{"id":"W4211222398","doi":"10.1037/cep0000271","title":"Determining the importance of frequency and contextual diversity in the lexical organization of multiword expressions.","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale","topic":"Linguistics, Language Diversity, and Identity","field":"Arts and Humanities","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Word lists by frequency; Lexical item; Linguistics; Natural language processing; Lexicon; Computer science; Diversity (politics); Context (archaeology); Psychology; Operationalization; Consistency (knowledge bases); Word (group theory); Artificial intelligence; Sentence; Sociology","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":[0.0006399839,0.0001292921,0.000239432,0.0002096611,0.000647891,0.00002810509,0.0007810177,0.0000463675,0.000816184],"category_scores_gemma":[0.0006544871,0.0001043393,0.00007642688,0.0001217431,0.0007318401,0.0001239591,0.0001268374,0.0003224708,8.424016e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002579608,"about_ca_system_score_gemma":0.000111901,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01120294,"about_ca_topic_score_gemma":0.05921676,"domain_scores_codex":[0.9987319,0.0002102595,0.0004273866,0.0001960352,0.0001032445,0.0003311534],"domain_scores_gemma":[0.9988096,0.0000918713,0.000394902,0.0002563591,0.0002658523,0.0001813595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003790365,0.0002240734,0.7620608,0.000008528847,0.0000421727,0.0001700102,0.2240584,0.0000036227,0.0011116,0.002820005,0.009359248,0.0001037319],"study_design_scores_gemma":[0.003036489,0.001016044,0.3386357,0.0000609045,0.00007082356,0.0001338071,0.6520722,0.000006426794,0.001141545,0.001434574,0.002062577,0.0003288972],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942603,0.0009171328,0.000004395683,0.0001926978,0.003027324,0.000174886,0.0001341702,0.000003103854,0.001286032],"genre_scores_gemma":[0.9982584,0.0000103067,0.00007358032,0.00119965,0.000391108,0.000004276515,0.00001266048,0.00001058617,0.00003943937],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4280138,"threshold_uncertainty_score":0.9953815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06765920548252147,"score_gpt":0.2858121736012857,"score_spread":0.2181529681187642,"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."}}