{"id":"W4393844318","doi":"10.5281/zenodo.6522634","title":"Caravan - A global community dataset for large-sample hydrology","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hydrology (agriculture); Sample (material); Environmental science; Geography; Geology; Physics","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":[0.001370445,0.0002771429,0.00033957,0.0002084887,0.004704533,0.001517869,0.005978099,0.0002104892,0.001425592],"category_scores_gemma":[0.001675311,0.0002992147,0.00008054217,0.0007204802,0.0001321331,0.0003489199,0.007181007,0.0007134079,0.0006048222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002002555,"about_ca_system_score_gemma":0.00003184517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002758005,"about_ca_topic_score_gemma":0.0000139873,"domain_scores_codex":[0.9972054,0.0008088621,0.0003581378,0.0006463485,0.0003475098,0.0006337033],"domain_scores_gemma":[0.997083,0.0001539305,0.0002361674,0.00191578,0.0004301312,0.0001809663],"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":[0.00002175738,0.0001613876,1.320398e-7,0.0002935461,0.00004859702,0.000007054475,0.0001050594,0.000009546206,0.000005929152,0.001918916,0.9809909,0.01643717],"study_design_scores_gemma":[0.0005161326,0.0001888369,0.000005300793,0.00005746181,0.00003178306,0.0000438633,0.00003001703,0.0008674574,0.000009085735,0.001046056,0.9969406,0.0002633939],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000006115301,0.00007144422,0.1639605,0.0007682033,0.0002321035,0.0003947941,0.8327987,0.0003094916,0.001458638],"genre_scores_gemma":[0.0001429125,0.00005120071,0.001844046,0.001968268,0.0001467181,1.611618e-7,0.9955718,0.0001892658,0.00008561326],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1627731,"threshold_uncertainty_score":0.999946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04401999281698787,"score_gpt":0.2955954227690002,"score_spread":0.2515754299520123,"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."}}