{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EANQNGOSWVM7HJW22ODHO4GNY4","short_pith_number":"pith:EANQNGOS","schema_version":"1.0","canonical_sha256":"201b0699d2b559f3a6dad3867770cdc707f45e75473e36b9139517ba50b91427","source":{"kind":"arxiv","id":"2306.13047","version":4},"attestation_state":"computed","paper":{"title":"Analysis of the Cambridge Multiple-Choice Questions Reading Dataset with a Focus on Candidate Response Distribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adian Liusie, Andrew Mullooly, Kate Knill, Mark J. F. Gales, Vatsal Raina","submitted_at":"2023-06-22T17:13:08Z","abstract_excerpt":"Multiple choice exams are widely used to assess candidates across a diverse range of domains and tasks. To moderate question quality, newly proposed questions often pass through pre-test evaluation stages before being deployed into real-world exams. Currently, this evaluation process is manually intensive, which can lead to time lags in the question development cycle. Streamlining this process via automation can significantly enhance efficiency, however, there's a current lack of datasets with adequate pre-test analysis information. In this paper we analyse a subset of the public Cambridge Mul"},"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":"2306.13047","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-22T17:13:08Z","cross_cats_sorted":[],"title_canon_sha256":"007091e441a295f8fd4815e0220e7ea5bd54eae272d3fa2aff17517c84c10bf6","abstract_canon_sha256":"960f99c9c351c5b6f1abd9605df90fe93fea89174b624305eef184974fda75f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:02.950125Z","signature_b64":"AgAP01g1QYDMgHj857s2WEbXWGqmF2Oa6SHAXNaND0NRY501xtTTYPu5okaxtKcg5QaeZRA5pG15rdd+gLJYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"201b0699d2b559f3a6dad3867770cdc707f45e75473e36b9139517ba50b91427","last_reissued_at":"2026-07-05T07:01:02.949547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:02.949547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of the Cambridge Multiple-Choice Questions Reading Dataset with a Focus on Candidate Response Distribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adian Liusie, Andrew Mullooly, Kate Knill, Mark J. F. Gales, Vatsal Raina","submitted_at":"2023-06-22T17:13:08Z","abstract_excerpt":"Multiple choice exams are widely used to assess candidates across a diverse range of domains and tasks. To moderate question quality, newly proposed questions often pass through pre-test evaluation stages before being deployed into real-world exams. Currently, this evaluation process is manually intensive, which can lead to time lags in the question development cycle. Streamlining this process via automation can significantly enhance efficiency, however, there's a current lack of datasets with adequate pre-test analysis information. In this paper we analyse a subset of the public Cambridge Mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13047","kind":"arxiv","version":4},"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/2306.13047/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":"2306.13047","created_at":"2026-07-05T07:01:02.949615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13047v4","created_at":"2026-07-05T07:01:02.949615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13047","created_at":"2026-07-05T07:01:02.949615+00:00"},{"alias_kind":"pith_short_12","alias_value":"EANQNGOSWVM7","created_at":"2026-07-05T07:01:02.949615+00:00"},{"alias_kind":"pith_short_16","alias_value":"EANQNGOSWVM7HJW2","created_at":"2026-07-05T07:01:02.949615+00:00"},{"alias_kind":"pith_short_8","alias_value":"EANQNGOS","created_at":"2026-07-05T07:01:02.949615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18709","citing_title":"LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19316","citing_title":"A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16991","citing_title":"Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning","ref_index":116,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EANQNGOSWVM7HJW22ODHO4GNY4","json":"https://pith.science/pith/EANQNGOSWVM7HJW22ODHO4GNY4.json","graph_json":"https://pith.science/api/pith-number/EANQNGOSWVM7HJW22ODHO4GNY4/graph.json","events_json":"https://pith.science/api/pith-number/EANQNGOSWVM7HJW22ODHO4GNY4/events.json","paper":"https://pith.science/paper/EANQNGOS"},"agent_actions":{"view_html":"https://pith.science/pith/EANQNGOSWVM7HJW22ODHO4GNY4","download_json":"https://pith.science/pith/EANQNGOSWVM7HJW22ODHO4GNY4.json","view_paper":"https://pith.science/paper/EANQNGOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13047&json=true","fetch_graph":"https://pith.science/api/pith-number/EANQNGOSWVM7HJW22ODHO4GNY4/graph.json","fetch_events":"https://pith.science/api/pith-number/EANQNGOSWVM7HJW22ODHO4GNY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EANQNGOSWVM7HJW22ODHO4GNY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EANQNGOSWVM7HJW22ODHO4GNY4/action/storage_attestation","attest_author":"https://pith.science/pith/EANQNGOSWVM7HJW22ODHO4GNY4/action/author_attestation","sign_citation":"https://pith.science/pith/EANQNGOSWVM7HJW22ODHO4GNY4/action/citation_signature","submit_replication":"https://pith.science/pith/EANQNGOSWVM7HJW22ODHO4GNY4/action/replication_record"}},"created_at":"2026-07-05T07:01:02.949615+00:00","updated_at":"2026-07-05T07:01:02.949615+00:00"}