{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JLSQMAU643MPFRBIITWXT7MFKM","short_pith_number":"pith:JLSQMAU6","schema_version":"1.0","canonical_sha256":"4ae506029ee6d8f2c42844ed79fd85530635cf0586a5932d1aea53943b560b77","source":{"kind":"arxiv","id":"2404.00344","version":1},"attestation_state":"computed","paper":{"title":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Akiko Aizawa, Andre Greiner-Petter, Ankit Satpute, Bela Gipp, Moritz Schubotz, Noah Giessing, Olaf Teschke","submitted_at":"2024-03-30T12:48:31Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language tasks, often achieving performances that surpass those of humans. Despite these advancements, the domain of mathematics presents a distinctive challenge, primarily due to its specialized structure and the precision it demands. In this study, we adopted a two-step approach for investigating the proficiency of LLMs in answering mathematical questions. First, we employ the most effective LLMs, as identified by their performance on math question-answer benchmarks, to generate answers to 78 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":"2404.00344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T12:48:31Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"0a17993728dd6886f021eb3b4396a160a1e0830e1c32afe8841312b3776b3e3c","abstract_canon_sha256":"21d9047f5bd277c4f0cadf8e9887d6117663534d1e22465422b75b262f5b7e5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:31.813077Z","signature_b64":"kd2L9+ZMGnjUf2w6lDh2OL0Bzo4GUguAwcIUH+o3UrfrGRwJ8TvpbCFhyfDXAjkT5kgsX0mkopwc/X//ZjpCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ae506029ee6d8f2c42844ed79fd85530635cf0586a5932d1aea53943b560b77","last_reissued_at":"2026-07-05T08:02:31.812542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:31.812542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Akiko Aizawa, Andre Greiner-Petter, Ankit Satpute, Bela Gipp, Moritz Schubotz, Noah Giessing, Olaf Teschke","submitted_at":"2024-03-30T12:48:31Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language tasks, often achieving performances that surpass those of humans. Despite these advancements, the domain of mathematics presents a distinctive challenge, primarily due to its specialized structure and the precision it demands. In this study, we adopted a two-step approach for investigating the proficiency of LLMs in answering mathematical questions. First, we employ the most effective LLMs, as identified by their performance on math question-answer benchmarks, to generate answers to 78 questions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00344","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/2404.00344/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":"2404.00344","created_at":"2026-07-05T08:02:31.812602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00344v1","created_at":"2026-07-05T08:02:31.812602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00344","created_at":"2026-07-05T08:02:31.812602+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLSQMAU643MP","created_at":"2026-07-05T08:02:31.812602+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLSQMAU643MPFRBI","created_at":"2026-07-05T08:02:31.812602+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLSQMAU6","created_at":"2026-07-05T08:02:31.812602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.17448","citing_title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLSQMAU643MPFRBIITWXT7MFKM","json":"https://pith.science/pith/JLSQMAU643MPFRBIITWXT7MFKM.json","graph_json":"https://pith.science/api/pith-number/JLSQMAU643MPFRBIITWXT7MFKM/graph.json","events_json":"https://pith.science/api/pith-number/JLSQMAU643MPFRBIITWXT7MFKM/events.json","paper":"https://pith.science/paper/JLSQMAU6"},"agent_actions":{"view_html":"https://pith.science/pith/JLSQMAU643MPFRBIITWXT7MFKM","download_json":"https://pith.science/pith/JLSQMAU643MPFRBIITWXT7MFKM.json","view_paper":"https://pith.science/paper/JLSQMAU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00344&json=true","fetch_graph":"https://pith.science/api/pith-number/JLSQMAU643MPFRBIITWXT7MFKM/graph.json","fetch_events":"https://pith.science/api/pith-number/JLSQMAU643MPFRBIITWXT7MFKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLSQMAU643MPFRBIITWXT7MFKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLSQMAU643MPFRBIITWXT7MFKM/action/storage_attestation","attest_author":"https://pith.science/pith/JLSQMAU643MPFRBIITWXT7MFKM/action/author_attestation","sign_citation":"https://pith.science/pith/JLSQMAU643MPFRBIITWXT7MFKM/action/citation_signature","submit_replication":"https://pith.science/pith/JLSQMAU643MPFRBIITWXT7MFKM/action/replication_record"}},"created_at":"2026-07-05T08:02:31.812602+00:00","updated_at":"2026-07-05T08:02:31.812602+00:00"}