{"id":"W2000242929","doi":"10.1007/s11092-014-9195-0","title":"Navigating dilemmas in transforming assessment practices: experiences of mathematics teachers in Ontario, Canada","year":2014,"lang":"en","type":"article","venue":"Educational Assessment Evaluation and Accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Situated; Accountability; Judgement; Pedagogy; Assessment for learning; Curriculum; Best practice; Mathematics education; Faculty development; Professional development; Psychology; Formative assessment; Political science; Computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007483715,0.0001323771,0.0002364628,0.00004948715,0.0002141798,0.00009123502,0.0001902647,0.00006220774,0.001675645],"category_scores_gemma":[0.0006279103,0.0001323064,0.00003027302,0.0002912103,0.0001409721,0.0006708196,0.0000261183,0.000335228,4.239731e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002408778,"about_ca_system_score_gemma":0.007218331,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9363547,"about_ca_topic_score_gemma":0.9939944,"domain_scores_codex":[0.9968973,0.0005048651,0.0006190287,0.0003094209,0.001427922,0.0002414273],"domain_scores_gemma":[0.9979545,0.001110368,0.0004901019,0.0001431114,0.0002327548,0.00006909706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002206206,0.0003801483,0.8405382,0.00002033674,0.000006491381,4.639756e-8,0.151267,0.00004699335,0.00003669066,0.004677813,0.00002114941,0.003002951],"study_design_scores_gemma":[0.0003766728,0.00001571663,0.7005319,0.00006494693,0.00001344698,1.452413e-7,0.2946471,0.001841067,0.000006590236,0.001827118,0.0005634249,0.0001118859],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9820801,0.00002126454,0.00006413774,0.002352575,0.0003463716,0.0007457044,0.000001386395,0.000005854846,0.01438261],"genre_scores_gemma":[0.9953084,0.000008397139,0.004129766,0.00007143129,0.00006525064,0.0003286995,0.00003082077,0.000005344497,0.0000518942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1433801,"threshold_uncertainty_score":0.9992369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0639113308409666,"score_gpt":0.4511814897350099,"score_spread":0.3872701588940433,"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."}}