{"id":"W2883136262","doi":"10.4995/carma2018.2018.8331","title":"Fishing for Errors in an Ocean Rather than a Pond","year":2018,"lang":"en","type":"article","venue":"","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Estimator; Key (lock); Upgrade; The Internet; Software; Service (business); Real-time computing; Distributed computing; Data mining; Computer security; World Wide Web; Statistics; Operating system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002790634,0.00007374215,0.00007732968,0.00005926537,0.00006224492,0.0001529508,0.000532108,0.00004368588,0.00002250696],"category_scores_gemma":[0.00001898745,0.00006186648,0.00002371899,0.0001557988,0.00002728,0.0005333268,0.0000649268,0.0000575963,0.00002458372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000884406,"about_ca_system_score_gemma":0.0000378079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001029595,"about_ca_topic_score_gemma":0.0006334085,"domain_scores_codex":[0.9992959,0.00002446779,0.0001157612,0.0002664934,0.00008134132,0.0002160351],"domain_scores_gemma":[0.9995191,0.00002804094,0.00002297999,0.0003046039,0.00005994011,0.00006537112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008705004,0.0005505559,0.01780232,0.00004274857,0.00002578046,0.00002041782,0.02850855,0.0003354816,0.008816327,0.7415951,0.02618066,0.176035],"study_design_scores_gemma":[0.0003260197,0.000365275,0.001987255,0.00002407697,0.000001582151,0.000004028152,0.0001227666,0.9559,0.003510572,0.03601162,0.001514205,0.0002326372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2630939,0.000005385329,0.7313247,0.00115463,0.0001123986,0.00007098396,5.837156e-7,0.00008216813,0.004155186],"genre_scores_gemma":[0.9105877,3.776543e-7,0.08795285,0.0006866531,0.00007314111,0.000003545775,7.106822e-7,0.000005147141,0.000689847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9555645,"threshold_uncertainty_score":0.2522842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04939046645532576,"score_gpt":0.3058586075740923,"score_spread":0.2564681411187665,"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."}}