{"id":"W4251831351","doi":"10.31219/osf.io/czbym","title":"A thorough evaluation of the Language Environment Analysis (LENATM) system","year":2020,"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; Agence Nationale de la Recherche","keywords":"Set (abstract data type); Key (lock); Psychology; Language acquisition; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007477262,0.000201619,0.0003748754,0.0001061141,0.0000348057,0.00001741515,0.0004492647,0.0002155453,0.007110849],"category_scores_gemma":[0.00003515525,0.0001295654,0.000384624,0.0002871691,0.00003919618,0.00001357157,0.0004762659,0.0002320208,0.0001979021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001490934,"about_ca_system_score_gemma":0.00008607501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008390921,"about_ca_topic_score_gemma":0.0001521839,"domain_scores_codex":[0.997747,0.0005067628,0.0003823685,0.0004666677,0.0007409892,0.0001562032],"domain_scores_gemma":[0.9986794,0.00003270714,0.0003109757,0.0008929422,0.00004439251,0.0000395827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0003321151,0.001312965,0.1448064,0.001796474,0.05366563,0.00009487978,0.5709893,0.01883052,0.00093059,0.0405733,0.02592086,0.140747],"study_design_scores_gemma":[0.00411133,0.00008741771,0.7474529,0.0002471766,0.03564378,0.00000697008,0.1778076,0.02718853,0.001430793,0.001952944,0.002386895,0.001683668],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7064592,0.002922703,0.003876819,0.001155239,0.001203908,0.001773139,0.00008621411,0.000136665,0.2823861],"genre_scores_gemma":[0.9966374,0.00000421185,0.0003829867,0.0001327146,0.00005900294,0.0001781759,0.0001547423,0.00001640484,0.002434374],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6026465,"threshold_uncertainty_score":0.9937968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04380322914320767,"score_gpt":0.3274161561716709,"score_spread":0.2836129270284632,"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."}}