{"id":"W4220806165","doi":"10.31234/osf.io/7ezx2","title":"Supervised classes, unsupervised mixing proportions: Detection of bots in a Likert-type questionnaire","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mahalanobis distance; Sample (material); Cutoff; Computer science; Statistics; Likert scale; Mixture model; Calibration; Artificial intelligence; Data mining; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03752984,0.0007196122,0.0008870038,0.001743208,0.0009437469,0.001511801,0.002122296,0.001556277,0.001672785],"category_scores_gemma":[0.104525,0.0005813595,0.0008072932,0.001230392,0.002022757,0.002129589,0.00228467,0.001468178,0.0007582931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00104241,"about_ca_system_score_gemma":0.001056209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001329383,"about_ca_topic_score_gemma":0.001615871,"domain_scores_codex":[0.9751651,0.01675176,0.001207153,0.003605443,0.002670288,0.0006003312],"domain_scores_gemma":[0.9237684,0.05151787,0.007122677,0.01177707,0.004882851,0.000931124],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002161432,0.001063156,0.4459206,0.000464272,0.0005120725,0.0002027612,0.007695818,0.02996464,0.01586146,0.02887872,0.004843563,0.4624314],"study_design_scores_gemma":[0.0001932606,0.0006697156,0.150592,0.0001569911,0.0001185228,0.0004549465,0.001856559,0.7591349,0.02771232,0.05299122,0.005952744,0.0001669312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2857624,0.00005848919,0.709076,0.0002834135,0.00004702854,0.001425668,0.0002747608,0.0009287198,0.002143441],"genre_scores_gemma":[0.7913412,0.00002606397,0.2057436,0.000172387,0.00002842695,0.00121486,0.0004458416,0.000085574,0.0009420743],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9624702,"threshold_uncertainty_score":0.1984791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1812106920313439,"score_gpt":0.4300105893073191,"score_spread":0.2487998972759752,"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."}}