{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004080497,0.0001231949,0.0001226681,0.00008534525,0.0004847954,0.0004638231,0.0007317899,0.00004371885,1.060722e-7],"category_scores_gemma":[0.0001234629,0.00008909241,0.00003551379,0.0003605848,0.00003481273,0.0001925044,0.0007081951,0.0002198783,4.245165e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001723635,"about_ca_system_score_gemma":0.00004100535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007140433,"about_ca_topic_score_gemma":0.00000201951,"domain_scores_codex":[0.9990602,0.00003995431,0.0001877626,0.0003377036,0.0001073926,0.0002669749],"domain_scores_gemma":[0.9990292,0.0004919745,0.00009782953,0.0002864094,0.00007082373,0.00002380919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004328216,0.00001849364,0.0004412717,0.0004227119,0.00001517657,0.00001188012,0.001149925,0.00008740416,0.006282791,0.4128321,0.0006359041,0.5780981],"study_design_scores_gemma":[0.0002940298,0.00004797249,0.0004499609,0.00072509,0.00002371079,0.0000666893,0.0000881923,0.8447764,0.01235324,0.1359446,0.004917042,0.0003130893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01323527,0.0009329892,0.9805305,0.00384131,0.0001605842,0.0003980402,2.909105e-7,0.0006179602,0.0002830844],"genre_scores_gemma":[0.4482709,0.000004987719,0.5507159,0.0008823233,0.00003948516,0.000009063359,2.132667e-7,0.000007229101,0.00006987993],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.844689,"threshold_uncertainty_score":0.4472657,"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."}}