{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TFMNSCFJ4QMLNV5FGG4IQQGL5H","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":"6d781c43874044d48cf7e27adcf27b02f29fc13537b19c4be9537d740adab68b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:12:20Z","title_canon_sha256":"2ebdb8d024fea0b2e7365c18d5d7e0a7a088578750a62b10603f7c94095ea0c1"},"schema_version":"1.0","source":{"id":"2505.15623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15623","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15623v1","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15623","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"TFMNSCFJ4QML","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"TFMNSCFJ4QMLNV5F","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"TFMNSCFJ","created_at":"2026-07-05T11:06:48Z"}],"graph_snapshots":[{"event_id":"sha256:4415e61482c943088bf79fd3eb55ea550a648d6a4d9db108e4d03f770f98418c","target":"graph","created_at":"2026-07-05T11:06:48Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.15623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Aditeya Baral, Ayush Rajesh Jhaveri, Tiasa Singha Roy, Yusuf Baig","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:12:20Z","title":"Can LLMs $\\textit{understand}$ Math? -- Exploring the Pitfalls in Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15623","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:d93e9b4221e23a88face220ce0c7ce7626bfbe2f9daa8f51696b740be36e62b8","target":"record","created_at":"2026-07-05T11:06:48Z","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":"6d781c43874044d48cf7e27adcf27b02f29fc13537b19c4be9537d740adab68b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T15:12:20Z","title_canon_sha256":"2ebdb8d024fea0b2e7365c18d5d7e0a7a088578750a62b10603f7c94095ea0c1"},"schema_version":"1.0","source":{"id":"2505.15623","kind":"arxiv","version":1}},"canonical_sha256":"9958d908a9e418b6d7a531b88840cbe9cbd6707e993ae4a15f8b59b710c17879","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9958d908a9e418b6d7a531b88840cbe9cbd6707e993ae4a15f8b59b710c17879","first_computed_at":"2026-07-05T11:06:48.589310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:48.589310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3vpB/XLCL378DfQpoc3l5niae3pGJAg5brhkHCDzPQBAeoFT7+xI9QghHNc0H9sCXnLNNO15fckhquKQ/D5CAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:48.589793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d93e9b4221e23a88face220ce0c7ce7626bfbe2f9daa8f51696b740be36e62b8","sha256:4415e61482c943088bf79fd3eb55ea550a648d6a4d9db108e4d03f770f98418c"],"state_sha256":"43e5d9ce98ffe0d3af4c11973ef9c8c59e206e9587f070cf5f4f428c4c90d407"}