{"id":"W4378619943","doi":"10.1017/s0305000923000272","title":"Realistic and broad-scope learning simulations: first results and challenges","year":2023,"lang":"en","type":"article","venue":"Journal of Child Language","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence de l'innovation de Défense; Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Language acquisition; Scope (computer science); Second-language acquisition; Computer science; Strengths and weaknesses; Fragmentation (computing); Cognitive science; Psychology; Linguistics; Mathematics education","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005272602,0.00009160583,0.0001596127,0.000229864,0.0001435195,0.0001342882,0.0002689479,0.00005298962,0.000001840671],"category_scores_gemma":[0.0008099381,0.00007138122,0.00002603416,0.0002425683,0.00003360219,0.0004021982,0.0001662079,0.0002944225,0.000001556125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001392682,"about_ca_system_score_gemma":0.00001597224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001513965,"about_ca_topic_score_gemma":0.00002156476,"domain_scores_codex":[0.9991857,0.00005525257,0.0002566663,0.0001554847,0.0002077511,0.0001390845],"domain_scores_gemma":[0.9991813,0.0002818279,0.0002389267,0.0001543735,0.00007103165,0.0000725183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001611306,0.00009336715,0.0004828164,0.0006433604,0.0001305774,0.002037668,0.05338965,0.001302174,0.00175828,0.029481,0.00521508,0.9053049],"study_design_scores_gemma":[0.0222885,0.007033976,0.1184471,0.01836368,0.0005325193,0.0186287,0.01240968,0.2782806,0.03415614,0.125955,0.3579069,0.005997206],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1978991,0.6793546,0.02979865,0.08416601,0.0006171817,0.0004968386,0.00002866591,0.001753439,0.005885543],"genre_scores_gemma":[0.9699901,0.006758706,0.02282769,0.0001540893,0.0001574573,5.593906e-7,0.000002333162,0.00001008464,0.00009898305],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8993077,"threshold_uncertainty_score":0.2910842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0178879742079047,"score_gpt":0.2774399470724877,"score_spread":0.259551972864583,"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."}}