{"id":"W4239260231","doi":"10.31219/osf.io/mxr8s","title":"A thorough evaluation of the Language Environment Analysis (LENATM) system","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Language Development and Disorders","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Economic and Social Research Council","keywords":"Set (abstract data type); Psychology; Language acquisition; Key (lock); Computer science; Annotation; Natural language processing; Mathematics education; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006766482,0.001252898,0.0008900354,0.0009124898,0.0006527484,0.001789611,0.002143452,0.0009469006,0.004520176],"category_scores_gemma":[0.01427565,0.0003586333,0.000527266,0.0004622602,0.0005647994,0.002359719,0.002311393,0.0009940247,0.004893877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00115927,"about_ca_system_score_gemma":0.001176992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00835807,"about_ca_topic_score_gemma":0.009578864,"domain_scores_codex":[0.9931092,0.002028642,0.0006633595,0.00153306,0.002367809,0.0002979996],"domain_scores_gemma":[0.9935312,0.002721957,0.0002098604,0.0008052403,0.002348483,0.0003832835],"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":[0.004368567,0.001343689,0.09913119,0.002536521,0.00141092,0.00186876,0.004495333,0.01982061,0.08030954,0.002343023,0.1311603,0.6512116],"study_design_scores_gemma":[0.001127147,0.006829571,0.244205,0.0008449853,0.0007016935,0.003652509,0.005099749,0.3873788,0.1329218,0.00239833,0.2141115,0.0007288488],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8061837,0.002845891,0.07925841,0.001452487,0.001241835,0.00199074,0.01994519,0.06304218,0.0240396],"genre_scores_gemma":[0.7948129,0.0008771373,0.1153958,0.001726243,0.0002031946,0.001145438,0.05995798,0.003511837,0.0223695],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00835807,"threshold_uncertainty_score":0.03578502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02782759158065745,"score_gpt":0.3177921741999969,"score_spread":0.2899645826193394,"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."}}