{"id":"W4388989556","doi":"10.1016/j.ipm.2023.103585","title":"Number-enhanced representation with hierarchical recursive tree decoding for math word problem solving","year":2023,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Decoding methods; Theoretical computer science; Benchmark (surveying); Tree (set theory); Representation (politics); Artificial intelligence; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004752564,0.0005553052,0.0007609896,0.0008627155,0.0004426028,0.001152051,0.001167993,0.0007877519,0.007924383],"category_scores_gemma":[0.003272561,0.0002289476,0.0007309908,0.001248469,0.0004011299,0.002471753,0.001139995,0.001110667,0.003133829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004703931,"about_ca_system_score_gemma":0.00145339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004090552,"about_ca_topic_score_gemma":0.00528601,"domain_scores_codex":[0.9994801,0.0001813113,0.00003823088,0.0001253456,0.0000975974,0.00007752508],"domain_scores_gemma":[0.9991996,0.0004097882,0.0000409958,0.0001353651,0.0001697844,0.00004455661],"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":[0.0004050432,0.000244342,0.0006546993,0.0002450346,0.00005176339,0.0001200719,0.0004667967,0.06970283,0.01933515,0.1003888,0.01245553,0.7959298],"study_design_scores_gemma":[0.00002488166,0.00004814736,0.0001998572,0.00001974016,0.0000217727,0.00003821118,0.00006141145,0.9214734,0.005148388,0.06859022,0.00435385,0.00002014175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01735799,0.0002044275,0.9749414,0.0001744254,0.0000897954,0.00005058488,0.0004083315,0.00235314,0.004420015],"genre_scores_gemma":[0.2925928,0.0002877759,0.6979394,0.0001349444,0.00008256637,0.0001929367,0.001846167,0.0004237026,0.006499786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007924383,"threshold_uncertainty_score":0.0265097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0228806507692149,"score_gpt":0.2855166168470324,"score_spread":0.2626359660778175,"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."}}