{"id":"W4386142511","doi":"10.1101/2023.08.22.23294261","title":"ACCORD (ACcurate COnsensus Reporting Document): A reporting guideline for consensus methods in biomedicine developed via a modified Delphi","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Universiteit Leiden","keywords":"Checklist; Guideline; Delphi; Delphi method; Systematic review; Management science; Psychology; MEDLINE; Medicine; Medical education; Political science; Computer science; Engineering; Pathology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6623353,0.004018146,0.005346909,0.02290202,0.006559475,0.01553166,0.01244755,0.01076793,0.008318445],"category_scores_gemma":[0.7342563,0.005981252,0.01137098,0.01868882,0.009904987,0.0128306,0.02045581,0.01880342,0.00924948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01573132,"about_ca_system_score_gemma":0.07619859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007362047,"about_ca_topic_score_gemma":0.006956255,"domain_scores_codex":[0.1434614,0.6289436,0.180143,0.006826296,0.0377587,0.00286691],"domain_scores_gemma":[0.2089647,0.4148506,0.06117773,0.05337449,0.2564416,0.005190857],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008287814,0.0005206562,0.003703079,0.06606455,0.001051114,0.0007254575,0.04835596,0.004943547,0.003113237,0.06585167,0.3638325,0.4410094],"study_design_scores_gemma":[0.00214332,0.001091288,0.006699997,0.1947514,0.001129612,0.00138068,0.01588256,0.01384433,0.005436441,0.07126538,0.6849602,0.001414885],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003822206,0.005700456,0.7118788,0.03745131,0.006793193,0.2094834,0.007083068,0.003105553,0.01468203],"genre_scores_gemma":[0.008463849,0.002613149,0.8073925,0.003326456,0.0003908495,0.1730022,0.003060382,0.00040098,0.001349603],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3376647,"threshold_uncertainty_score":0.4164008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4747212117583177,"score_gpt":0.5896183772544429,"score_spread":0.1148971654961252,"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."}}