{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:24YK2SV2Z4AHHA6YTYSTYBIGDQ","short_pith_number":"pith:24YK2SV2","schema_version":"1.0","canonical_sha256":"d730ad4abacf007383d89e253c05061c236ce9322877738e86a91e1438473a4d","source":{"kind":"arxiv","id":"2402.11111","version":2},"attestation_state":"computed","paper":{"title":"Language Models as Science Tutors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshara Prabhakar, Alexander Wettig, Alexis Chevalier, Arturo Rodr\\'iguez Fanlo, Danqi Chen, Ellie Thieu, Howard Chen, Jiachen T. Wang, Jiatong Yu, Jiayi Geng, Jun-Jie Zhu, Max Jameson Aragon, Mengzhou Xia, Sanjeev Arora, Sebastian Mizera, Simon Frieder, Simon Machado, Toni Annala, Wenhan Xia, Xindi Wu, Zhiyong Jason Ren, Zirui Wang","submitted_at":"2024-02-16T22:24:13Z","abstract_excerpt":"NLP has recently made exciting progress toward training language models (LMs) with strong scientific problem-solving skills. However, model development has not focused on real-life use-cases of LMs for science, including applications in education that require processing long scientific documents. To address this, we introduce TutorEval and TutorChat. TutorEval is a diverse question-answering benchmark consisting of questions about long chapters from STEM textbooks, written by experts. TutorEval helps measure real-life usability of LMs as scientific assistants, and it is the first benchmark com"},"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":"2402.11111","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T22:24:13Z","cross_cats_sorted":[],"title_canon_sha256":"0e74f929daebf0542c2b8720d167bb9e469e8b30b58ddc4617c2059df047eb65","abstract_canon_sha256":"630966c3889ec932e0cd2e53fecb35f37e89274b229ad3d50edf17724ac81080"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:21.621966Z","signature_b64":"smLWO/o0nCzWLJmn2FldILg6NwXOFO5q+hI5Ay1P2O+BN62X3J3q85l+ECRAStksHEU6T7AJsU0PFMrsCa+6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d730ad4abacf007383d89e253c05061c236ce9322877738e86a91e1438473a4d","last_reissued_at":"2026-07-05T08:46:21.621499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:21.621499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models as Science Tutors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshara Prabhakar, Alexander Wettig, Alexis Chevalier, Arturo Rodr\\'iguez Fanlo, Danqi Chen, Ellie Thieu, Howard Chen, Jiachen T. Wang, Jiatong Yu, Jiayi Geng, Jun-Jie Zhu, Max Jameson Aragon, Mengzhou Xia, Sanjeev Arora, Sebastian Mizera, Simon Frieder, Simon Machado, Toni Annala, Wenhan Xia, Xindi Wu, Zhiyong Jason Ren, Zirui Wang","submitted_at":"2024-02-16T22:24:13Z","abstract_excerpt":"NLP has recently made exciting progress toward training language models (LMs) with strong scientific problem-solving skills. However, model development has not focused on real-life use-cases of LMs for science, including applications in education that require processing long scientific documents. To address this, we introduce TutorEval and TutorChat. TutorEval is a diverse question-answering benchmark consisting of questions about long chapters from STEM textbooks, written by experts. TutorEval helps measure real-life usability of LMs as scientific assistants, and it is the first benchmark com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11111","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/2402.11111/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":"2402.11111","created_at":"2026-07-05T08:46:21.621565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11111v2","created_at":"2026-07-05T08:46:21.621565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11111","created_at":"2026-07-05T08:46:21.621565+00:00"},{"alias_kind":"pith_short_12","alias_value":"24YK2SV2Z4AH","created_at":"2026-07-05T08:46:21.621565+00:00"},{"alias_kind":"pith_short_16","alias_value":"24YK2SV2Z4AHHA6Y","created_at":"2026-07-05T08:46:21.621565+00:00"},{"alias_kind":"pith_short_8","alias_value":"24YK2SV2","created_at":"2026-07-05T08:46:21.621565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.07720","citing_title":"Empowering Robot Teleoperation: Exploring the Synergies Between Devices and Manipulator Controllers in a Comparative Study","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24YK2SV2Z4AHHA6YTYSTYBIGDQ","json":"https://pith.science/pith/24YK2SV2Z4AHHA6YTYSTYBIGDQ.json","graph_json":"https://pith.science/api/pith-number/24YK2SV2Z4AHHA6YTYSTYBIGDQ/graph.json","events_json":"https://pith.science/api/pith-number/24YK2SV2Z4AHHA6YTYSTYBIGDQ/events.json","paper":"https://pith.science/paper/24YK2SV2"},"agent_actions":{"view_html":"https://pith.science/pith/24YK2SV2Z4AHHA6YTYSTYBIGDQ","download_json":"https://pith.science/pith/24YK2SV2Z4AHHA6YTYSTYBIGDQ.json","view_paper":"https://pith.science/paper/24YK2SV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11111&json=true","fetch_graph":"https://pith.science/api/pith-number/24YK2SV2Z4AHHA6YTYSTYBIGDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/24YK2SV2Z4AHHA6YTYSTYBIGDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24YK2SV2Z4AHHA6YTYSTYBIGDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24YK2SV2Z4AHHA6YTYSTYBIGDQ/action/storage_attestation","attest_author":"https://pith.science/pith/24YK2SV2Z4AHHA6YTYSTYBIGDQ/action/author_attestation","sign_citation":"https://pith.science/pith/24YK2SV2Z4AHHA6YTYSTYBIGDQ/action/citation_signature","submit_replication":"https://pith.science/pith/24YK2SV2Z4AHHA6YTYSTYBIGDQ/action/replication_record"}},"created_at":"2026-07-05T08:46:21.621565+00:00","updated_at":"2026-07-05T08:46:21.621565+00:00"}