{"id":"W2883031472","doi":"10.1017/s0261444818000216","title":"Input-based tasks for beginner-level learners: An approximate replication and extension of Erlam & Ellis (2018)","year":2018,"lang":"en","type":"article","venue":"Language Teaching","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Vocabulary; Replication (statistics); Mathematics education; Psychology; Computer science; Second-language acquisition; Linguistics; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0159525,0.00113681,0.001542253,0.001363714,0.001239102,0.001825194,0.003139875,0.00145114,0.002740022],"category_scores_gemma":[0.04603918,0.0009083932,0.001890687,0.001429286,0.001776941,0.002504814,0.002019597,0.002065514,0.000745039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001333145,"about_ca_system_score_gemma":0.003461507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006636227,"about_ca_topic_score_gemma":0.006983662,"domain_scores_codex":[0.9877968,0.005772641,0.001807686,0.001335115,0.00306833,0.0002193614],"domain_scores_gemma":[0.9621647,0.01509238,0.002579814,0.01310881,0.006713056,0.000341211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01064268,0.04353974,0.0439139,0.01766417,0.002078293,0.001935952,0.07603091,0.001660038,0.04704728,0.008622332,0.003683555,0.743181],"study_design_scores_gemma":[0.01359202,0.1536228,0.3904113,0.009961834,0.01040596,0.006081132,0.0424617,0.00466752,0.1647405,0.02267734,0.179726,0.001651978],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9527693,0.008331904,0.01595584,0.0009309109,0.0005154695,0.0121204,0.0007818803,0.0001378662,0.008456549],"genre_scores_gemma":[0.8942456,0.01000946,0.05858991,0.001385359,0.0003734632,0.02455733,0.001187315,0.000122258,0.009529317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0159525,"threshold_uncertainty_score":0.0843659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06353615573222245,"score_gpt":0.3762069209236499,"score_spread":0.3126707651914274,"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."}}