{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006743161,0.0009217866,0.0005400497,0.008309843,0.001621724,0.001347123,0.0005832665,0.0004025046,0.04719878],"category_scores_gemma":[0.005814097,0.0004295552,0.0004583708,0.004530047,0.0003760836,0.001803149,0.0008660664,0.0005520202,0.02227639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005436085,"about_ca_system_score_gemma":0.001776888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002408684,"about_ca_topic_score_gemma":0.003558495,"domain_scores_codex":[0.9993563,0.0001145396,0.0001378934,0.00011371,0.000227888,0.00004969258],"domain_scores_gemma":[0.996021,0.001656326,0.0003840931,0.0003195197,0.001463317,0.0001558237],"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":[0.0006756826,0.0001267961,0.02912011,0.001919781,0.00009266668,0.001239029,0.001866634,0.001550223,0.04462462,0.01359138,0.1691843,0.7360087],"study_design_scores_gemma":[0.00008649631,0.0002229139,0.02390913,0.0006681429,0.0001256738,0.003452468,0.001388837,0.008634863,0.03486111,0.01361064,0.9128248,0.0002148964],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1929342,0.00348605,0.3956609,0.001061723,0.0006231606,0.0009481797,0.3026711,0.04491798,0.05769665],"genre_scores_gemma":[0.2102808,0.001714964,0.5230901,0.0002185534,0.0002129106,0.001032115,0.2316482,0.007546575,0.02425587],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04719878,"threshold_uncertainty_score":0.1578956,"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."}}