{"id":"W4285490559","doi":"10.1080/15512169.2022.2099410","title":"Evaluating Simultaneous Group Activities Through Self- and Peer-Assessment: Addressing the \"Evaluation Challenge\" in Active Learning","year":2022,"lang":"en","type":"article","venue":"Journal of Political Science Education","topic":"Innovative Teaching Methodologies in Social Sciences","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Grading (engineering); Peer assessment; Scholarship; Normalization (sociology); Peer evaluation; Computer science; Mathematics education; Peer feedback; Formative assessment; Protocol (science); Psychology; Higher education; Engineering; Sociology; Political science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.1271355,0.0009210154,0.0008663553,0.001891314,0.003290331,0.003624011,0.002833688,0.001442845,0.00196882],"category_scores_gemma":[0.2409152,0.0005063265,0.0006063302,0.001420735,0.003363353,0.004034472,0.006335265,0.002189236,0.0007191621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002144508,"about_ca_system_score_gemma":0.00601733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007364345,"about_ca_topic_score_gemma":0.002812844,"domain_scores_codex":[0.8149049,0.1369887,0.009962118,0.008576143,0.02764592,0.001922175],"domain_scores_gemma":[0.6971877,0.168663,0.01887522,0.04833132,0.06145226,0.005490461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002767618,0.004530318,0.04127228,0.001114911,0.0002217706,0.0001525977,0.05919722,0.002815477,0.02861321,0.01888854,0.004895427,0.8355305],"study_design_scores_gemma":[0.003030101,0.02905257,0.2793986,0.002136267,0.0008271531,0.0008052958,0.04996361,0.075692,0.2980628,0.1281735,0.1316367,0.001221393],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5358907,0.000256996,0.422039,0.001473826,0.0004864144,0.0165364,0.0001574333,0.0007953863,0.02236397],"genre_scores_gemma":[0.6642285,0.0001161252,0.3053434,0.0003591326,0.0001528427,0.02311098,0.000111019,0.0002200897,0.006358047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1271355,"threshold_uncertainty_score":0.672365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3137626305748978,"score_gpt":0.5734745516704596,"score_spread":0.2597119210955618,"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."}}