{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7JSWZZEX35BKQWPZE7ZXNA6I3U","short_pith_number":"pith:7JSWZZEX","schema_version":"1.0","canonical_sha256":"fa656ce497df42a859f927f37683c8dd1837f2038c774674c27acc447a974b5c","source":{"kind":"arxiv","id":"2306.08997","version":2},"attestation_state":"computed","paper":{"title":"Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrei Marginean, Annie Wang, Ariel N. Lee, Armando Solar-Lezama, Eamon Niknafs, Iddo Drori, Keith Tyser, Madeleine Udell, Nikhil Singh, Samuel Florin, Sarah J. Zhang, Tonio Buonassisi, Yann Hicke, Yoon Kim, Zad Chin","submitted_at":"2023-06-15T09:48:14Z","abstract_excerpt":"We curate a comprehensive dataset of 4,550 questions and solutions from problem sets, midterm exams, and final exams across all MIT Mathematics and Electrical Engineering and Computer Science (EECS) courses required for obtaining a degree. We evaluate the ability of large language models to fulfill the graduation requirements for any MIT major in Mathematics and EECS. Our results demonstrate that GPT-3.5 successfully solves a third of the entire MIT curriculum, while GPT-4, with prompt engineering, achieves a perfect solve rate on a test set excluding questions based on images. We fine-tune an"},"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":"2306.08997","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T09:48:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b10ec23e7e23d698d13cafdfeb5f4fde84080ccf6a561ebb84bc0f90453adfeb","abstract_canon_sha256":"3c7c1152b120b2bb883a65aafec5f2d2d09e3458974c12c378911e2829f217d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:13.475723Z","signature_b64":"nCE5bNRfU35krNXvWipDB8BVqOEHsRujyKxBqyyND7jZ/XHZYq3m4VuDHhhk7x8zUyOpww8D5PwZ3qZ0htJmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa656ce497df42a859f927f37683c8dd1837f2038c774674c27acc447a974b5c","last_reissued_at":"2026-07-05T06:24:13.475280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:13.475280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrei Marginean, Annie Wang, Ariel N. Lee, Armando Solar-Lezama, Eamon Niknafs, Iddo Drori, Keith Tyser, Madeleine Udell, Nikhil Singh, Samuel Florin, Sarah J. Zhang, Tonio Buonassisi, Yann Hicke, Yoon Kim, Zad Chin","submitted_at":"2023-06-15T09:48:14Z","abstract_excerpt":"We curate a comprehensive dataset of 4,550 questions and solutions from problem sets, midterm exams, and final exams across all MIT Mathematics and Electrical Engineering and Computer Science (EECS) courses required for obtaining a degree. We evaluate the ability of large language models to fulfill the graduation requirements for any MIT major in Mathematics and EECS. Our results demonstrate that GPT-3.5 successfully solves a third of the entire MIT curriculum, while GPT-4, with prompt engineering, achieves a perfect solve rate on a test set excluding questions based on images. We fine-tune an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08997","kind":"arxiv","version":2},"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/2306.08997/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":"2306.08997","created_at":"2026-07-05T06:24:13.475365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08997v2","created_at":"2026-07-05T06:24:13.475365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08997","created_at":"2026-07-05T06:24:13.475365+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JSWZZEX35BK","created_at":"2026-07-05T06:24:13.475365+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JSWZZEX35BKQWPZ","created_at":"2026-07-05T06:24:13.475365+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JSWZZEX","created_at":"2026-07-05T06:24:13.475365+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/7JSWZZEX35BKQWPZE7ZXNA6I3U","json":"https://pith.science/pith/7JSWZZEX35BKQWPZE7ZXNA6I3U.json","graph_json":"https://pith.science/api/pith-number/7JSWZZEX35BKQWPZE7ZXNA6I3U/graph.json","events_json":"https://pith.science/api/pith-number/7JSWZZEX35BKQWPZE7ZXNA6I3U/events.json","paper":"https://pith.science/paper/7JSWZZEX"},"agent_actions":{"view_html":"https://pith.science/pith/7JSWZZEX35BKQWPZE7ZXNA6I3U","download_json":"https://pith.science/pith/7JSWZZEX35BKQWPZE7ZXNA6I3U.json","view_paper":"https://pith.science/paper/7JSWZZEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08997&json=true","fetch_graph":"https://pith.science/api/pith-number/7JSWZZEX35BKQWPZE7ZXNA6I3U/graph.json","fetch_events":"https://pith.science/api/pith-number/7JSWZZEX35BKQWPZE7ZXNA6I3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JSWZZEX35BKQWPZE7ZXNA6I3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JSWZZEX35BKQWPZE7ZXNA6I3U/action/storage_attestation","attest_author":"https://pith.science/pith/7JSWZZEX35BKQWPZE7ZXNA6I3U/action/author_attestation","sign_citation":"https://pith.science/pith/7JSWZZEX35BKQWPZE7ZXNA6I3U/action/citation_signature","submit_replication":"https://pith.science/pith/7JSWZZEX35BKQWPZE7ZXNA6I3U/action/replication_record"}},"created_at":"2026-07-05T06:24:13.475365+00:00","updated_at":"2026-07-05T06:24:13.475365+00:00"}