL5H/events.json","paper":"https://pith.science/paper/TFMNSCFJ"},"agent_actions":{"view_html":"https://pith.science/pith/TFMNSCFJ4QMLNV5FGG4IQQGL5H","download_json":"https://pith.science/pith/TFMNSCFJ4QMLNV5FGG4IQQGL5H.json","view_paper":"https://pith.science/paper/TFMNSCFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15623&json=true","fetch_graph":"https://pith.science/api/pith-number/TFMNSCFJ4QMLNV5FGG4IQQGL5H/graph.json","fetch_events":"https://pith.science/api/pith-number/TFMNSCFJ4QMLNV5FGG4IQQGL5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFMNSCFJ4QMLNV5FGG4IQQGL5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFMNSCFJ4QMLNV5FGG4IQQGL5H/action/storage_attestation","attest_author":"https://pith.science/pith/TFMNSCFJ4QMLNV5FGG4IQQGL5H/action/author_attestation","sign_citation":"https://pith.science/pith/TFMNSCFJ4QMLNV5FGG4IQQGL5H/action/citation_signature","submit_replication":"https://pith.science/pith/TFMNSCFJ4QMLNV5FGG4IQQGL5H/action/replication_record"}},"created_at":"2026-07-05T11:06:48.589377+00:00","updated_at":"2026-07-05T11:06:48.589377+00:00"}