{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02273374,0.0002166038,0.0004670114,0.0005009925,0.0004265682,0.00003420933,0.0004563446,0.0006132565,0.005340001],"category_scores_gemma":[0.02091988,0.0002329701,0.0001634693,0.00101126,0.0003023458,0.0001406653,0.0003518348,0.0009795249,0.00001182467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003757361,"about_ca_system_score_gemma":0.001821842,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02174307,"about_ca_topic_score_gemma":0.04269541,"domain_scores_codex":[0.9757721,0.0221246,0.0006670735,0.0005666592,0.000502212,0.0003673034],"domain_scores_gemma":[0.9952071,0.003721041,0.000264659,0.0004335482,0.0002767273,0.0000969514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.03093079,0.003605086,0.659416,0.00181909,0.0007508509,0.0003891218,0.1330466,0.002835631,0.03011178,0.01010693,0.003823991,0.123164],"study_design_scores_gemma":[0.001314442,0.0004106851,0.927674,0.0007033541,0.0001265503,0.00000756549,0.02428425,0.001147383,0.00307408,0.01430951,0.02567639,0.001271775],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879598,0.001184629,0.00165711,0.0008915669,0.002592377,0.001147953,0.00004858248,0.0002434932,0.0042745],"genre_scores_gemma":[0.9932353,0.0005343277,0.003764279,0.0001099529,0.0001312064,0.0002610933,0.0001057983,0.00002525991,0.001832783],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.268258,"threshold_uncertainty_score":0.9955692,"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."}}