{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05048972,0.00009165355,0.000166508,0.000202422,0.004108366,0.0002626128,0.0006281172,0.00004200735,0.00008651961],"category_scores_gemma":[0.02886119,0.00007115019,0.00003822477,0.001365582,0.001696755,0.001335468,0.00019469,0.0009534491,2.163369e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003514666,"about_ca_system_score_gemma":0.006342968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001621995,"about_ca_topic_score_gemma":0.0001738509,"domain_scores_codex":[0.9905269,0.00504523,0.0003866939,0.0002360776,0.003182294,0.0006227627],"domain_scores_gemma":[0.9942433,0.004233949,0.0005466639,0.00009037067,0.0007744874,0.0001112622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001487419,0.0002537058,0.002917817,0.000005401089,0.000006321533,0.000001183777,0.1654229,0.0009837551,0.000891368,0.6502589,0.0000156294,0.1792282],"study_design_scores_gemma":[0.0002265048,0.0004563836,0.03706549,0.00003872415,0.00003031245,0.00001565723,0.8199729,0.004607994,0.00006624763,0.1355613,0.001806631,0.0001518945],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9613897,0.0001024451,0.0003882698,0.01523512,0.001537149,0.0002863343,9.29526e-7,0.00001700556,0.021043],"genre_scores_gemma":[0.9887661,0.00001809773,0.01040867,0.0002139281,0.0005058798,0.00002286076,5.205665e-7,0.000004630338,0.00005933819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.65455,"threshold_uncertainty_score":0.9992902,"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."}}