{"id":"W4406793594","doi":"10.1038/s41598-025-87380-2","title":"Development of a checklist for cognitive assessment requirements (CARE) based on a Delphi consensus study","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Checklist; Delphi method; Delphi; MEDLINE; Cognition; Computer science; Medicine; Psychology; Artificial intelligence; Biology; Psychiatry","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":[0.009505849,0.0001421133,0.0002528219,0.0005158256,0.001242852,0.0002413895,0.0002968561,0.00007949191,0.00006037077],"category_scores_gemma":[0.001991917,0.0001396177,0.00009653775,0.001110739,0.0006925639,0.00005637567,0.0001196942,0.0001215713,0.000002845348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000532399,"about_ca_system_score_gemma":0.004828524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001913774,"about_ca_topic_score_gemma":0.00125675,"domain_scores_codex":[0.9959515,0.0002445775,0.0008145123,0.0008008739,0.001732052,0.0004565135],"domain_scores_gemma":[0.9969997,0.0004226035,0.0003679637,0.0005564707,0.001539825,0.0001134071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001595247,0.02093255,0.2753238,0.001799695,0.001192592,0.001802214,0.2108213,0.0002355136,0.0392858,0.01297718,0.1450655,0.2889685],"study_design_scores_gemma":[0.005738128,0.00128781,0.04105386,0.002934594,0.0003377385,0.000004706684,0.4454481,0.001598759,0.1190443,0.01669961,0.364244,0.001608478],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8932929,0.00002827166,0.007239894,0.0005537447,0.003801126,0.007635858,0.00001612134,0.0001677986,0.0872643],"genre_scores_gemma":[0.9847514,2.72886e-7,0.01154438,0.00003769408,0.00001738928,0.0007656656,0.00002948428,0.00001049243,0.002843244],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.28736,"threshold_uncertainty_score":0.9559137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1445342508448562,"score_gpt":0.5058025185177568,"score_spread":0.3612682676729005,"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."}}