{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001226807,0.0001546087,0.0002108128,0.0001631208,0.0002064577,0.00004134491,0.0001546383,0.0001374667,0.002482235],"category_scores_gemma":[0.0004543164,0.0001450443,0.00005962076,0.00008564648,0.0001069164,0.0001393893,0.00002940149,0.0002583219,0.00005266431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001987277,"about_ca_system_score_gemma":0.00001340218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004995663,"about_ca_topic_score_gemma":0.00005876135,"domain_scores_codex":[0.9985501,0.0002707923,0.0002730775,0.0005188677,0.0001174018,0.000269816],"domain_scores_gemma":[0.9983983,0.0001679499,0.000219794,0.001067671,0.00005722901,0.00008906026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0005445157,0.0004326518,0.0009633956,0.0001639628,0.00009398811,0.00001952587,0.1828531,0.00003211582,0.2780779,0.006014972,0.006255989,0.5245479],"study_design_scores_gemma":[0.03026456,0.006904399,0.09307938,0.001484347,0.001048014,0.0008588821,0.4136271,0.0699713,0.09346213,0.002151185,0.2809873,0.006161377],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9117165,0.000806412,0.08313392,0.0001957932,0.0001820036,0.000313115,0.00003356878,0.0001681125,0.003450588],"genre_scores_gemma":[0.9606672,8.810625e-7,0.03302608,0.002862626,0.0004231386,0.00003988882,0.0003355339,0.00004657044,0.002598056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5183865,"threshold_uncertainty_score":0.9984297,"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."}}