{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:R2NGLJMHATMRFN6CQLRGUTVVLW","short_pith_number":"pith:R2NGLJMH","schema_version":"1.0","canonical_sha256":"8e9a65a58704d912b7c282e26a4eb55d89e2f28ce7504213bb7d50d569f9344b","source":{"kind":"arxiv","id":"1909.01958","version":3},"attestation_state":"computed","paper":{"title":"From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Bhavana Dalvi Mishra, Carissa Schoenick, Daniel Khashabi, Dirk Groeneveld, Kyle Richardson, Michael Schmitz, Michal Guerquin, Niket Tandon, Oren Etzioni, Oyvind Tafjord, Peter Clark, Sumithra Bhakthavatsalam, Tushar Khot","submitted_at":"2019-09-04T17:33:42Z","abstract_excerpt":"AI has achieved remarkable mastery over games such as Chess, Go, and Poker, and even Jeopardy, but the rich variety of standardized exams has remained a landmark challenge. Even in 2016, the best AI system achieved merely 59.3% on an 8th Grade science exam challenge. This paper reports unprecedented success on the Grade 8 New York Regents Science Exam, where for the first time a system scores more than 90% on the exam's non-diagram, multiple choice (NDMC) questions. In addition, our Aristo system, building upon the success of recent language models, exceeded 83% on the corresponding Grade 12 S"},"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":"1909.01958","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-04T17:33:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4f230ff925374b3e919226189dfa72ce53e871c9d1c4f98a20e906de4f59056d","abstract_canon_sha256":"8915f57284c5cbe413b46be146a082223f26cbda7b4c8f54319362bb47934390"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:19.820503Z","signature_b64":"NCqLol3oMrbzDQ5yBWo4+S08K9BkKVMje5BJr3xpH18i/crJxsPZTudKfn5EpLSXCva94UtK/UUj0mZdxSR3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e9a65a58704d912b7c282e26a4eb55d89e2f28ce7504213bb7d50d569f9344b","last_reissued_at":"2026-07-05T02:11:19.820058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:19.820058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashish Sabharwal, Bhavana Dalvi Mishra, Carissa Schoenick, Daniel Khashabi, Dirk Groeneveld, Kyle Richardson, Michael Schmitz, Michal Guerquin, Niket Tandon, Oren Etzioni, Oyvind Tafjord, Peter Clark, Sumithra Bhakthavatsalam, Tushar Khot","submitted_at":"2019-09-04T17:33:42Z","abstract_excerpt":"AI has achieved remarkable mastery over games such as Chess, Go, and Poker, and even Jeopardy, but the rich variety of standardized exams has remained a landmark challenge. Even in 2016, the best AI system achieved merely 59.3% on an 8th Grade science exam challenge. This paper reports unprecedented success on the Grade 8 New York Regents Science Exam, where for the first time a system scores more than 90% on the exam's non-diagram, multiple choice (NDMC) questions. In addition, our Aristo system, building upon the success of recent language models, exceeded 83% on the corresponding Grade 12 S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01958","kind":"arxiv","version":3},"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/1909.01958/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":"1909.01958","created_at":"2026-07-05T02:11:19.820115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.01958v3","created_at":"2026-07-05T02:11:19.820115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01958","created_at":"2026-07-05T02:11:19.820115+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2NGLJMHATMR","created_at":"2026-07-05T02:11:19.820115+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2NGLJMHATMRFN6C","created_at":"2026-07-05T02:11:19.820115+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2NGLJMH","created_at":"2026-07-05T02:11:19.820115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2009.03300","citing_title":"Measuring Massive Multitask Language Understanding","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2NGLJMHATMRFN6CQLRGUTVVLW","json":"https://pith.science/pith/R2NGLJMHATMRFN6CQLRGUTVVLW.json","graph_json":"https://pith.science/api/pith-number/R2NGLJMHATMRFN6CQLRGUTVVLW/graph.json","events_json":"https://pith.science/api/pith-number/R2NGLJMHATMRFN6CQLRGUTVVLW/events.json","paper":"https://pith.science/paper/R2NGLJMH"},"agent_actions":{"view_html":"https://pith.science/pith/R2NGLJMHATMRFN6CQLRGUTVVLW","download_json":"https://pith.science/pith/R2NGLJMHATMRFN6CQLRGUTVVLW.json","view_paper":"https://pith.science/paper/R2NGLJMH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.01958&json=true","fetch_graph":"https://pith.science/api/pith-number/R2NGLJMHATMRFN6CQLRGUTVVLW/graph.json","fetch_events":"https://pith.science/api/pith-number/R2NGLJMHATMRFN6CQLRGUTVVLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2NGLJMHATMRFN6CQLRGUTVVLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2NGLJMHATMRFN6CQLRGUTVVLW/action/storage_attestation","attest_author":"https://pith.science/pith/R2NGLJMHATMRFN6CQLRGUTVVLW/action/author_attestation","sign_citation":"https://pith.science/pith/R2NGLJMHATMRFN6CQLRGUTVVLW/action/citation_signature","submit_replication":"https://pith.science/pith/R2NGLJMHATMRFN6CQLRGUTVVLW/action/replication_record"}},"created_at":"2026-07-05T02:11:19.820115+00:00","updated_at":"2026-07-05T02:11:19.820115+00:00"}