{"id":"W6902305220","doi":"10.6084/m9.figshare.26594327","title":"Additional file 2 of Exploring the merits of research performance measures that comply with the San Francisco Declaration on Research Assessment and strategies to overcome barriers of adoption: qualitative interviews with administrators and researchers","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network","funders":"","keywords":"Qualitative research; Interview; Confidentiality; Data collection; Government (linguistics); Audit","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":"evaluation","study_design":"qualitative","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"dataset","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01305628,0.0007211022,0.0008465197,0.003776341,0.002087903,0.002002458,0.001750918,0.001352121,0.8466204],"category_scores_gemma":[0.1178306,0.0006810556,0.0006005135,0.005666654,0.0005650282,0.003156167,0.001419172,0.001482851,0.1047419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003037801,"about_ca_system_score_gemma":0.00632721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01281349,"about_ca_topic_score_gemma":0.03031019,"domain_scores_codex":[0.9959999,0.001832487,0.0006552149,0.0002989383,0.0008642069,0.0003492182],"domain_scores_gemma":[0.8186142,0.1581599,0.004131733,0.003696043,0.01397718,0.001420948],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001360291,0.00007795886,0.0007415015,0.001902905,0.00000793022,0.000033746,0.0008251073,0.0001543359,0.00003520714,0.001838823,0.9857981,0.008448369],"study_design_scores_gemma":[0.003134504,0.0002628543,0.01657937,0.006338644,0.00007185941,0.0001880926,0.008899984,0.001155648,0.0005101087,0.01538153,0.9473222,0.0001551373],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0008747234,0.00003952272,0.001742458,0.001322276,0.0001204878,0.003430602,0.9801084,0.0003753865,0.01198621],"genre_scores_gemma":[0.03858553,0.0005645051,0.03799069,0.004450948,0.0003874213,0.165297,0.6469702,0.001846516,0.1039072],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9869437,"threshold_uncertainty_score":0.2187772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9093092718707463,"score_gpt":0.6988889109440457,"score_spread":0.2104203609267006,"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."}}