{"id":"W4415150289","doi":"10.1002/berj.70056","title":"Self‐ and peer‐assessment in upper secondary schools. A quasi‐experimental study to investigate the educational effectiveness of formative assessment","year":2025,"lang":"en","type":"article","venue":"British Educational Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Thomas University","funders":"","keywords":"Formative assessment; Summative assessment; Metacognition; Knowledge survey; Test (biology); Educational research","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":[],"consensus_categories":[],"category_scores_codex":[0.01219724,0.0007910531,0.001333576,0.001090421,0.002177694,0.001371008,0.0009356714,0.0008501537,0.003089583],"category_scores_gemma":[0.01571846,0.000870971,0.0006936392,0.0004481099,0.001759241,0.0007595066,0.001092529,0.001504333,0.0008950948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260588,"about_ca_system_score_gemma":0.003127216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003237368,"about_ca_topic_score_gemma":0.003448293,"domain_scores_codex":[0.9937062,0.003018156,0.000409521,0.0008675449,0.00106275,0.00093593],"domain_scores_gemma":[0.9867491,0.004955975,0.002090008,0.001594772,0.001312148,0.00329795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"nonrandomized_trial","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.01590876,0.5517728,0.2126621,0.0007499701,0.0002735056,0.0004873333,0.07370545,0.0006813824,0.01988686,0.0007236786,0.001340754,0.1218075],"study_design_scores_gemma":[0.006964603,0.2873627,0.6646575,0.0002562156,0.0002027095,0.0002949552,0.01812655,0.002051676,0.01025048,0.0007044938,0.008955243,0.0001728918],"study_design_candidate":"nonrandomized_trial","study_design_consensus":"nonrandomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9993906,0.0000216766,0.00008005033,0.0000156554,0.00001004768,0.0002384011,0.00001081583,0.000006601433,0.0002261284],"genre_scores_gemma":[0.9977378,0.00004136661,0.0007466772,0.00003559457,0.00001550214,0.0006251923,0.00003138266,0.000003762414,0.0007627544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01219724,"threshold_uncertainty_score":0.06450593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04421725327059,"score_gpt":0.4866450570754541,"score_spread":0.4424278038048641,"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."}}