{"id":"W4408800806","doi":"10.1016/j.neucom.2025.130042","title":"Unifying the syntax and semantics for math word problem solving","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation for Distinguished Young Scholars of Hunan Province; Central China Normal University; China Postdoctoral Science Foundation; Ministry of Education of the People's Republic of China","keywords":"Syntax; Semantics (computer science); Computer science; Word (group theory); Abstract syntax tree; Natural language processing; Artificial intelligence; Linguistics; Programming language; Mathematics; Algebra over a field; Pure mathematics; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.00196924,0.0007290944,0.001021054,0.001213845,0.001238193,0.004448407,0.00195809,0.001482473,0.006382857],"category_scores_gemma":[0.00773271,0.0007779533,0.002419705,0.00124382,0.003349756,0.01347234,0.003883482,0.003059663,0.00132418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001283705,"about_ca_system_score_gemma":0.0026189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004503927,"about_ca_topic_score_gemma":0.005583641,"domain_scores_codex":[0.9979747,0.0006630889,0.0003151744,0.0004953908,0.0003288757,0.0002228007],"domain_scores_gemma":[0.9973276,0.001149597,0.0002376568,0.0006865381,0.0004577165,0.0001408462],"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":[0.0001034389,0.00006033356,0.0006864372,0.0001639468,0.00002734567,0.00006837639,0.0008618387,0.00469181,0.002329798,0.9286314,0.002254626,0.06012063],"study_design_scores_gemma":[0.00001532024,0.00002004464,0.0002511237,0.0000268457,0.0000206243,0.00004224292,0.000136226,0.02920072,0.001068207,0.96544,0.003759522,0.00001902954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03723237,0.0004935561,0.9444634,0.001820271,0.0002285912,0.0001261032,0.0008049061,0.001934188,0.01289666],"genre_scores_gemma":[0.5439271,0.0004479712,0.4470719,0.0005559474,0.0002238502,0.0002536809,0.001627839,0.0008158543,0.005075949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006382857,"threshold_uncertainty_score":0.02135277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01244940995402049,"score_gpt":0.2720112182723778,"score_spread":0.2595618083183573,"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."}}