{"id":"W4408592579","doi":"10.1109/taslpro.2025.3552936","title":"A Multilingual Dataset (MultiMWP) and Benchmark for Math Word Problem Generation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Benchmark (surveying); Natural language processing; Artificial intelligence; Word (group theory); Speech recognition; 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":[0.0003431294,0.0002227039,0.0002046319,0.0002564303,0.0004664439,0.0004675033,0.0002762956,0.0001231002,0.000003983468],"category_scores_gemma":[0.00002736422,0.0001959502,0.00003703809,0.0003561292,0.00006743595,0.0006247525,0.00001090331,0.0002467509,9.573844e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004123731,"about_ca_system_score_gemma":0.0001019242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004938028,"about_ca_topic_score_gemma":0.0001016212,"domain_scores_codex":[0.9987105,0.00003815427,0.000248846,0.0005683064,0.0001544979,0.0002796665],"domain_scores_gemma":[0.9993706,0.00009418411,0.00009281292,0.0002754304,0.00008942214,0.00007752431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000264432,0.00006119807,0.000002850306,0.000245004,0.00001545753,0.00001103635,0.001148543,0.00002044148,0.02317166,0.0001205496,0.000278449,0.9748983],"study_design_scores_gemma":[0.001334758,0.0001468241,0.00001134142,0.0005487991,0.00008688067,0.0001007908,0.0003360525,0.3574418,0.6362434,0.001620899,0.001548805,0.0005796651],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01239349,0.005850531,0.9801846,0.0004698464,0.0001166508,0.0004691159,0.0001123918,0.0003580403,0.00004531443],"genre_scores_gemma":[0.4474689,0.00004350922,0.551572,0.0004863127,0.00003980761,0.00007861908,0.00004269087,0.00001146123,0.0002566465],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9743187,"threshold_uncertainty_score":0.7990619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01368458297070991,"score_gpt":0.2964765663066384,"score_spread":0.2827919833359285,"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."}}