{"id":"W7117324681","doi":"10.1016/j.jmathb.2025.101316","title":"“It won’t work every time”: Prospective elementary teachers’ counterexamples for students’ false arguments about fractions","year":2025,"lang":"en","type":"article","venue":"The Journal of Mathematical Behavior","topic":"Mathematics Education and Teaching Techniques","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada; Bombardier","keywords":"Counterexample; Argument (complex analysis); Construct (python library); Elementary mathematics; Task (project management); Proportional reasoning; School teachers","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004140791,0.0001400184,0.0003007809,0.0001234009,0.0005997343,0.0001536317,0.0007442767,0.00008348076,0.0009481652],"category_scores_gemma":[0.0007862384,0.00009594875,0.0001690292,0.0002038582,0.0002007087,0.0001887953,0.0000704534,0.0003848188,0.00003841029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003194406,"about_ca_system_score_gemma":0.0002080001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000030206,"about_ca_topic_score_gemma":0.00002694563,"domain_scores_codex":[0.9980766,0.0002901169,0.00064491,0.0001037408,0.000637466,0.0002471253],"domain_scores_gemma":[0.9978235,0.001179871,0.0004137245,0.0002417174,0.0002448418,0.00009633198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004328166,0.01524092,0.07206454,0.0003474044,0.001291404,0.000009919044,0.2772039,0.000003369309,0.00117259,0.2246082,0.3901159,0.01750902],"study_design_scores_gemma":[0.002747142,0.000570373,0.03245646,0.003225589,0.003834619,0.00003039621,0.08632122,0.00002371432,0.001566548,0.767455,0.1009252,0.0008437283],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8576556,0.0002051029,0.1176405,0.008495833,0.0007288115,0.003330223,0.00002251106,0.0001487427,0.01177258],"genre_scores_gemma":[0.951193,0.0001222014,0.03463848,0.0009318167,0.000282656,0.0003041652,0.000003630545,0.00003263745,0.01249142],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5428468,"threshold_uncertainty_score":0.9999651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0412299444180451,"score_gpt":0.4222847164607189,"score_spread":0.3810547720426737,"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."}}