{"id":"W4383566577","doi":"10.1016/b978-0-443-15284-9.00002-1","title":"Dataset preparation","year":2023,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval; University of Ottawa","funders":"","keywords":"Process (computing); Computer science; Sample (material); Management science; Data science; Engineering; Chemistry; Programming language","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":[0.0002916476,0.0002762501,0.0002545672,0.00003618343,0.0001247918,0.00003782387,0.0003290537,0.0002821599,0.003571182],"category_scores_gemma":[0.00003660543,0.0002451799,0.0000864284,0.00001460364,0.0002435724,0.00004283275,0.0004542391,0.0003247591,0.02711198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001248444,"about_ca_system_score_gemma":0.00001159842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000022661,"about_ca_topic_score_gemma":0.00006663882,"domain_scores_codex":[0.9984668,0.00002178808,0.0002928771,0.0005553181,0.0003982088,0.0002649638],"domain_scores_gemma":[0.9991001,0.00005223744,0.0001582541,0.0005749047,0.000004466399,0.0001100179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001105825,0.000005751445,0.000009523208,0.00001415592,0.00002360783,0.00006424186,0.00007401867,0.0004009626,0.00007637197,0.0005706813,0.03335841,0.9653912],"study_design_scores_gemma":[0.00005848438,0.00006572438,0.00001490023,0.00005442685,0.00003551116,0.000009542231,1.759677e-7,0.0002323169,0.00001598908,0.01540113,0.9838421,0.0002696577],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0002280072,0.00001209526,0.000002140741,0.00005629285,0.0002542088,0.000301246,0.000544595,0.000165466,0.998436],"genre_scores_gemma":[0.00048541,0.000008437585,0.0002835044,0.0004249657,0.0001308074,0.0000178095,0.001230966,0.00006616535,0.9973519],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9651216,"threshold_uncertainty_score":0.9998146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03364178429534586,"score_gpt":0.2676409802213966,"score_spread":0.2339991959260507,"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."}}