{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002451218,0.002528577,0.001117056,0.005166922,0.001049955,0.002063704,0.002104785,0.001723965,0.2508793],"category_scores_gemma":[0.01788164,0.0006854178,0.002188518,0.003682125,0.0005592353,0.001452885,0.002014957,0.002066525,0.2344099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008997743,"about_ca_system_score_gemma":0.003447757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008540195,"about_ca_topic_score_gemma":0.02448187,"domain_scores_codex":[0.9985645,0.0002839996,0.0001879441,0.0005641265,0.0002210701,0.0001783898],"domain_scores_gemma":[0.995096,0.001630266,0.0002062213,0.001628478,0.001108329,0.000330673],"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":[0.0001048794,0.00004340233,0.0005755869,0.0005998579,0.00003361329,0.00004119644,0.00002602078,0.0003220318,0.0004295741,0.000420013,0.9803476,0.01705615],"study_design_scores_gemma":[0.0004220125,0.0001137232,0.002985583,0.0005908267,0.00008673759,0.0001593653,0.0001695377,0.002496061,0.001829456,0.005359222,0.9857298,0.00005767932],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.0006743484,0.0002385184,0.002964233,0.0002692169,0.0003662341,0.0005936426,0.9795876,0.009390686,0.005915504],"genre_scores_gemma":[0.001286774,0.0001255491,0.009083525,0.0002589422,0.00005144552,0.001529788,0.9824945,0.0008460262,0.004323309],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2508793,"threshold_uncertainty_score":0.8392748,"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."}}