{"id":"W4397030200","doi":"10.1007/s42330-024-00315-3","title":"Assessing Mathematical Deductive Reasoning Competence of Eighth-Grade Students from China","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Competence (human resources); Deductive reasoning; Psychology; Logical reasoning; Science education; Grade level; China; Abstract reasoning; Context (archaeology); Cognition; Pedagogy; Geography; Computer science; Social psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006661856,0.0005448841,0.000515746,0.001374471,0.00117988,0.001072967,0.0005122862,0.0004952415,0.001703931],"category_scores_gemma":[0.002018267,0.0002496885,0.0003634915,0.0009790844,0.0004460104,0.0006686234,0.0008889871,0.0006458388,0.0004550875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001194616,"about_ca_system_score_gemma":0.003873829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08025651,"about_ca_topic_score_gemma":0.09735149,"domain_scores_codex":[0.9995779,0.00003241188,0.00005827061,0.00008543964,0.0001314539,0.0001144902],"domain_scores_gemma":[0.9985903,0.000111225,0.0002067929,0.00006346111,0.0005348981,0.0004933995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008933436,0.0004418402,0.9653336,0.00005578094,0.00003143533,0.0002457819,0.01035444,0.000162671,0.002753612,0.0002868684,0.0004894916,0.01975505],"study_design_scores_gemma":[0.00001264407,0.0002038187,0.9940705,0.00001757683,0.00002430277,0.00009070225,0.003347568,0.0004823266,0.0007199061,0.0001325186,0.0008880125,0.00001005193],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9993451,0.00002321251,0.00001557919,0.0000206814,0.000001735034,0.000004982311,0.00004227878,0.0000012691,0.0005450473],"genre_scores_gemma":[0.9979767,0.00005262825,0.00006570374,0.00001684619,0.000001518786,0.00001013437,0.0001767555,0.000001128131,0.00169856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08025651,"threshold_uncertainty_score":0.1595787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02053476746901769,"score_gpt":0.3363943752514828,"score_spread":0.3158596077824651,"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."}}