{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P7ESQRJBBOX7D5JSWCDAG2ORVE","short_pith_number":"pith:P7ESQRJB","schema_version":"1.0","canonical_sha256":"7fc92845210baff1f532b0860369d1a90b7a7ec7845eba2d5ccb37bb2566fce5","source":{"kind":"arxiv","id":"2503.10533","version":3},"attestation_state":"computed","paper":{"title":"The Impact of Item-Writing Flaws on Difficulty and Discrimination in Item Response Theory","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Robin Schmucker, Steven Moore","submitted_at":"2025-03-13T16:47:07Z","abstract_excerpt":"High-quality test items are essential for educational assessments, particularly within Item Response Theory (IRT). Traditional validation methods rely on resource-intensive pilot testing to estimate item difficulty and discrimination. More recently, Item-Writing Flaw (IWF) rubrics emerged as a domain-general approach for evaluating test items based on textual features. This method offers a scalable, pre-deployment evaluation without requiring student data, but its predictive validity concerning empirical IRT parameters is underexplored. To address this gap, we conducted a study involving 7,126"},"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":"2503.10533","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-13T16:47:07Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"6e7048a024c481bdfeb6682b7f2a0fae4bab810089a571293e953db351b2a70b","abstract_canon_sha256":"0a37c74f58de47b3c373ad5de3b90a1bbf874caa155354121fd7badbf2de038f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:52.086782Z","signature_b64":"xARhEQ62ECviZY7JSpzvHytOTASMVz1NO72e5kHT+aY5e3RUDs+fBNImqaUt0bWqpkEfeZFUi6tr1Of6YuUGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fc92845210baff1f532b0860369d1a90b7a7ec7845eba2d5ccb37bb2566fce5","last_reissued_at":"2026-07-05T11:49:52.086327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:52.086327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Impact of Item-Writing Flaws on Difficulty and Discrimination in Item Response Theory","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Robin Schmucker, Steven Moore","submitted_at":"2025-03-13T16:47:07Z","abstract_excerpt":"High-quality test items are essential for educational assessments, particularly within Item Response Theory (IRT). Traditional validation methods rely on resource-intensive pilot testing to estimate item difficulty and discrimination. More recently, Item-Writing Flaw (IWF) rubrics emerged as a domain-general approach for evaluating test items based on textual features. This method offers a scalable, pre-deployment evaluation without requiring student data, but its predictive validity concerning empirical IRT parameters is underexplored. To address this gap, we conducted a study involving 7,126"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10533","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/2503.10533/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":"2503.10533","created_at":"2026-07-05T11:49:52.086385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10533v3","created_at":"2026-07-05T11:49:52.086385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10533","created_at":"2026-07-05T11:49:52.086385+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7ESQRJBBOX7","created_at":"2026-07-05T11:49:52.086385+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7ESQRJBBOX7D5JS","created_at":"2026-07-05T11:49:52.086385+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7ESQRJB","created_at":"2026-07-05T11:49:52.086385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.06221","citing_title":"BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7ESQRJBBOX7D5JSWCDAG2ORVE","json":"https://pith.science/pith/P7ESQRJBBOX7D5JSWCDAG2ORVE.json","graph_json":"https://pith.science/api/pith-number/P7ESQRJBBOX7D5JSWCDAG2ORVE/graph.json","events_json":"https://pith.science/api/pith-number/P7ESQRJBBOX7D5JSWCDAG2ORVE/events.json","paper":"https://pith.science/paper/P7ESQRJB"},"agent_actions":{"view_html":"https://pith.science/pith/P7ESQRJBBOX7D5JSWCDAG2ORVE","download_json":"https://pith.science/pith/P7ESQRJBBOX7D5JSWCDAG2ORVE.json","view_paper":"https://pith.science/paper/P7ESQRJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10533&json=true","fetch_graph":"https://pith.science/api/pith-number/P7ESQRJBBOX7D5JSWCDAG2ORVE/graph.json","fetch_events":"https://pith.science/api/pith-number/P7ESQRJBBOX7D5JSWCDAG2ORVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7ESQRJBBOX7D5JSWCDAG2ORVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7ESQRJBBOX7D5JSWCDAG2ORVE/action/storage_attestation","attest_author":"https://pith.science/pith/P7ESQRJBBOX7D5JSWCDAG2ORVE/action/author_attestation","sign_citation":"https://pith.science/pith/P7ESQRJBBOX7D5JSWCDAG2ORVE/action/citation_signature","submit_replication":"https://pith.science/pith/P7ESQRJBBOX7D5JSWCDAG2ORVE/action/replication_record"}},"created_at":"2026-07-05T11:49:52.086385+00:00","updated_at":"2026-07-05T11:49:52.086385+00:00"}