{"id":"W6946104736","doi":"10.3389/frai.2021.648543.s001","title":"Data_Sheet_1_Considering Performance in the Automated and Manual Coding of Sociolinguistic Variables: Lessons From Variable (ING).PDF","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Coding (social sciences); Workflow; Pronunciation; Variable (mathematics); Variation (astronomy); Natural language; Random forest; Ground truth","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05062896,0.0008941197,0.001169516,0.004683147,0.001873802,0.003831271,0.003814693,0.002583253,0.2471442],"category_scores_gemma":[0.2337166,0.001011103,0.001567821,0.006959747,0.001401775,0.0046899,0.003626346,0.002535118,0.08689705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002672243,"about_ca_system_score_gemma":0.006160668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009203016,"about_ca_topic_score_gemma":0.01415502,"domain_scores_codex":[0.9695317,0.01297404,0.004788382,0.001961154,0.009906197,0.0008385008],"domain_scores_gemma":[0.6596984,0.2049263,0.01147096,0.04632794,0.07508925,0.002487103],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0008923694,0.0001643274,0.006745095,0.002245008,0.0000564112,0.00008598121,0.0007161512,0.0007768289,0.0006023631,0.00541576,0.86339,0.1189097],"study_design_scores_gemma":[0.0004386654,0.0002754399,0.04228099,0.002923728,0.00004721236,0.0001584465,0.00129277,0.001512855,0.002565227,0.008148451,0.9401522,0.0002039182],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00503709,0.0003830077,0.01789176,0.007897742,0.0009918523,0.005277007,0.9178916,0.003999683,0.04063024],"genre_scores_gemma":[0.045068,0.001323971,0.155413,0.01008889,0.0007876131,0.05023598,0.6788896,0.005437604,0.05275522],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.949371,"threshold_uncertainty_score":0.8267797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0702464039766101,"score_gpt":0.3259831756698855,"score_spread":0.2557367716932755,"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."}}