{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04239976,0.0006004723,0.0009914219,0.003983566,0.001455447,0.002421286,0.002045183,0.001093208,0.002482159],"category_scores_gemma":[0.1916346,0.0004950853,0.001946418,0.001682731,0.001747096,0.003035277,0.00453765,0.001149053,0.001308067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00126441,"about_ca_system_score_gemma":0.002736834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001719263,"about_ca_topic_score_gemma":0.002590396,"domain_scores_codex":[0.9453062,0.0188553,0.007375853,0.003731838,0.02335474,0.001375978],"domain_scores_gemma":[0.8109215,0.1035971,0.0238162,0.0146624,0.04348724,0.003515515],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003168799,0.001082049,0.8115079,0.001023083,0.00130094,0.0001782419,0.008838905,0.001283943,0.003906832,0.001618055,0.00197457,0.1641168],"study_design_scores_gemma":[0.000354341,0.003106965,0.9655592,0.0006365701,0.0008907648,0.0009722986,0.004712951,0.009567859,0.006420149,0.001550251,0.006010223,0.0002184098],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9775858,0.0007208763,0.006341129,0.0002610096,0.0002312292,0.001100855,0.0004510672,0.0001474567,0.01316067],"genre_scores_gemma":[0.9903237,0.0001890907,0.006653573,0.00005568217,0.00004792555,0.0007691904,0.0003971753,0.00005013367,0.001513416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9576002,"threshold_uncertainty_score":0.224234,"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."}}