{"id":"W4382567068","doi":"10.1007/978-3-031-36336-8_47","title":"Enhancing the Automatic Identification of Common Math Misconceptions Using Natural Language Processing","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Interpretability; Identification (biology); Computer science; Domain (mathematical analysis); Mathematics education; Cluster analysis; Blank; Natural (archaeology); Natural language processing; Artificial intelligence; Data science; Psychology; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.001710065,0.00015377,0.0002097608,0.000584957,0.0006838263,0.0005829586,0.002266476,0.00006468988,0.000001129534],"category_scores_gemma":[0.00005729058,0.0001249922,0.00004756318,0.0004897186,0.0004802094,0.003435683,0.00117414,0.0003910511,0.00002446703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001214307,"about_ca_system_score_gemma":0.0002192193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004082932,"about_ca_topic_score_gemma":0.00001570733,"domain_scores_codex":[0.9982277,0.00005006198,0.0009283198,0.00019016,0.0004298854,0.0001738712],"domain_scores_gemma":[0.9973711,0.0002313362,0.0007702013,0.001269469,0.0003253731,0.00003252103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[3.898986e-7,0.000008541756,0.00001817131,0.000117727,0.000006559991,3.201012e-7,0.01603409,0.001492167,0.0003703482,0.784114,0.000006334851,0.1978314],"study_design_scores_gemma":[0.00005583407,0.00001069838,0.0007156174,0.0007054043,0.00000610978,0.00001605914,0.0003618131,0.9951146,0.0001265917,0.0008797437,0.001859453,0.0001480733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003768896,0.00130549,0.9819158,0.0004519382,0.0008504307,0.0006914193,0.000009228357,0.0002436316,0.01076313],"genre_scores_gemma":[0.9545912,0.0002420479,0.04055344,0.0001369642,0.00005790576,0.00002022724,0.00002185801,0.00001468317,0.004361701],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9936224,"threshold_uncertainty_score":0.5621484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04389635562848965,"score_gpt":0.3196040104459846,"score_spread":0.275707654817495,"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."}}