{"id":"W3137241310","doi":"10.12688/openreseurope.13008.1","title":"Testing a computational model of causative overgeneralizations: Child judgment and production data from English, Hebrew, Hindi, Japanese and K’iche’","year":2021,"lang":"en","type":"article","venue":"Open Research Europe","topic":"Language Development and Disorders","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Economic and Social Research Council; Horizon 2020 Framework Programme","keywords":"Verb; Grammaticality; Linguistics; Psychology; Hebrew; Argument (complex analysis); Reflexive verb; Grammar; Modal verb; Philosophy; Chemistry","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":[0.0008308418,0.00009057039,0.00013757,0.00008006851,0.0002214276,0.0001528839,0.0003184457,0.00003364678,0.0004675108],"category_scores_gemma":[0.002027793,0.00008459863,0.000005949063,0.0004856261,0.0001253798,0.0003304131,0.001253845,0.0001721633,0.00001792207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001426428,"about_ca_system_score_gemma":0.0001688825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001077028,"about_ca_topic_score_gemma":0.0001705137,"domain_scores_codex":[0.9982939,0.000412444,0.0002045537,0.0005687042,0.0003264688,0.0001939017],"domain_scores_gemma":[0.9985594,0.000225532,0.00006016465,0.0004142781,0.0006661065,0.00007454976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.001050783,0.003396177,0.2131441,0.0003508036,0.001581931,0.0003784687,0.3612814,0.01479318,0.01649522,0.02403388,0.3333391,0.030155],"study_design_scores_gemma":[0.01257345,0.000553587,0.6514217,0.0009459758,0.0001923203,0.0001017307,0.08196608,0.2039334,0.002480672,0.0159905,0.02782849,0.002011992],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9379969,0.001882618,0.000171285,0.001430063,0.0001574823,0.0006855587,0.0003066333,0.00002076684,0.05734867],"genre_scores_gemma":[0.9707687,0.0001984383,0.01937006,0.0003602342,0.0001382512,0.0000606764,0.002625266,0.00004192593,0.006436375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4382776,"threshold_uncertainty_score":0.5118915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2963087469316512,"score_gpt":0.4307112702622181,"score_spread":0.1344025233305668,"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."}}