{"id":"W4296865992","doi":"10.3102/1679721","title":"Comparing Unsupervised Machine Learning Algorithms to Cluster the Responses to the Canadian Community Health Survey","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 AERA Annual Meeting","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Unsupervised learning; Cluster (spacecraft); Artificial intelligence; Machine learning; Algorithm; Computer network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.010907,0.0002439514,0.0003175617,0.00005883801,0.003357915,0.0001763734,0.001140657,0.00006217531,0.0001383851],"category_scores_gemma":[0.004554503,0.0001569439,0.0000837588,0.001035477,0.0001854294,0.0001973363,0.001792978,0.001214747,0.0001070874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007038664,"about_ca_system_score_gemma":0.0001532282,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.4865569,"about_ca_topic_score_gemma":0.6949184,"domain_scores_codex":[0.996336,0.001238492,0.0004940248,0.0004709608,0.000665377,0.0007951066],"domain_scores_gemma":[0.9979474,0.000894383,0.0002298746,0.0003933889,0.0001198286,0.0004151162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006598177,0.00006104341,0.9458447,0.00003909234,0.00003199608,0.000001424136,0.03484093,0.003884925,0.00201972,0.00001641415,0.002907269,0.01028658],"study_design_scores_gemma":[0.0002562743,0.0001026818,0.9622387,0.0002487386,0.00001634773,0.00001799366,0.01494555,0.00312031,0.002663104,0.00003080398,0.01609304,0.0002664258],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9676974,0.00009771961,0.00003062816,0.02744319,0.0001338533,0.0007476496,0.00007057788,0.00001967815,0.003759345],"genre_scores_gemma":[0.9891977,0.00002302438,0.0008996207,0.009004598,0.00007388469,0.00003801967,0.000009070584,0.00003768785,0.0007163698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2083616,"threshold_uncertainty_score":0.9979396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0359772690094172,"score_gpt":0.2788880380899685,"score_spread":0.2429107690805513,"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."}}