{"id":"W4413750761","doi":"10.2196/78682","title":"Extension of the Consolidated Criteria for Reporting Qualitative Research Guideline to Large Language Models (COREQ+LLM): Protocol for a Multiphase Study","year":2025,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Guideline; Protocol (science); Qualitative research; Computer science; Psychology; Medicine; Alternative medicine; World Wide Web; Sociology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07699444,0.0001475826,0.0004358928,0.0005751827,0.001778782,0.0002077578,0.0008242237,0.0001066059,0.00007527489],"category_scores_gemma":[0.03455335,0.0001038854,0.0002141159,0.002742239,0.0003573824,0.0001816931,0.0005715985,0.0003947043,0.000002619023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002088348,"about_ca_system_score_gemma":0.001499076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001470403,"about_ca_topic_score_gemma":0.001697809,"domain_scores_codex":[0.9869106,0.008237403,0.00159618,0.0006577158,0.001732687,0.0008654475],"domain_scores_gemma":[0.9858282,0.00498863,0.0004959593,0.0006342616,0.007889088,0.0001638244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01559906,0.01811622,0.001830555,0.002917505,0.0004264755,0.00003092999,0.5575562,0.0008223373,0.04176635,0.1079103,0.2107778,0.0422463],"study_design_scores_gemma":[0.01420159,0.004312226,0.001116178,0.003830436,0.00002072584,5.762452e-7,0.3171962,0.0590621,0.009644832,0.1732992,0.4167904,0.0005256],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"protocol","genre_scores_codex":[0.002990187,7.615093e-7,0.04299139,0.001989676,0.00000936496,0.9508467,0.00006735128,0.00003918757,0.00106541],"genre_scores_gemma":[0.01587591,1.629205e-8,0.0254737,0.00007584762,0.0001242954,0.9549384,0.000009425294,0.00001883246,0.003483546],"genre_candidate":"protocol","genre_consensus":"protocol","teacher_disagreement_score":0.2403601,"threshold_uncertainty_score":0.9995208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7942757918621323,"score_gpt":0.7988086140447332,"score_spread":0.004532822182600982,"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."}}