{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1302661,0.0006810949,0.001939841,0.001481341,0.0006113109,0.0002871995,0.001442781,0.001054516,0.0000638087],"category_scores_gemma":[0.2839489,0.0006790621,0.0004535845,0.002268321,0.0009193106,0.00006649415,0.001857937,0.001757622,0.00001659188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009423011,"about_ca_system_score_gemma":0.003858451,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02144671,"about_ca_topic_score_gemma":0.007065906,"domain_scores_codex":[0.9756185,0.002348147,0.01621441,0.002098364,0.001763192,0.001957377],"domain_scores_gemma":[0.9689101,0.006392713,0.02023716,0.001592699,0.002369538,0.0004977785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002455913,0.0009065651,0.09653303,0.005833369,0.002266982,0.02956945,0.04944885,0.005630218,0.09770924,0.006763985,0.1386017,0.5642806],"study_design_scores_gemma":[0.007516417,0.0005847954,0.01533845,0.00841951,0.0008158492,0.0006339698,0.04247465,0.1262027,0.0233993,0.5410039,0.2254598,0.008150673],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5353522,0.000569676,0.3688173,0.06882364,0.005616046,0.01185917,0.00009096883,0.002921168,0.005949853],"genre_scores_gemma":[0.3665147,0.0001659262,0.6272732,0.0003288561,0.0007795828,0.002167533,0.0001449669,0.0002117492,0.002413472],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.55613,"threshold_uncertainty_score":0.9995661,"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."}}