{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MF33NPWS7A7EGXVOVKVHPA7A6H","short_pith_number":"pith:MF33NPWS","schema_version":"1.0","canonical_sha256":"6177b6bed2f83e435eaeaaaa7783e0f1eedc872c1f459766ee9e28c14041d26e","source":{"kind":"arxiv","id":"2405.20529","version":1},"attestation_state":"computed","paper":{"title":"An Automatic Question Usability Evaluation Toolkit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Eamon Costello, Huy A. Nguyen, John Stamper, Steven Moore","submitted_at":"2024-05-30T23:04:53Z","abstract_excerpt":"Evaluating multiple-choice questions (MCQs) involves either labor intensive human assessments or automated methods that prioritize readability, often overlooking deeper question design flaws. To address this issue, we introduce the Scalable Automatic Question Usability Evaluation Toolkit (SAQUET), an open-source tool that leverages the Item-Writing Flaws (IWF) rubric for a comprehensive and automated quality evaluation of MCQs. By harnessing the latest in large language models such as GPT-4, advanced word embeddings, and Transformers designed to analyze textual complexity, SAQUET effectively p"},"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":"2405.20529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-30T23:04:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c3af9b2692a60c71d3e597f10744132416c7f54282b7210a33f8c4e81d33e730","abstract_canon_sha256":"bbf8bf9a17fb3584746e707df8bfec60bbe1bf4c2e018a760aeb2bfbbd743e74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:38.648837Z","signature_b64":"H9eDlNTmt4CchRBafzd7pjtcm+Zi1eNh/sY0hSXJ+xn6gLKSREoy8PQwcKabiMcbFHekN0klF3AjnLrIsXr9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6177b6bed2f83e435eaeaaaa7783e0f1eedc872c1f459766ee9e28c14041d26e","last_reissued_at":"2026-07-05T08:25:38.648429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:38.648429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Automatic Question Usability Evaluation Toolkit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Eamon Costello, Huy A. Nguyen, John Stamper, Steven Moore","submitted_at":"2024-05-30T23:04:53Z","abstract_excerpt":"Evaluating multiple-choice questions (MCQs) involves either labor intensive human assessments or automated methods that prioritize readability, often overlooking deeper question design flaws. To address this issue, we introduce the Scalable Automatic Question Usability Evaluation Toolkit (SAQUET), an open-source tool that leverages the Item-Writing Flaws (IWF) rubric for a comprehensive and automated quality evaluation of MCQs. By harnessing the latest in large language models such as GPT-4, advanced word embeddings, and Transformers designed to analyze textual complexity, SAQUET effectively p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20529","kind":"arxiv","version":1},"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/2405.20529/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":"2405.20529","created_at":"2026-07-05T08:25:38.648480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20529v1","created_at":"2026-07-05T08:25:38.648480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20529","created_at":"2026-07-05T08:25:38.648480+00:00"},{"alias_kind":"pith_short_12","alias_value":"MF33NPWS7A7E","created_at":"2026-07-05T08:25:38.648480+00:00"},{"alias_kind":"pith_short_16","alias_value":"MF33NPWS7A7EGXVO","created_at":"2026-07-05T08:25:38.648480+00:00"},{"alias_kind":"pith_short_8","alias_value":"MF33NPWS","created_at":"2026-07-05T08:25:38.648480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MF33NPWS7A7EGXVOVKVHPA7A6H","json":"https://pith.science/pith/MF33NPWS7A7EGXVOVKVHPA7A6H.json","graph_json":"https://pith.science/api/pith-number/MF33NPWS7A7EGXVOVKVHPA7A6H/graph.json","events_json":"https://pith.science/api/pith-number/MF33NPWS7A7EGXVOVKVHPA7A6H/events.json","paper":"https://pith.science/paper/MF33NPWS"},"agent_actions":{"view_html":"https://pith.science/pith/MF33NPWS7A7EGXVOVKVHPA7A6H","download_json":"https://pith.science/pith/MF33NPWS7A7EGXVOVKVHPA7A6H.json","view_paper":"https://pith.science/paper/MF33NPWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20529&json=true","fetch_graph":"https://pith.science/api/pith-number/MF33NPWS7A7EGXVOVKVHPA7A6H/graph.json","fetch_events":"https://pith.science/api/pith-number/MF33NPWS7A7EGXVOVKVHPA7A6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MF33NPWS7A7EGXVOVKVHPA7A6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MF33NPWS7A7EGXVOVKVHPA7A6H/action/storage_attestation","attest_author":"https://pith.science/pith/MF33NPWS7A7EGXVOVKVHPA7A6H/action/author_attestation","sign_citation":"https://pith.science/pith/MF33NPWS7A7EGXVOVKVHPA7A6H/action/citation_signature","submit_replication":"https://pith.science/pith/MF33NPWS7A7EGXVOVKVHPA7A6H/action/replication_record"}},"created_at":"2026-07-05T08:25:38.648480+00:00","updated_at":"2026-07-05T08:25:38.648480+00:00"}