{"id":"W4413982879","doi":"10.3390/higheredu4030048","title":"Learning with Peers in Higher Education: Exploring Strengths and Weaknesses of Formative Assessment","year":2025,"lang":"en","type":"article","venue":"Trends in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Thomas University","funders":"Università degli Studi di Genova","keywords":"Formative assessment; Strengths and weaknesses; Peer assessment; Psychology; Assessment for learning; Mathematics education; Higher education; Pedagogy; Peer evaluation; Political science; Social psychology","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":[0.0002713768,0.0001097824,0.0001650655,0.000500805,0.0001232699,0.00006065864,0.0001238934,0.00005411515,0.0007453738],"category_scores_gemma":[0.00001424028,0.0001049388,0.00001872768,0.001169231,0.00009978044,0.0005580712,0.00003006456,0.0001674434,0.000001273684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002842066,"about_ca_system_score_gemma":0.000561344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001091955,"about_ca_topic_score_gemma":0.0006615078,"domain_scores_codex":[0.9990093,0.0001309806,0.000237607,0.000193047,0.0002478825,0.000181184],"domain_scores_gemma":[0.9994767,0.0001783722,0.0001229994,0.00009835065,0.00008648689,0.00003711857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001986191,0.000458045,0.8023782,0.0000427842,0.00002041482,1.724813e-7,0.02791186,0.00003604792,0.00002076538,0.09742789,0.0007026782,0.07098123],"study_design_scores_gemma":[0.0003216749,0.00004107875,0.9177328,0.0001992394,0.00001801862,5.781708e-8,0.0510385,0.000003608182,0.00001649366,0.0005787076,0.02993903,0.0001107488],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.741573,0.000271425,0.000002187405,0.004870499,0.001280962,0.0001192737,4.728151e-7,0.00002215361,0.25186],"genre_scores_gemma":[0.9528447,0.0001489555,0.0006052769,0.00004729054,0.000126988,0.0001824131,0.00001738809,0.00000639641,0.04602055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2112717,"threshold_uncertainty_score":0.816132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05943047214718355,"score_gpt":0.4132873053782435,"score_spread":0.3538568332310599,"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."}}