{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004175421,0.0001339117,0.0001243877,0.0002387276,0.0003192969,0.0006651254,0.000431643,0.00003760775,0.000002399091],"category_scores_gemma":[0.00003116604,0.0001211113,0.00003538579,0.0007934986,0.00001946889,0.003483214,0.0002028433,0.00009069619,0.00006856107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009017475,"about_ca_system_score_gemma":0.00004645235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003784027,"about_ca_topic_score_gemma":0.000003409755,"domain_scores_codex":[0.9985753,0.00001711603,0.0004143719,0.0002642801,0.0004017476,0.0003272234],"domain_scores_gemma":[0.9991801,0.00005068562,0.0002618097,0.0002916618,0.0001624082,0.00005329938],"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":[0.00002044303,0.000009523397,0.00003688515,0.0003548939,0.00001729876,0.000001903956,0.006089649,0.008834885,0.00001202593,0.04821198,0.0004038322,0.9360067],"study_design_scores_gemma":[0.0008485666,0.00003211841,0.0007200755,0.0003770695,0.00001708923,0.000005429798,0.001451449,0.9619865,0.0004281342,0.031496,0.002385133,0.0002524383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01047051,0.000004104244,0.9719111,0.001081711,0.000119506,0.0006978816,8.233407e-7,0.0005612415,0.01515315],"genre_scores_gemma":[0.3722119,0.00001055355,0.6266065,0.0002856465,0.00004047869,0.0003126099,0.0000357192,0.00001019611,0.0004864073],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9531516,"threshold_uncertainty_score":0.6413819,"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."}}