{"id":"W4366817651","doi":"10.1016/j.cptl.2023.04.004","title":"Assessment of the validity of peer scores and peer feedback in an online peer assessment platform (Kritik)","year":2023,"lang":"en","type":"article","venue":"Currents in Pharmacy Teaching and Learning","topic":"Innovations in Medical Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Peer assessment; Peer feedback; Peer review; Peer evaluation; Psychology; Computer science; Applied psychology; Mathematics education; Higher education; Political science","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":[0.005449268,0.0001292379,0.0002694279,0.0003169001,0.000161366,0.00002200054,0.0001180307,0.00005109146,0.00004577709],"category_scores_gemma":[0.002702286,0.0001013055,0.00003098166,0.0004404012,0.000125523,0.0001799991,0.0001227595,0.002200996,4.353539e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001034541,"about_ca_system_score_gemma":0.0001575953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001601943,"about_ca_topic_score_gemma":0.00001227794,"domain_scores_codex":[0.9978051,0.0003598744,0.0004843809,0.0002395964,0.0009005425,0.0002105616],"domain_scores_gemma":[0.9991246,0.0002060827,0.0001821472,0.0001656131,0.0002690767,0.00005252011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001155426,0.0004343276,0.8875434,0.0002405627,0.00001287229,0.000001775206,0.003412622,0.0002775147,0.000753088,0.0002057063,0.000625562,0.106481],"study_design_scores_gemma":[0.001839464,0.00007325262,0.9226652,0.0005823624,0.0000339892,0.000006166772,0.003982238,0.06604148,0.00006435926,0.00007872386,0.004542855,0.00008992019],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961146,0.00003301297,0.00008057717,0.002442067,0.0005242225,0.000247029,0.00000834992,0.00002685373,0.0005233531],"genre_scores_gemma":[0.9968446,0.00004677624,0.002113157,0.0001017709,0.0001224375,0.00001395593,0.0002053627,0.0000165003,0.0005353753],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1063911,"threshold_uncertainty_score":0.9562355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1276765278907462,"score_gpt":0.4797441963164834,"score_spread":0.3520676684257372,"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."}}