{"id":"W4402008279","doi":"10.31235/osf.io/wg82k","title":"Updating “The Future of Coding”: Qualitative Coding with Generative Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generative grammar; Coding (social sciences); Computer science; Natural language processing; Generative model; Artificial intelligence; Linguistics; Mathematics; Statistics; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.001177825,0.000321384,0.0004137647,0.0001401171,0.000137092,0.0002812989,0.001291919,0.0001693135,0.00002611946],"category_scores_gemma":[0.00001729624,0.0001959608,0.000128325,0.0002833802,0.00005277324,0.0001940228,0.002840442,0.0009705867,0.000008525682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007942718,"about_ca_system_score_gemma":0.0002086657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001392916,"about_ca_topic_score_gemma":0.0001978339,"domain_scores_codex":[0.9976128,0.0002910795,0.0004593546,0.0007903008,0.0005144641,0.0003320287],"domain_scores_gemma":[0.9982437,0.0001855063,0.0002921572,0.001022435,0.0001967939,0.00005938648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002813886,0.00001335491,0.000001474177,0.0001552993,0.00009640142,0.00001423056,0.1541285,0.01275128,0.0001509376,0.8300085,0.0004215605,0.002255622],"study_design_scores_gemma":[0.0001403516,0.00002451656,0.000001038124,0.000295647,0.0000276601,0.000006417932,0.03379032,0.8972554,0.001645852,0.06646932,0.00006318529,0.0002802846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01264869,0.001290552,0.9718255,0.00249032,0.0006993453,0.0003908149,0.00005070844,0.0002295903,0.01037448],"genre_scores_gemma":[0.7483199,0.00002576851,0.2500908,0.0003202072,0.0003670334,0.00004252975,0.00001776449,0.00002348576,0.0007925166],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8845041,"threshold_uncertainty_score":0.7991048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04143052169491773,"score_gpt":0.3302597114237466,"score_spread":0.2888291897288289,"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."}}