{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1450383,0.001423208,0.0009625413,0.004098671,0.004843164,0.01218582,0.004987217,0.002798446,0.009748672],"category_scores_gemma":[0.4446427,0.001556783,0.001525877,0.004195776,0.02694574,0.02438786,0.01067899,0.006763448,0.002623544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01021281,"about_ca_system_score_gemma":0.01473867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006793946,"about_ca_topic_score_gemma":0.008921273,"domain_scores_codex":[0.7985219,0.1782885,0.004230367,0.007846711,0.0100183,0.001094163],"domain_scores_gemma":[0.4858758,0.3883091,0.01418253,0.07850019,0.03091722,0.002215277],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001875412,0.00007070487,0.004540558,0.00127844,0.00009679854,0.0001957302,0.13612,0.006370578,0.001849917,0.7195998,0.01441154,0.1152783],"study_design_scores_gemma":[0.00007219223,0.00003979199,0.0008097984,0.001592215,0.00003738846,0.0001752657,0.01866881,0.03233928,0.002946022,0.8712533,0.07190628,0.0001596892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01357034,0.000486505,0.9591738,0.01505915,0.0005261713,0.0005324371,0.0007495381,0.0008488533,0.009053214],"genre_scores_gemma":[0.260394,0.0005273927,0.7280648,0.003789688,0.0001945691,0.002735575,0.0007785886,0.001122387,0.002392892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8549617,"threshold_uncertainty_score":0.767045,"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."}}