{"id":"W6962501024","doi":"10.17605/osf.io/39a2m","title":"Accurate Versus Inaccurate Labelers (July 2017)","year":2017,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Noise (video); Reliability (semiconductor); Feature (linguistics); Key (lock); Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":false,"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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003164169,0.0006446623,0.001265117,0.0005431952,0.0004024667,0.0004803874,0.002612878,0.0005926339,0.846247],"category_scores_gemma":[0.002075735,0.0008175388,0.0004233886,0.0001359187,0.0004906951,0.0003885368,0.002175189,0.0005732423,0.9908257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000373535,"about_ca_system_score_gemma":0.0001017653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001267317,"about_ca_topic_score_gemma":0.0002370225,"domain_scores_codex":[0.9946166,0.00007636262,0.0008474956,0.003545731,0.0001124483,0.0008014044],"domain_scores_gemma":[0.9916561,0.0001644682,0.001942229,0.005910334,0.00005547615,0.0002713687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008132918,0.00009548121,0.0005155309,0.00008796029,0.0007524912,0.00002402652,0.0003259058,0.0000478804,0.00000232607,0.01065859,0.9860073,0.001401158],"study_design_scores_gemma":[0.001378945,0.000001233398,0.0003838892,0.0001176924,0.00005310757,0.000003776349,0.00008620556,0.0001204118,0.00001839925,0.001430728,0.9955987,0.0008068659],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00007493835,0.00007172661,0.0001280729,0.000127134,0.008782453,0.0007135359,0.001218152,0.0002321972,0.9886518],"genre_scores_gemma":[0.0007649109,0.00252249,0.0003081197,0.00008242156,0.0003307739,0.0001490984,0.00006265836,0.0002795786,0.9955],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1445788,"threshold_uncertainty_score":0.9994276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06390379466558854,"score_gpt":0.2641865076702731,"score_spread":0.2002827130046846,"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."}}