{"id":"W3164004475","doi":"10.1111/lang.12452","title":"The Nuclear Word Family List: A List of the Most Frequent Family Members, Including Base and Affixed Words","year":2021,"lang":"en","type":"article","venue":"Language Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Word (group theory); Construct (python library); Word list; Computer science; Linguistics; Natural language processing; Nuclear family; Psychology; Artificial intelligence; Programming language; Sociology","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":[0.0006663562,0.0001979471,0.0002186167,0.00005903059,0.0007100491,0.0004795704,0.001080611,0.0001001259,0.00001675529],"category_scores_gemma":[0.0008657767,0.0001278661,0.00008970287,0.0008704996,0.0001617055,0.0002910508,0.00143358,0.0007409606,0.000002463162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006613834,"about_ca_system_score_gemma":0.00009717993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005493883,"about_ca_topic_score_gemma":0.0001598325,"domain_scores_codex":[0.9981563,0.0003469955,0.0002870715,0.0004195788,0.0004357526,0.000354264],"domain_scores_gemma":[0.9984798,0.0003491118,0.0002396177,0.0007286877,0.0001279462,0.00007482586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003785037,0.00007989879,0.001891321,0.0001822968,0.0000936737,0.000536721,0.04367534,0.0001034609,0.6074471,0.02728353,0.001887208,0.3167816],"study_design_scores_gemma":[0.005175347,0.0008065611,0.01387467,0.006812436,0.0004078035,0.00122329,0.1303991,0.1975734,0.4349302,0.01712371,0.1862041,0.005469362],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9324508,0.04485283,0.01309915,0.003749644,0.0004797744,0.0003054868,0.000005222011,0.0008636158,0.004193495],"genre_scores_gemma":[0.9368118,0.0001266327,0.06068742,0.001255349,0.00007766072,0.000007604278,0.000002718522,0.00003036004,0.001000464],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3113122,"threshold_uncertainty_score":0.5461196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01210238985731501,"score_gpt":0.2534263177498619,"score_spread":0.2413239278925468,"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."}}