{"id":"W4406281472","doi":"10.1016/j.ipm.2025.104059","title":"A diversity-enhanced knowledge distillation model for practical math word problem solving","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Diversity (politics); Distillation; Mathematics; Mathematics education; Computer science; Chemistry; Sociology; Chromatography","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":[0.0005020757,0.0001196244,0.0001125944,0.000231432,0.001107064,0.0004886257,0.0002948102,0.00004169912,7.709432e-7],"category_scores_gemma":[0.00004239631,0.0001151417,0.00004597273,0.0003250489,0.00001253468,0.002928651,0.0007379947,0.00009763741,0.00002410482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001603233,"about_ca_system_score_gemma":0.00009110807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003190175,"about_ca_topic_score_gemma":0.000001448857,"domain_scores_codex":[0.9990271,0.00001802315,0.000346076,0.0001811721,0.0002049594,0.0002226394],"domain_scores_gemma":[0.9992654,0.00004100592,0.0002254007,0.0001675319,0.0002705267,0.00003018908],"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":[0.00001117463,0.00002547723,0.00002099142,0.0007867052,0.00002228757,2.605977e-7,0.009311216,0.02350109,0.000005932106,0.6929045,0.0003886391,0.2730217],"study_design_scores_gemma":[0.0002440618,0.00001067111,0.0002125927,0.0003692855,0.00001621529,5.064842e-7,0.0004731296,0.9639478,0.000060985,0.008157142,0.02637889,0.0001286652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005829202,0.0000246517,0.9706287,0.0004275831,0.0002085844,0.0005239722,5.684419e-7,0.0002323748,0.02737068],"genre_scores_gemma":[0.782035,0.000004036577,0.2078262,0.0001532625,0.00002213911,0.00007336381,0.000005859262,0.00000376281,0.009876366],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9404467,"threshold_uncertainty_score":0.8514753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02701293583463594,"score_gpt":0.2946960030078121,"score_spread":0.2676830671731762,"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."}}