{"id":"W6910107838","doi":"10.4224/20377598","title":"Results of the HAMSTAD benchmarking exercises using hygIRC 1D Version 1.1","year":2006,"lang":"en","type":"report","venue":"NPARC","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Robustness (evolution); Benchmark (surveying); Reliability (semiconductor); Work (physics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01388479,0.001177205,0.001238367,0.00182758,0.0008499788,0.001505081,0.001352408,0.0009693487,0.006437346],"category_scores_gemma":[0.02519781,0.000466834,0.0007464741,0.001989105,0.0004688035,0.0009814496,0.001548308,0.0008524066,0.004063388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001443617,"about_ca_system_score_gemma":0.0009372508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008447732,"about_ca_topic_score_gemma":0.008350451,"domain_scores_codex":[0.9896404,0.00424978,0.0006557665,0.0007998446,0.004144378,0.0005097991],"domain_scores_gemma":[0.9840164,0.005334775,0.0007340862,0.002751657,0.006656724,0.0005063719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004486558,0.003974694,0.02183428,0.001698443,0.0001709733,0.0004142484,0.002025863,0.3794203,0.01970815,0.006508043,0.1195207,0.4402377],"study_design_scores_gemma":[0.0007133613,0.00729904,0.1486057,0.0007051482,0.0002687736,0.0004426375,0.003018883,0.5098371,0.123818,0.008425245,0.1961659,0.0007002545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.737359,0.001406949,0.09734321,0.001109651,0.000755863,0.00174446,0.02960179,0.01113671,0.1195424],"genre_scores_gemma":[0.8444252,0.0005218099,0.09440494,0.0001677558,0.00006359604,0.001175938,0.03254539,0.003061427,0.02363383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01388479,"threshold_uncertainty_score":0.07343072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04862593931209611,"score_gpt":0.2965930559980333,"score_spread":0.2479671166859372,"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."}}