{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RXOP5R7SE2WC7QFKVPEVO4TNF3","short_pith_number":"pith:RXOP5R7S","schema_version":"1.0","canonical_sha256":"8ddcfec7f226ac2fc0aaabc957726d2ee529b3846fee3dff9340c3a6df10825e","source":{"kind":"arxiv","id":"2602.17377","version":2},"attestation_state":"computed","paper":{"title":"Corpus Prevalence of Multiple-Choice Question Options","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hedderik van Rijn, Leonidas Zotos, Malvina Nissim","submitted_at":"2026-02-19T13:58:48Z","abstract_excerpt":"In recent years, corpus-driven AI methods, such as Large Language Models (LLMs), have seen widespread use in education. While on the surface their abilities look promising for tasks ranging from generating assessment materials to simulating student performance, we should be aware of the subtle nuances of their frequentist nature that might be affecting their behaviour. In this work, we focus on the aspect of corpus frequency in the context of creating high-quality Multiple Choice Questions (MCQs), specifically asking: What if corpus prevalence were enough to identify the correct answer to an M"},"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":"2602.17377","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-19T13:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"9517f8308478e17daac9dfa28d9e43cba0f450bedd0e5c287af4f52470e3e435","abstract_canon_sha256":"63c9a516b3676d93ddc6a273feec0c8d248ad0a8cc89978f57d5d1f090a90e28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:54.584391Z","signature_b64":"+IEctJAxsv++vrEfcHgRiHaOG8vyOTbn66aVlKlpNKsZQ1Vy3xqbIMiKZGi8vpW1eyXC5xT1GTmwQXbiPcs0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ddcfec7f226ac2fc0aaabc957726d2ee529b3846fee3dff9340c3a6df10825e","last_reissued_at":"2026-06-23T03:13:54.583942Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:54.583942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corpus Prevalence of Multiple-Choice Question Options","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hedderik van Rijn, Leonidas Zotos, Malvina Nissim","submitted_at":"2026-02-19T13:58:48Z","abstract_excerpt":"In recent years, corpus-driven AI methods, such as Large Language Models (LLMs), have seen widespread use in education. While on the surface their abilities look promising for tasks ranging from generating assessment materials to simulating student performance, we should be aware of the subtle nuances of their frequentist nature that might be affecting their behaviour. In this work, we focus on the aspect of corpus frequency in the context of creating high-quality Multiple Choice Questions (MCQs), specifically asking: What if corpus prevalence were enough to identify the correct answer to an M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17377","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/2602.17377/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":"2602.17377","created_at":"2026-06-23T03:13:54.583998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.17377v2","created_at":"2026-06-23T03:13:54.583998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17377","created_at":"2026-06-23T03:13:54.583998+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXOP5R7SE2WC","created_at":"2026-06-23T03:13:54.583998+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXOP5R7SE2WC7QFK","created_at":"2026-06-23T03:13:54.583998+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXOP5R7S","created_at":"2026-06-23T03:13:54.583998+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/RXOP5R7SE2WC7QFKVPEVO4TNF3","json":"https://pith.science/pith/RXOP5R7SE2WC7QFKVPEVO4TNF3.json","graph_json":"https://pith.science/api/pith-number/RXOP5R7SE2WC7QFKVPEVO4TNF3/graph.json","events_json":"https://pith.science/api/pith-number/RXOP5R7SE2WC7QFKVPEVO4TNF3/events.json","paper":"https://pith.science/paper/RXOP5R7S"},"agent_actions":{"view_html":"https://pith.science/pith/RXOP5R7SE2WC7QFKVPEVO4TNF3","download_json":"https://pith.science/pith/RXOP5R7SE2WC7QFKVPEVO4TNF3.json","view_paper":"https://pith.science/paper/RXOP5R7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.17377&json=true","fetch_graph":"https://pith.science/api/pith-number/RXOP5R7SE2WC7QFKVPEVO4TNF3/graph.json","fetch_events":"https://pith.science/api/pith-number/RXOP5R7SE2WC7QFKVPEVO4TNF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXOP5R7SE2WC7QFKVPEVO4TNF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXOP5R7SE2WC7QFKVPEVO4TNF3/action/storage_attestation","attest_author":"https://pith.science/pith/RXOP5R7SE2WC7QFKVPEVO4TNF3/action/author_attestation","sign_citation":"https://pith.science/pith/RXOP5R7SE2WC7QFKVPEVO4TNF3/action/citation_signature","submit_replication":"https://pith.science/pith/RXOP5R7SE2WC7QFKVPEVO4TNF3/action/replication_record"}},"created_at":"2026-06-23T03:13:54.583998+00:00","updated_at":"2026-06-23T03:13:54.583998+00:00"}