{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:C7GOVM4SRUQRWPA6TOFBYCMR44","short_pith_number":"pith:C7GOVM4S","canonical_record":{"source":{"id":"2206.05442","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T06:38:06Z","cross_cats_sorted":[],"title_canon_sha256":"1190ec19275ec643bbbcfddb8f346e7fbaca5bae7ad1a09d4eee34ecfbf81871","abstract_canon_sha256":"86129a8773809908b576b19a04ffc300401e2105aa8aa866dbc746f08d01af52"},"schema_version":"1.0"},"canonical_sha256":"17cceab3928d211b3c1e9b8a1c0991e71f0b8ec3110eb45cd60ddae351d30348","source":{"kind":"arxiv","id":"2206.05442","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05442","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05442v7","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05442","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"pith_short_12","alias_value":"C7GOVM4SRUQR","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"pith_short_16","alias_value":"C7GOVM4SRUQRWPA6","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"pith_short_8","alias_value":"C7GOVM4S","created_at":"2026-07-05T06:25:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:C7GOVM4SRUQRWPA6TOFBYCMR44","target":"record","payload":{"canonical_record":{"source":{"id":"2206.05442","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T06:38:06Z","cross_cats_sorted":[],"title_canon_sha256":"1190ec19275ec643bbbcfddb8f346e7fbaca5bae7ad1a09d4eee34ecfbf81871","abstract_canon_sha256":"86129a8773809908b576b19a04ffc300401e2105aa8aa866dbc746f08d01af52"},"schema_version":"1.0"},"canonical_sha256":"17cceab3928d211b3c1e9b8a1c0991e71f0b8ec3110eb45cd60ddae351d30348","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:37.528660Z","signature_b64":"noq4dnL3DpmYtQUPAUdEK+9gpzdszi4ZqfWfSx+puIFUnSSEblDrvrg/LDND1QsO2H68wMlL/cTOV4zwod36AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17cceab3928d211b3c1e9b8a1c0991e71f0b8ec3110eb45cd60ddae351d30348","last_reissued_at":"2026-07-05T06:25:37.528295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:37.528295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.05442","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:25:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/WbTbqYXn92Ak3MnS0xD5z6jEGV7H6S05j/ed87C4+yz21IbHOop9Xa5nfgR+cN7WKK/zjfi5ZuI7rKj4/KQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:11:57.652388Z"},"content_sha256":"609cf18777b6a5ddc8fad99aceef0902b3853899d6309c921fb20ae33028cff1","schema_version":"1.0","event_id":"sha256:609cf18777b6a5ddc8fad99aceef0902b3853899d6309c921fb20ae33028cff1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:C7GOVM4SRUQRWPA6TOFBYCMR44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Human Days to Machine Seconds: Automatically Answering and Generating Machine Learning Final Exams","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Darnell Granberry, Derek Austin, Gregory Hunter, Iddo Drori, Keith Tyser, Leonard Tang, Madeleine Udell, Pedro Lantigua, Reece Shuttleworth, Sage Simhon, Saisamrit Surbehera, Sarah J. Zhang, Sarah Zhang, Sathwik Karnik, Yann Hicke, Zad Chin","submitted_at":"2022-06-11T06:38:06Z","abstract_excerpt":"A final exam in machine learning at a top institution such as MIT, Harvard, or Cornell typically takes faculty days to write, and students hours to solve. We demonstrate that large language models pass machine learning finals at a human level, on finals available online after the models were trained, and automatically generate new human-quality final exam questions in seconds. Previous work has developed program synthesis and few-shot learning methods to solve university-level problem set questions in mathematics and STEM courses. In this work, we develop and compare methods that solve final e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05442","kind":"arxiv","version":7},"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/2206.05442/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:25:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"65px5oEZobbJWDkFUqzCohJtRMnk1AR7b/8cfT9Uk5U0J/TM2g809ichE183S/2EsZ3DEWCevbpKV1YSM1ABBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:11:57.652767Z"},"content_sha256":"66848c8df5cea901be2fbddd7c67536fccdef665d71e428f0488ea658d253c91","schema_version":"1.0","event_id":"sha256:66848c8df5cea901be2fbddd7c67536fccdef665d71e428f0488ea658d253c91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C7GOVM4SRUQRWPA6TOFBYCMR44/bundle.json","state_url":"https://pith.science/pith/C7GOVM4SRUQRWPA6TOFBYCMR44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C7GOVM4SRUQRWPA6TOFBYCMR44/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T18:11:57Z","links":{"resolver":"https://pith.science/pith/C7GOVM4SRUQRWPA6TOFBYCMR44","bundle":"https://pith.science/pith/C7GOVM4SRUQRWPA6TOFBYCMR44/bundle.json","state":"https://pith.science/pith/C7GOVM4SRUQRWPA6TOFBYCMR44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C7GOVM4SRUQRWPA6TOFBYCMR44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:C7GOVM4SRUQRWPA6TOFBYCMR44","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":"86129a8773809908b576b19a04ffc300401e2105aa8aa866dbc746f08d01af52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T06:38:06Z","title_canon_sha256":"1190ec19275ec643bbbcfddb8f346e7fbaca5bae7ad1a09d4eee34ecfbf81871"},"schema_version":"1.0","source":{"id":"2206.05442","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05442","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05442v7","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05442","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"pith_short_12","alias_value":"C7GOVM4SRUQR","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"pith_short_16","alias_value":"C7GOVM4SRUQRWPA6","created_at":"2026-07-05T06:25:37Z"},{"alias_kind":"pith_short_8","alias_value":"C7GOVM4S","created_at":"2026-07-05T06:25:37Z"}],"graph_snapshots":[{"event_id":"sha256:66848c8df5cea901be2fbddd7c67536fccdef665d71e428f0488ea658d253c91","target":"graph","created_at":"2026-07-05T06:25:37Z","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/2206.05442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A final exam in machine learning at a top institution such as MIT, Harvard, or Cornell typically takes faculty days to write, and students hours to solve. We demonstrate that large language models pass machine learning finals at a human level, on finals available online after the models were trained, and automatically generate new human-quality final exam questions in seconds. Previous work has developed program synthesis and few-shot learning methods to solve university-level problem set questions in mathematics and STEM courses. In this work, we develop and compare methods that solve final e","authors_text":"Darnell Granberry, Derek Austin, Gregory Hunter, Iddo Drori, Keith Tyser, Leonard Tang, Madeleine Udell, Pedro Lantigua, Reece Shuttleworth, Sage Simhon, Saisamrit Surbehera, Sarah J. Zhang, Sarah Zhang, Sathwik Karnik, Yann Hicke, Zad Chin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T06:38:06Z","title":"From Human Days to Machine Seconds: Automatically Answering and Generating Machine Learning Final Exams"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05442","kind":"arxiv","version":7},"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":"sha256:609cf18777b6a5ddc8fad99aceef0902b3853899d6309c921fb20ae33028cff1","target":"record","created_at":"2026-07-05T06:25:37Z","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":"86129a8773809908b576b19a04ffc300401e2105aa8aa866dbc746f08d01af52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T06:38:06Z","title_canon_sha256":"1190ec19275ec643bbbcfddb8f346e7fbaca5bae7ad1a09d4eee34ecfbf81871"},"schema_version":"1.0","source":{"id":"2206.05442","kind":"arxiv","version":7}},"canonical_sha256":"17cceab3928d211b3c1e9b8a1c0991e71f0b8ec3110eb45cd60ddae351d30348","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17cceab3928d211b3c1e9b8a1c0991e71f0b8ec3110eb45cd60ddae351d30348","first_computed_at":"2026-07-05T06:25:37.528295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:25:37.528295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"noq4dnL3DpmYtQUPAUdEK+9gpzdszi4ZqfWfSx+puIFUnSSEblDrvrg/LDND1QsO2H68wMlL/cTOV4zwod36AA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:25:37.528660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.05442","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:609cf18777b6a5ddc8fad99aceef0902b3853899d6309c921fb20ae33028cff1","sha256:66848c8df5cea901be2fbddd7c67536fccdef665d71e428f0488ea658d253c91"],"state_sha256":"db517d5b3457509041c8c0becb64af5a6d4d6a8300334367e8718cab693ff768"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zMiG7fpgaFdpSU7GGgA/m+rJSX5pFvdTYihLEYaF5Q6CpRxWhffGmOYTXMwE9iGNPcFMKXsIytOXp/bQBJmABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:11:57.654999Z","bundle_sha256":"a457b73f344e4264523be78ba2f0a15b12091b38daf6e0a7e90c4a16b62fff11"}}