{"id":"W4391718096","doi":"10.31234/osf.io/4nmxh","title":"Unsupervised [randomly responding] survey bot detection: In search of high classification accuracy","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Variety (cybernetics); Set (abstract data type); Data mining; Sample (material); Machine learning; Data set; Data quality; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007520581,0.0002941709,0.0006474328,0.001190392,0.00004695372,0.0001156013,0.0004071562,0.0005231255,0.0001806715],"category_scores_gemma":[0.005334889,0.0002704717,0.0001507151,0.0009058692,0.00006850041,0.0000610895,0.000474381,0.001028254,0.00004195875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002030564,"about_ca_system_score_gemma":0.0002645268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004667374,"about_ca_topic_score_gemma":0.001298581,"domain_scores_codex":[0.9966007,0.001029102,0.001052944,0.0005839329,0.0004889577,0.0002443006],"domain_scores_gemma":[0.9931152,0.00527123,0.0002440451,0.0008817455,0.0004287539,0.00005906516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01474834,0.00503495,0.06886744,0.0502916,0.00233185,0.0001095873,0.02045951,0.002747176,0.06855784,0.3577925,0.04018959,0.3688696],"study_design_scores_gemma":[0.001420466,0.0001368228,0.1373149,0.001930016,0.00009507959,0.000008795139,0.000270029,0.03556446,0.1061223,0.7161481,0.0001118074,0.000877179],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9036729,0.0001149689,0.09156964,0.000336896,0.000534091,0.001019213,0.0001509875,0.0007491627,0.001852145],"genre_scores_gemma":[0.9822556,0.00008737511,0.01601028,0.0000105181,0.00005840781,0.000166432,0.0001679776,0.00006335328,0.00118004],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3679925,"threshold_uncertainty_score":0.9999747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2643761707962933,"score_gpt":0.426084819815171,"score_spread":0.1617086490188777,"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."}}