{"id":"W4401043227","doi":"10.18653/v1/2024.clinicalnlp-1.62","title":"Overview of the EHRSQL 2024 Shared Task on Reliable Text-to-SQL Modeling on Electronic Health Records","year":2024,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation; National Research Foundation of Korea; Strong","keywords":"Computer science; Task (project management); SQL; Health records; Electronic health record; World Wide Web; Database; Health care; Engineering; Political science","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008162837,0.0001605811,0.0002690696,0.0004003242,0.0002271958,0.0006600047,0.001522432,0.00003704942,0.001085573],"category_scores_gemma":[0.001061847,0.00008763779,0.0001686092,0.002716386,0.00002383268,0.0001515147,0.0006072277,0.0002742975,0.002159823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001792735,"about_ca_system_score_gemma":0.0003170015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004535777,"about_ca_topic_score_gemma":0.0002638113,"domain_scores_codex":[0.9955993,0.0001610557,0.000734938,0.001091747,0.001918048,0.000494918],"domain_scores_gemma":[0.9971012,0.0006661865,0.0001039963,0.001892254,0.0001182279,0.0001181323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001372568,0.00004376613,0.00001419752,0.00002675813,0.0000114427,7.750118e-7,0.0001979917,0.03305656,0.0000109797,0.01983511,0.8707672,0.07602149],"study_design_scores_gemma":[0.00007255263,0.0002033786,0.00007959809,0.0003942754,0.00000562317,6.539898e-7,0.0002287854,0.5058217,0.00003358992,0.01286639,0.4801871,0.0001063416],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1792174,0.009581045,0.1857861,0.1493666,0.1347087,0.004749776,0.0006061741,0.00134438,0.3346399],"genre_scores_gemma":[0.9077452,0.0001348869,0.0007377836,0.003964781,0.0003941515,0.00001500874,0.000008969665,0.00002248132,0.08697672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7285278,"threshold_uncertainty_score":0.9998276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1986647325953776,"score_gpt":0.4249938521769817,"score_spread":0.2263291195816041,"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."}}