{"id":"W4295260896","doi":"10.1007/s10459-022-10153-3","title":"How progress evaluations are used in postgraduate education with longitudinal supervisor-trainee relationships: a mixed method study","year":2022,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Supervisor; Summative assessment; Formative assessment; Psychology; Medical education; Process (computing); Longitudinal study; Reliability (semiconductor); Medicine; Pedagogy; Computer science; Management","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09619529,0.000574583,0.0009090919,0.002779072,0.001615684,0.002057608,0.001187387,0.0006754308,0.001117397],"category_scores_gemma":[0.1272651,0.000670593,0.0009850455,0.002268731,0.001277214,0.001744815,0.001994998,0.0008912792,0.0002628335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002483883,"about_ca_system_score_gemma":0.004049408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002269541,"about_ca_topic_score_gemma":0.004785251,"domain_scores_codex":[0.8964941,0.0855218,0.005503071,0.003403077,0.007087841,0.001990136],"domain_scores_gemma":[0.8306826,0.1241279,0.01950905,0.008291304,0.01461449,0.0027747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.002423388,0.004652883,0.5795305,0.001410401,0.0003491148,0.0004369832,0.1519602,0.0003964685,0.002788085,0.0004240645,0.0006697486,0.254958],"study_design_scores_gemma":[0.0004153399,0.02068182,0.8453117,0.001152655,0.0004507982,0.0007007755,0.1134025,0.003247894,0.00739565,0.0006865171,0.006346697,0.0002076879],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927197,0.0004330834,0.004438897,0.0001112985,0.00002220194,0.001305224,0.00009531234,0.00002240481,0.000851859],"genre_scores_gemma":[0.9832774,0.0003726702,0.01164221,0.0001403116,0.00003280735,0.003793575,0.0001167354,0.00002255018,0.0006016173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09619529,"threshold_uncertainty_score":0.5087354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08759495072738945,"score_gpt":0.4811399796021822,"score_spread":0.3935450288747928,"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."}}