{"id":"W7077904876","doi":"10.48448/ywpx-b446","title":"NBDESCRIB: A Dataset for Text Description Generation from Tables and Code in Jupyter Notebooks with Guidelines","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Documentation; Usability; Table (database); Code (set theory); Focus (optics); Resource (disambiguation); Source code","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":[0.0005569134,0.0002321397,0.000242833,0.0002852604,0.0001557108,0.0003415329,0.0008373266,0.0001509158,0.00004542119],"category_scores_gemma":[0.0002336708,0.0001864645,0.00001547685,0.0003540706,0.0002979541,0.000322972,0.0003161948,0.00012526,0.000004427015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005119496,"about_ca_system_score_gemma":0.0004678704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001161581,"about_ca_topic_score_gemma":0.005856281,"domain_scores_codex":[0.9982004,0.00002422624,0.000293621,0.0008903283,0.0002739887,0.0003174855],"domain_scores_gemma":[0.9989155,0.00005551113,0.0001685887,0.0005860927,0.0002054456,0.0000688915],"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":[0.00002037511,0.00007974928,0.0004227837,0.0001053234,0.0000286418,0.00001628233,0.0001795382,0.001150985,0.01443908,0.01877561,0.9314864,0.03329521],"study_design_scores_gemma":[0.0005717731,0.00005367922,0.00007127724,0.0003069664,0.00001524665,0.000005430694,0.00004054876,0.3393143,0.00159699,0.004017705,0.6536563,0.0003498434],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000180409,0.0004168956,0.9772925,0.003998482,0.0003946992,0.0006086126,0.002174321,0.000117177,0.01481684],"genre_scores_gemma":[0.008546163,0.0001124324,0.8245855,0.00246448,0.0006623185,0.0001427177,0.004230093,0.00004026212,0.159216],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3381633,"threshold_uncertainty_score":0.7603802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07054459338351604,"score_gpt":0.297182975072791,"score_spread":0.2266383816892749,"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."}}