{"id":"W4393456865","doi":"10.5281/zenodo.7944025","title":"Caravan - A global community dataset for large-sample hydrology","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sample (material); Hydrology (agriculture); Environmental science; Geography; Geology; Physics; 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":[],"category_scores_codex":[0.001718747,0.0002776581,0.0003301874,0.0002083496,0.004754425,0.001563345,0.005730435,0.0002062659,0.0009060607],"category_scores_gemma":[0.001779936,0.0002992422,0.00008091368,0.0008330095,0.0001384245,0.0003660387,0.007020118,0.000705338,0.01056137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001839128,"about_ca_system_score_gemma":0.00002080765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004821429,"about_ca_topic_score_gemma":0.00002638066,"domain_scores_codex":[0.9970776,0.0007679958,0.0003597794,0.0006615624,0.0004183754,0.0007146506],"domain_scores_gemma":[0.9971952,0.0001691254,0.0002535994,0.00178411,0.0003779461,0.0002199563],"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":[0.0000178247,0.0001216462,1.155764e-7,0.0002185268,0.00004554412,0.00001319246,0.0001326163,0.00001343418,0.000007671262,0.0009573274,0.98808,0.01039208],"study_design_scores_gemma":[0.0004716258,0.0002249923,0.00001296127,0.00004123559,0.00002500955,0.00006068412,0.00004314058,0.00111471,0.000005513348,0.001278146,0.9964353,0.0002866137],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00001240901,0.00003860655,0.09192979,0.0007662352,0.0003028236,0.0004164161,0.9054061,0.000631866,0.0004957129],"genre_scores_gemma":[0.0001032255,0.00005346853,0.001130598,0.001141851,0.000215885,1.850172e-7,0.9967986,0.0004902275,0.0000659427],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.09139248,"threshold_uncertainty_score":0.999946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0672245055361929,"score_gpt":0.3027392767888361,"score_spread":0.2355147712526431,"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."}}