{"id":"W1666652448","doi":"","title":"Benchmarking terrestrial models. ENSEMBLES Deliverable 6.5","year":2010,"lang":"en","type":"article","venue":"NERC Open Research Archive (Natural Environment Research Council)","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Deliverable; Benchmarking; Work (physics); Banner; Carbon cycle; Meteorology; Water cycle; Timeline; Greenhouse gas; Operations research; Environmental science; Geography; Environmental resource management; Library science; Climatology; Engineering; Computer science; Systems engineering; Ecology; Management; Archaeology","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","open_science","research_integrity","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.01913055,0.0005893398,0.0005312528,0.0001022886,0.002629258,0.0008697025,0.004488783,0.0003104584,0.01009705],"category_scores_gemma":[0.0009506618,0.0005130826,0.0002024534,0.0007560231,0.00456883,0.001822187,0.0114654,0.005929059,0.002828078],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004949913,"about_ca_system_score_gemma":0.0005428469,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02026087,"about_ca_topic_score_gemma":0.005566447,"domain_scores_codex":[0.9807023,0.001505291,0.000667212,0.002275858,0.01175184,0.003097542],"domain_scores_gemma":[0.9953696,0.001263439,0.0001262677,0.002056615,0.0001008383,0.001083272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002847759,0.002291987,0.01119976,0.0000522822,0.000219518,0.0007086197,0.003527441,0.1473149,0.4132539,0.007364726,0.181658,0.2295611],"study_design_scores_gemma":[0.002673216,0.001057028,0.01254609,0.00006397421,0.00002080621,0.00007326934,0.0009260799,0.306741,0.0008279393,0.05088353,0.6229736,0.00121342],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7022426,0.0002519156,0.002734532,0.001439731,0.0006629683,0.004189204,0.00004419039,0.00009455225,0.2883403],"genre_scores_gemma":[0.9250095,0.001755448,0.05690246,0.000191455,0.0005407416,0.0005926251,0.00007289543,0.0001364219,0.01479839],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4413157,"threshold_uncertainty_score":0.9997321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1036959062530516,"score_gpt":0.3191298178302563,"score_spread":0.2154339115772047,"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."}}