{"id":"W3036211922","doi":"10.3758/s13428-020-01397-1","title":"CompLex: an eye-movement database of compound word reading in English","year":2020,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; McMaster University","keywords":"Eye movement; Sentence; Reading (process); Population; Natural language processing; Sample (material); Computer science; Word lists by frequency; Set (abstract data type); Word (group theory); Eye tracking; Word recognition; Artificial intelligence; Psychology; Database; Linguistics; Medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000256488,0.0004539343,0.0004087626,0.001979806,0.0002395583,0.0006029549,0.0003881016,0.000573313,0.01256384],"category_scores_gemma":[0.002151503,0.0001723584,0.0002739415,0.001183513,0.0001351272,0.0008022453,0.0006387353,0.0002423557,0.0053697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002410776,"about_ca_system_score_gemma":0.0003386902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008351371,"about_ca_topic_score_gemma":0.0178867,"domain_scores_codex":[0.9997569,0.00003796277,0.00003252123,0.00008521234,0.00006299946,0.00002442534],"domain_scores_gemma":[0.9986467,0.000463282,0.0001202751,0.0002546653,0.0003847143,0.0001304002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005547175,0.001172322,0.09798971,0.002273743,0.0005565233,0.002053145,0.002711255,0.003351181,0.2030611,0.001774622,0.1143726,0.5651367],"study_design_scores_gemma":[0.0004086434,0.0008064838,0.8459351,0.0001443794,0.0003189263,0.003511351,0.001887988,0.02347266,0.05403556,0.001952819,0.06730324,0.0002227953],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.7319723,0.001053817,0.01762955,0.0001736489,0.0001312202,0.0005367952,0.2220187,0.008794562,0.01768941],"genre_scores_gemma":[0.7638401,0.0005512733,0.0303324,0.0001449051,0.0001103764,0.0006461687,0.1896832,0.001241344,0.01345031],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01256384,"threshold_uncertainty_score":0.04203027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4670532478115519,"score_gpt":0.6103505975625049,"score_spread":0.1432973497509529,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}