{"id":"W4410554739","doi":"10.1177/00491241251339188","title":"Updating “The Future of Coding”: Qualitative Coding with Generative Large Language Models","year":2025,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Russell Sage Foundation","keywords":"Coding (social sciences); Generative grammar; Computer science; Natural language processing; Linguistics; Qualitative research; Artificial intelligence; Sociology; Social science","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.04042321,0.0001178569,0.0003649787,0.0001701724,0.001677359,0.00006897556,0.0005026357,0.0001769391,0.0002370867],"category_scores_gemma":[0.0025708,0.00006646978,0.0001473957,0.0016509,0.001451326,0.0001056277,0.0002281118,0.0007973563,0.000003221759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001248944,"about_ca_system_score_gemma":0.0002825468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003871115,"about_ca_topic_score_gemma":0.0002233953,"domain_scores_codex":[0.9705421,0.02758991,0.000309702,0.0003485035,0.0007048061,0.0005049744],"domain_scores_gemma":[0.9836655,0.01517398,0.0001217887,0.0001800652,0.0007807243,0.00007790979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003357737,0.00004334928,0.0001109683,0.00001072084,0.00009170164,0.000001980707,0.1327832,0.00008180809,0.0007955644,0.823782,0.0002319007,0.04203318],"study_design_scores_gemma":[0.0001886675,0.00006571945,0.0003307612,0.00002457674,0.00002096569,1.406636e-7,0.5135484,0.003798995,0.000438294,0.4792315,0.002260648,0.00009127773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05357642,0.001910926,0.8853077,0.01080898,0.0001221268,0.0004653877,0.00001659326,0.00005142595,0.0477404],"genre_scores_gemma":[0.6370149,0.0001343241,0.3607495,0.0002346493,0.0002982038,0.00005661263,0.000009084752,0.000005569766,0.001497242],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5834385,"threshold_uncertainty_score":0.9996223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2818745422435381,"score_gpt":0.6225325648240265,"score_spread":0.3406580225804884,"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."}}