{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XR2WMGCW7E2SMTQWCXZEDKVXTW","short_pith_number":"pith:XR2WMGCW","schema_version":"1.0","canonical_sha256":"bc75661856f935264e1615f241aab79db905734d1f0d8e55bac8d320312df97b","source":{"kind":"arxiv","id":"2311.07618","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models' Understanding of Math: Source Criticism and Extrapolation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","math.HO"],"primary_cat":"cs.LG","authors_text":"Roozbeh Yousefzadeh, Xuenan Cao","submitted_at":"2023-11-12T07:52:32Z","abstract_excerpt":"It has been suggested that large language models such as GPT-4 have acquired some form of understanding beyond the correlations among the words in text including some understanding of mathematics as well. Here, we perform a critical inquiry into this claim by evaluating the mathematical understanding of the GPT-4 model. Considering that GPT-4's training set is a secret, it is not straightforward to evaluate whether the model's correct answers are based on a mathematical understanding or based on replication of proofs that the model has seen before. We specifically craft mathematical questions "},"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":"2311.07618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-12T07:52:32Z","cross_cats_sorted":["cs.AI","cs.CL","math.HO"],"title_canon_sha256":"4c540d676a994b0f2d37b08f271b02e5c81cf3c4736bbb9b4892cdc42ee458d1","abstract_canon_sha256":"1d6a3ad984c44dc4eaec449e94edfd211ed2f6bdde80f96ce91209d2f504bed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:21.172084Z","signature_b64":"p6PEhXBwe1ozh7ErtbEnE1d0ZTTTkW08vf0/F5PZ2t91d7QkKKZ9FkkKAtLYGosh/VoZVOPU94aSG99SXSUyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc75661856f935264e1615f241aab79db905734d1f0d8e55bac8d320312df97b","last_reissued_at":"2026-07-05T07:12:21.171752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:21.171752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models' Understanding of Math: Source Criticism and Extrapolation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","math.HO"],"primary_cat":"cs.LG","authors_text":"Roozbeh Yousefzadeh, Xuenan Cao","submitted_at":"2023-11-12T07:52:32Z","abstract_excerpt":"It has been suggested that large language models such as GPT-4 have acquired some form of understanding beyond the correlations among the words in text including some understanding of mathematics as well. Here, we perform a critical inquiry into this claim by evaluating the mathematical understanding of the GPT-4 model. Considering that GPT-4's training set is a secret, it is not straightforward to evaluate whether the model's correct answers are based on a mathematical understanding or based on replication of proofs that the model has seen before. We specifically craft mathematical questions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07618","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/2311.07618/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":"2311.07618","created_at":"2026-07-05T07:12:21.171807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07618v1","created_at":"2026-07-05T07:12:21.171807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07618","created_at":"2026-07-05T07:12:21.171807+00:00"},{"alias_kind":"pith_short_12","alias_value":"XR2WMGCW7E2S","created_at":"2026-07-05T07:12:21.171807+00:00"},{"alias_kind":"pith_short_16","alias_value":"XR2WMGCW7E2SMTQW","created_at":"2026-07-05T07:12:21.171807+00:00"},{"alias_kind":"pith_short_8","alias_value":"XR2WMGCW","created_at":"2026-07-05T07:12:21.171807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20047","citing_title":"Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XR2WMGCW7E2SMTQWCXZEDKVXTW","json":"https://pith.science/pith/XR2WMGCW7E2SMTQWCXZEDKVXTW.json","graph_json":"https://pith.science/api/pith-number/XR2WMGCW7E2SMTQWCXZEDKVXTW/graph.json","events_json":"https://pith.science/api/pith-number/XR2WMGCW7E2SMTQWCXZEDKVXTW/events.json","paper":"https://pith.science/paper/XR2WMGCW"},"agent_actions":{"view_html":"https://pith.science/pith/XR2WMGCW7E2SMTQWCXZEDKVXTW","download_json":"https://pith.science/pith/XR2WMGCW7E2SMTQWCXZEDKVXTW.json","view_paper":"https://pith.science/paper/XR2WMGCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07618&json=true","fetch_graph":"https://pith.science/api/pith-number/XR2WMGCW7E2SMTQWCXZEDKVXTW/graph.json","fetch_events":"https://pith.science/api/pith-number/XR2WMGCW7E2SMTQWCXZEDKVXTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XR2WMGCW7E2SMTQWCXZEDKVXTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XR2WMGCW7E2SMTQWCXZEDKVXTW/action/storage_attestation","attest_author":"https://pith.science/pith/XR2WMGCW7E2SMTQWCXZEDKVXTW/action/author_attestation","sign_citation":"https://pith.science/pith/XR2WMGCW7E2SMTQWCXZEDKVXTW/action/citation_signature","submit_replication":"https://pith.science/pith/XR2WMGCW7E2SMTQWCXZEDKVXTW/action/replication_record"}},"created_at":"2026-07-05T07:12:21.171807+00:00","updated_at":"2026-07-05T07:12:21.171807+00:00"}