{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7JSWZZEX35BKQWPZE7ZXNA6I3U","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":"3c7c1152b120b2bb883a65aafec5f2d2d09e3458974c12c378911e2829f217d0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T09:48:14Z","title_canon_sha256":"b10ec23e7e23d698d13cafdfeb5f4fde84080ccf6a561ebb84bc0f90453adfeb"},"schema_version":"1.0","source":{"id":"2306.08997","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08997","created_at":"2026-07-05T06:24:13Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08997v2","created_at":"2026-07-05T06:24:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08997","created_at":"2026-07-05T06:24:13Z"},{"alias_kind":"pith_short_12","alias_value":"7JSWZZEX35BK","created_at":"2026-07-05T06:24:13Z"},{"alias_kind":"pith_short_16","alias_value":"7JSWZZEX35BKQWPZ","created_at":"2026-07-05T06:24:13Z"},{"alias_kind":"pith_short_8","alias_value":"7JSWZZEX","created_at":"2026-07-05T06:24:13Z"}],"graph_snapshots":[{"event_id":"sha256:a2d5c7e5273915a6f453d5f57363217b2ce0d5e4eedc6f80c4013f740f37e84a","target":"graph","created_at":"2026-07-05T06:24:13Z","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/2306.08997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T09:48:14Z","title":"Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08997","kind":"arxiv","version":2},"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":"sha256:8c55b8885a664607af12a968496e44c80c92176f626d2a8c46acf9b0313cbb6c","target":"record","created_at":"2026-07-05T06:24:13Z","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":"3c7c1152b120b2bb883a65aafec5f2d2d09e3458974c12c378911e2829f217d0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T09:48:14Z","title_canon_sha256":"b10ec23e7e23d698d13cafdfeb5f4fde84080ccf6a561ebb84bc0f90453adfeb"},"schema_version":"1.0","source":{"id":"2306.08997","kind":"arxiv","version":2}},"canonical_sha256":"fa656ce497df42a859f927f37683c8dd1837f2038c774674c27acc447a974b5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa656ce497df42a859f927f37683c8dd1837f2038c774674c27acc447a974b5c","first_computed_at":"2026-07-05T06:24:13.475280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:13.475280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nCE5bNRfU35krNXvWipDB8BVqOEHsRujyKxBqyyND7jZ/XHZYq3m4VuDHhhk7x8zUyOpww8D5PwZ3qZ0htJmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:13.475723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08997","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c55b8885a664607af12a968496e44c80c92176f626d2a8c46acf9b0313cbb6c","sha256:a2d5c7e5273915a6f453d5f57363217b2ce0d5e4eedc6f80c4013f740f37e84a"],"state_sha256":"661bdd46562911a51e0fb033a98cc3f5cd01339a77e74abefaf3bd4df11cce20"}