{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W5C5QI326YPCLGS2ENVEQZ26QN","short_pith_number":"pith:W5C5QI32","schema_version":"1.0","canonical_sha256":"b745d8237af61e259a5a236a48675e8341afec1f7091ce02e166614738d223e1","source":{"kind":"arxiv","id":"2510.25064","version":2},"attestation_state":"computed","paper":{"title":"Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gary Geunbae Lee, Hyounghun Kim, Seonjeong Hwang","submitted_at":"2025-10-29T01:07:26Z","abstract_excerpt":"Estimating the cognitive complexity of reading comprehension (RC) items is crucial for assessing item difficulty before it is administered to learners. Unlike syntactic and semantic features, such as passage length or semantic similarity between options, cognitive features that arise during answer reasoning are not readily extractable using existing NLP tools and have traditionally relied on human annotation. In this study, we examine whether large language models (LLMs) can estimate the cognitive complexity of RC items by focusing on two dimensions-Evidence Scope and Transformation Level-that"},"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":"2510.25064","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-29T01:07:26Z","cross_cats_sorted":[],"title_canon_sha256":"db14cdd982544da1059107284b2007cfac263903c658704d86dd1ef9f171b201","abstract_canon_sha256":"9156249be418cf7f2582115e5207e805e95568ccaac5fc5f35f5177f649c9250"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:00.861491Z","signature_b64":"zSYvGz/O44TZaPxR+24coNhOTdVtvfY0e5ro+YcR7g7Ly0/82YT+/lUVYhIQPWVaAq4eTNdboNCSwLcZUYrACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b745d8237af61e259a5a236a48675e8341afec1f7091ce02e166614738d223e1","last_reissued_at":"2026-05-20T01:05:00.860634Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:00.860634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gary Geunbae Lee, Hyounghun Kim, Seonjeong Hwang","submitted_at":"2025-10-29T01:07:26Z","abstract_excerpt":"Estimating the cognitive complexity of reading comprehension (RC) items is crucial for assessing item difficulty before it is administered to learners. Unlike syntactic and semantic features, such as passage length or semantic similarity between options, cognitive features that arise during answer reasoning are not readily extractable using existing NLP tools and have traditionally relied on human annotation. In this study, we examine whether large language models (LLMs) can estimate the cognitive complexity of RC items by focusing on two dimensions-Evidence Scope and Transformation Level-that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.25064","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/2510.25064/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":"2510.25064","created_at":"2026-05-20T01:05:00.860757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.25064v2","created_at":"2026-05-20T01:05:00.860757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.25064","created_at":"2026-05-20T01:05:00.860757+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5C5QI326YPC","created_at":"2026-05-20T01:05:00.860757+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5C5QI326YPCLGS2","created_at":"2026-05-20T01:05:00.860757+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5C5QI32","created_at":"2026-05-20T01:05:00.860757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.19316","citing_title":"A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5C5QI326YPCLGS2ENVEQZ26QN","json":"https://pith.science/pith/W5C5QI326YPCLGS2ENVEQZ26QN.json","graph_json":"https://pith.science/api/pith-number/W5C5QI326YPCLGS2ENVEQZ26QN/graph.json","events_json":"https://pith.science/api/pith-number/W5C5QI326YPCLGS2ENVEQZ26QN/events.json","paper":"https://pith.science/paper/W5C5QI32"},"agent_actions":{"view_html":"https://pith.science/pith/W5C5QI326YPCLGS2ENVEQZ26QN","download_json":"https://pith.science/pith/W5C5QI326YPCLGS2ENVEQZ26QN.json","view_paper":"https://pith.science/paper/W5C5QI32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.25064&json=true","fetch_graph":"https://pith.science/api/pith-number/W5C5QI326YPCLGS2ENVEQZ26QN/graph.json","fetch_events":"https://pith.science/api/pith-number/W5C5QI326YPCLGS2ENVEQZ26QN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5C5QI326YPCLGS2ENVEQZ26QN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5C5QI326YPCLGS2ENVEQZ26QN/action/storage_attestation","attest_author":"https://pith.science/pith/W5C5QI326YPCLGS2ENVEQZ26QN/action/author_attestation","sign_citation":"https://pith.science/pith/W5C5QI326YPCLGS2ENVEQZ26QN/action/citation_signature","submit_replication":"https://pith.science/pith/W5C5QI326YPCLGS2ENVEQZ26QN/action/replication_record"}},"created_at":"2026-05-20T01:05:00.860757+00:00","updated_at":"2026-05-20T01:05:00.860757+00:00"}