{"id":"W7129036557","doi":"10.1109/icet67421.2025.11380681","title":"A Mathematics Question Diagram Generation Strategy Defined with Codes and Empowered by Reasoning Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Diagram; Function (biology); Code (set theory); Quality (philosophy); Code generation; Encoding (memory)","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001145008,0.0003851309,0.0004448745,0.0002139759,0.0006007127,0.001908686,0.0003734252,0.0001739763,0.00003364184],"category_scores_gemma":[0.0001385666,0.0003232558,0.00004790507,0.0005558251,0.00008205679,0.00206017,0.000228285,0.0002256605,0.00000757582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000688822,"about_ca_system_score_gemma":0.0002777303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006986284,"about_ca_topic_score_gemma":0.00007377507,"domain_scores_codex":[0.997627,0.0001022918,0.0008899887,0.0004832482,0.0004178213,0.000479613],"domain_scores_gemma":[0.9983861,0.0001098348,0.0005331342,0.0005033867,0.0003361562,0.0001313497],"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":[0.000009931347,0.0003285688,0.00006051167,0.001152201,0.00008235543,0.000003396103,0.0253163,0.004309114,0.0004365898,0.9014767,0.002359055,0.06446522],"study_design_scores_gemma":[0.0007705636,0.0001133835,0.00001301256,0.0007598235,0.00004798906,0.00002093978,0.001726584,0.983566,0.002340146,0.01022476,0.00005052201,0.0003662053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03899902,0.001437227,0.9398561,0.0002186765,0.0001303809,0.0004317296,0.00001167935,0.0002333075,0.01868194],"genre_scores_gemma":[0.8110316,0.0001288652,0.1861549,0.0003617276,0.0000371719,0.00001821176,0.00004242806,0.00001512666,0.00220994],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.979257,"threshold_uncertainty_score":0.999922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01339690474757257,"score_gpt":0.2659466993643034,"score_spread":0.2525497946167309,"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."}}