{"id":"W2076994293","doi":"10.1007/s11409-011-9070-z","title":"Measuring strategy use in context with multiple-choice items","year":2011,"lang":"en","type":"article","venue":"Metacognition and Learning","topic":"Reading and Literacy Development","field":"Psychology","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reading comprehension; Psychology; Vocabulary; Metacognition; Context (archaeology); Reliability (semiconductor); Concurrent validity; Construct validity; Measure (data warehouse); Comprehension; Inference; Construct (python library); Reading (process); Vocabulary development; Social psychology; Internal consistency; Computer science; Psychometrics; Developmental psychology; Cognition; Mathematics education; Artificial intelligence; Teaching method; Linguistics; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003710229,0.0001190531,0.000152067,0.0001568253,0.00009976019,0.00005956675,0.00003720921,0.00005586264,0.0005355877],"category_scores_gemma":[0.0002168606,0.0000995786,0.00001954214,0.0001275107,0.00003344213,0.0002146672,0.00001035073,0.0003577448,0.00008623947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000120113,"about_ca_system_score_gemma":0.00000931955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001201701,"about_ca_topic_score_gemma":0.0003931299,"domain_scores_codex":[0.998965,0.0002852187,0.000191442,0.0002531511,0.00009454448,0.0002106514],"domain_scores_gemma":[0.9993816,0.0003503496,0.00007485926,0.00007427626,0.00005137114,0.00006754254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002011503,0.00009999321,0.8795071,0.00001538033,0.00007794559,0.00006383663,0.02726231,0.00001713063,0.0002930333,0.0002925472,0.00002436564,0.09214521],"study_design_scores_gemma":[0.00161583,0.0001312226,0.9792951,0.0001143076,0.00002194805,0.00003542863,0.007142975,0.0001297827,0.0002040617,0.00002044545,0.01108704,0.0002018867],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9793686,0.0001947953,0.0004521734,0.000009392122,0.00008414771,0.0001203017,8.92518e-7,0.00006069392,0.01970898],"genre_scores_gemma":[0.9954135,0.000007774531,0.0005290332,0.0001259046,0.00002683044,0.00003842123,0.0000123004,0.00001710459,0.003829087],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09978798,"threshold_uncertainty_score":0.586431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1421308067241243,"score_gpt":0.2906518890518613,"score_spread":0.148521082327737,"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."}}