{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01190757,0.0001253455,0.0002370371,0.0004969753,0.001483792,0.0008488076,0.0005949326,0.00004915199,0.000577016],"category_scores_gemma":[0.001209965,0.0001223457,0.00006283301,0.001108409,0.0003647277,0.0006033751,0.0002729524,0.001207195,0.000007932881],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001459993,"about_ca_system_score_gemma":0.01137188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003186423,"about_ca_topic_score_gemma":0.001561682,"domain_scores_codex":[0.9938564,0.002815457,0.0004678257,0.0002953031,0.00208559,0.0004794596],"domain_scores_gemma":[0.9957042,0.002623474,0.000107287,0.0001386844,0.001152319,0.0002739936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006102112,0.007700629,0.8570789,0.00006117547,0.0001751742,0.000004434001,0.02684071,0.000005982366,0.0001526143,0.09554146,0.0113574,0.00102052],"study_design_scores_gemma":[0.0008754724,0.0003440467,0.8710309,0.0002928899,0.000009638115,0.00001267858,0.1097559,0.00001411249,0.00002493184,0.01599116,0.001545808,0.0001024554],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9419923,0.0004638799,0.00001977606,0.02862849,0.0005258458,0.00152758,0.00001189115,0.000005106876,0.02682512],"genre_scores_gemma":[0.9959489,0.0001408568,0.001534959,0.0001290007,0.0002613692,0.000450886,0.000009703182,0.000009074823,0.001515297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08291515,"threshold_uncertainty_score":0.9998161,"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."}}