{"id":"W6910447145","doi":"10.48448/987h-0v73","title":"NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Preprocessor; Parsing; The Symbolic; Table (database); Parse tree; Symbolic data analysis","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002787809,0.0006624633,0.0006121831,0.002094038,0.0002063358,0.0007303217,0.003851331,0.000387729,0.0007281546],"category_scores_gemma":[0.0007385121,0.0006364734,0.00005039654,0.005853402,0.001159622,0.001955703,0.002555822,0.0008379333,0.008135552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006819847,"about_ca_system_score_gemma":0.001513214,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008805401,"about_ca_topic_score_gemma":0.01115706,"domain_scores_codex":[0.9937773,0.0000957736,0.0007264558,0.00240304,0.001737066,0.00126033],"domain_scores_gemma":[0.9960943,0.00004098522,0.0005235001,0.003010056,0.0001389685,0.0001922245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004097067,0.0006770176,0.004676322,0.002001974,0.0001975106,0.0006168074,0.004077527,0.001974982,0.02142699,0.07181128,0.8722032,0.02029547],"study_design_scores_gemma":[0.0008202832,0.00008353305,0.0001744034,0.003356648,0.0001920772,0.00007535786,0.0009080856,0.4271268,0.0005786055,0.001573838,0.5630993,0.002011061],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0008481755,0.01251773,0.0264489,0.0003160638,0.004516202,0.002495445,0.002275663,0.003702295,0.9468795],"genre_scores_gemma":[0.1634895,0.001081344,0.1849005,0.001286911,0.00629474,0.0002028197,0.009832609,0.01193197,0.6209797],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4251518,"threshold_uncertainty_score":0.9996086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04501706533176654,"score_gpt":0.3431838697605389,"score_spread":0.2981668044287724,"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."}}