{"id":"W7017577258","doi":"","title":"Balancing Assessment: How School Leaders Can Support Balanced Assessment Systems in Secondary Schools","year":2022,"lang":"en","type":"other","venue":"National University System Repository (National University System)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Capstone; Standardized test; Formative assessment; Capstone course; Function (biology); Test (biology); Authentic assessment; Standards-based assessment","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.003983345,0.001358713,0.001982656,0.006585962,0.001667602,0.0004422292,0.002395098,0.001262754,0.001002497],"category_scores_gemma":[0.0001242464,0.001908293,0.0006859749,0.002749458,0.0003130154,0.001359255,0.0008061575,0.002934788,0.0004257434],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.09928101,"about_ca_system_score_gemma":0.0177525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006117162,"about_ca_topic_score_gemma":0.0009112062,"domain_scores_codex":[0.9829034,0.005078174,0.001033737,0.002525151,0.007291776,0.001167778],"domain_scores_gemma":[0.9927139,0.0006326862,0.002708762,0.0009894378,0.002122203,0.000832969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004730747,0.0005492654,0.03712781,0.009782082,0.003022088,0.007104674,0.000245138,0.006143654,0.001287689,0.1685682,0.7656903,0.000005982987],"study_design_scores_gemma":[0.0116991,0.0002386986,0.02421992,0.005982439,0.0006606202,0.001611756,0.1245721,0.008129733,0.00001070614,0.000007824709,0.8194035,0.003463612],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0007660987,0.0001736511,0.0003736044,0.0002512176,0.003306984,0.00365588,0.01128963,0.001939202,0.9782437],"genre_scores_gemma":[0.580802,0.00001023988,0.0005510466,0.0000298818,0.0006803267,0.00001970575,0.005794263,0.0005880211,0.4115245],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5800359,"threshold_uncertainty_score":0.9999164,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01312908886980351,"score_gpt":0.230825913014756,"score_spread":0.2176968241449525,"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."}}