{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YRAVJDS5WIH2I27PH5Z7MR6HDJ","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":"8b55305dcf3901e383026e7b8365603acb82d53d86bfd75053a5ab37c7752416","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-03T21:19:50Z","title_canon_sha256":"1f822b18c55b4958b6d87983eab8d8ec393df3e9d52549df5f82e5bd5f7fc8bd"},"schema_version":"1.0","source":{"id":"2310.02439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02439","created_at":"2026-07-05T06:56:57Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02439v1","created_at":"2026-07-05T06:56:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02439","created_at":"2026-07-05T06:56:57Z"},{"alias_kind":"pith_short_12","alias_value":"YRAVJDS5WIH2","created_at":"2026-07-05T06:56:57Z"},{"alias_kind":"pith_short_16","alias_value":"YRAVJDS5WIH2I27P","created_at":"2026-07-05T06:56:57Z"},{"alias_kind":"pith_short_8","alias_value":"YRAVJDS5","created_at":"2026-07-05T06:56:57Z"}],"graph_snapshots":[{"event_id":"sha256:17d80a457f89c29592ab904c7eab178115218d3caca78d1682aa7e5ba91a62ed","target":"graph","created_at":"2026-07-05T06:56:57Z","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/2310.02439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose novel evaluations for mathematical reasoning capabilities of Large Language Models (LLMs) based on mathematical misconceptions. Our primary approach is to simulate LLMs as a novice learner and an expert tutor, aiming to identify the incorrect answer to math question resulted from a specific misconception and to recognize the misconception(s) behind an incorrect answer, respectively. Contrary to traditional LLMs-based mathematical evaluations that focus on answering math questions correctly, our approach takes inspirations from principles in educational learning sciences. We explicit","authors_text":"Naiming Liu, Richard G. Baraniuk, Shashank Sonkar, Simon Woodhead, Zichao Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-03T21:19:50Z","title":"Novice Learner and Expert Tutor: Evaluating Math Reasoning Abilities of Large Language Models with Misconceptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02439","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":"sha256:551046abe317102402fc7cdf62bab7c5df07e51f9f4a662113ae552b1cae5c88","target":"record","created_at":"2026-07-05T06:56:57Z","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":"8b55305dcf3901e383026e7b8365603acb82d53d86bfd75053a5ab37c7752416","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-03T21:19:50Z","title_canon_sha256":"1f822b18c55b4958b6d87983eab8d8ec393df3e9d52549df5f82e5bd5f7fc8bd"},"schema_version":"1.0","source":{"id":"2310.02439","kind":"arxiv","version":1}},"canonical_sha256":"c441548e5db20fa46bef3f73f647c71a5fa4249e62b8c2332b408ba61d2f2ca3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c441548e5db20fa46bef3f73f647c71a5fa4249e62b8c2332b408ba61d2f2ca3","first_computed_at":"2026-07-05T06:56:57.364287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:57.364287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FvXmDnhyHFqzVhUpoNwCm4xneVworSQFLca0SBwcRlz9HFIQxwc66IGaiKx8f/xHTfwhR4eWbBqYnTB6WwWACA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:57.364794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:551046abe317102402fc7cdf62bab7c5df07e51f9f4a662113ae552b1cae5c88","sha256:17d80a457f89c29592ab904c7eab178115218d3caca78d1682aa7e5ba91a62ed"],"state_sha256":"1f909c6cff7b9ff28689ee346d667d0d5fa4cab11734904a4a5fd6edcc48fec2"}