{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:24YK2SV2Z4AHHA6YTYSTYBIGDQ","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":"630966c3889ec932e0cd2e53fecb35f37e89274b229ad3d50edf17724ac81080","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T22:24:13Z","title_canon_sha256":"0e74f929daebf0542c2b8720d167bb9e469e8b30b58ddc4617c2059df047eb65"},"schema_version":"1.0","source":{"id":"2402.11111","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11111","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11111v2","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11111","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"pith_short_12","alias_value":"24YK2SV2Z4AH","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"pith_short_16","alias_value":"24YK2SV2Z4AHHA6Y","created_at":"2026-07-05T08:46:21Z"},{"alias_kind":"pith_short_8","alias_value":"24YK2SV2","created_at":"2026-07-05T08:46:21Z"}],"graph_snapshots":[{"event_id":"sha256:00e739895e8138fdd1d857a9e35aba2498eb3d37a15224d8f4c1187b83310240","target":"graph","created_at":"2026-07-05T08:46:21Z","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/2402.11111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T22:24:13Z","title":"Language Models as Science Tutors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11111","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:e4f9e3ea5b823287dea911f41202494c720f8c00106447ad9bcca91886289f9d","target":"record","created_at":"2026-07-05T08:46:21Z","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":"630966c3889ec932e0cd2e53fecb35f37e89274b229ad3d50edf17724ac81080","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T22:24:13Z","title_canon_sha256":"0e74f929daebf0542c2b8720d167bb9e469e8b30b58ddc4617c2059df047eb65"},"schema_version":"1.0","source":{"id":"2402.11111","kind":"arxiv","version":2}},"canonical_sha256":"d730ad4abacf007383d89e253c05061c236ce9322877738e86a91e1438473a4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d730ad4abacf007383d89e253c05061c236ce9322877738e86a91e1438473a4d","first_computed_at":"2026-07-05T08:46:21.621499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:21.621499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"smLWO/o0nCzWLJmn2FldILg6NwXOFO5q+hI5Ay1P2O+BN62X3J3q85l+ECRAStksHEU6T7AJsU0PFMrsCa+6Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:21.621966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11111","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4f9e3ea5b823287dea911f41202494c720f8c00106447ad9bcca91886289f9d","sha256:00e739895e8138fdd1d857a9e35aba2498eb3d37a15224d8f4c1187b83310240"],"state_sha256":"aa0ba5af21b133750bc0b62925fb180c2fa8ebc7f9744e8e15fab62b2d021136"}