{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008985038,0.002136142,0.0006205415,0.003777198,0.0008165832,0.001234763,0.002063988,0.001989894,0.01313739],"category_scores_gemma":[0.007488915,0.0004906181,0.001080259,0.003102858,0.0005019485,0.001822115,0.00184737,0.001602656,0.01659901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00147652,"about_ca_system_score_gemma":0.001824274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01896451,"about_ca_topic_score_gemma":0.04637929,"domain_scores_codex":[0.9987621,0.0002346485,0.0001684555,0.0003372487,0.0004088251,0.00008865552],"domain_scores_gemma":[0.9963388,0.001586752,0.0002646837,0.0008464865,0.0006971656,0.0002660859],"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":[0.0005753189,0.0003572417,0.007952609,0.00286901,0.00009673082,0.0008917872,0.0005149567,0.004665519,0.004877951,0.002043004,0.8970626,0.07809343],"study_design_scores_gemma":[0.0004734253,0.0001988011,0.02139754,0.0005380744,0.00006493629,0.0007616169,0.0006809963,0.02619241,0.01398023,0.004129792,0.9314284,0.0001537773],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02068203,0.001194264,0.009917551,0.0005145984,0.000241328,0.0004606564,0.9236412,0.03558385,0.007764538],"genre_scores_gemma":[0.009863159,0.0002061313,0.01497517,0.0001395756,0.00001532977,0.0004192352,0.9714618,0.0007544837,0.002165141],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01896451,"threshold_uncertainty_score":0.04394901,"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."}}