{"id":"W4393450135","doi":"10.5281/zenodo.7540792","title":"Caravan - A global community dataset for large-sample hydrology","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hydrology (agriculture); Sample (material); Environmental science; Geography; Geology; Geotechnical engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.001773478,0.0002706386,0.0003201943,0.0001877916,0.007184705,0.00135225,0.006492572,0.0001438505,0.03113396],"category_scores_gemma":[0.001198446,0.0003031598,0.00008291494,0.000689261,0.0001258606,0.0003720532,0.009884724,0.0008964642,0.001073039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002743058,"about_ca_system_score_gemma":0.00002442928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000317194,"about_ca_topic_score_gemma":0.00001138683,"domain_scores_codex":[0.9967239,0.00111808,0.0003515607,0.0006641376,0.0004806084,0.0006616932],"domain_scores_gemma":[0.9972507,0.000135116,0.0002833048,0.001846372,0.0002808367,0.0002036731],"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":[0.00002533802,0.0001966911,1.314313e-7,0.0001679006,0.00004295259,0.00001243426,0.0001833597,0.00002112606,0.000006862487,0.001258504,0.9862779,0.01180678],"study_design_scores_gemma":[0.0005102659,0.000323935,0.000005676513,0.00001530348,0.00002602919,0.0001087868,0.00006230686,0.0006526167,0.00000425096,0.000882469,0.9971158,0.0002925904],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00001337857,0.00007348758,0.07556506,0.0006738422,0.0002687592,0.0004410428,0.9217804,0.0003545725,0.0008294514],"genre_scores_gemma":[0.0001569842,0.0000437833,0.001063694,0.001747858,0.0001380955,2.743571e-7,0.9964265,0.0003804951,0.00004233569],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.07464607,"threshold_uncertainty_score":0.9999421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05481088497349262,"score_gpt":0.2909864378229017,"score_spread":0.2361755528494091,"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."}}