{"id":"W4382052297","doi":"10.4050/f-0079-2023-18094","title":"Towards an Evaluation Process for Regime Recognition Approaches: Addressing Variability in Labeling Training Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Target Tracking and Data Fusion in Sensor Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; USable; Process (computing); Task (project management); Test data; Machine learning; Training set; Artificial intelligence; Flight test; Flight training; Flight simulator; Path (computing); Test (biology); Data mining; Simulation; Engineering","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":[0.01067157,0.0001258805,0.0001666119,0.0001577634,0.0001799323,0.0002517965,0.001074754,0.0001102455,0.00001944289],"category_scores_gemma":[0.001369707,0.0001195448,0.00002187591,0.0009410643,0.00002478689,0.001824291,0.0002471762,0.0001608264,0.000009846025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004078999,"about_ca_system_score_gemma":0.0002067073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003064179,"about_ca_topic_score_gemma":0.00004491002,"domain_scores_codex":[0.9976172,0.000353054,0.000360957,0.0009003744,0.0004192117,0.0003492192],"domain_scores_gemma":[0.9981568,0.0004075989,0.0001010792,0.00108763,0.0001738623,0.0000729766],"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":[0.00001311399,0.00006278417,0.0001059701,0.0000554404,0.000005100597,0.000001160252,0.003049839,0.007871539,0.00005751155,0.0009123866,0.0003189146,0.9875463],"study_design_scores_gemma":[0.0004284093,0.00002558816,0.0003978917,0.00008753352,0.000009861038,0.000002924922,0.000813265,0.9663892,0.0001720121,0.03137891,0.0001226733,0.0001717612],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05124245,0.00002097301,0.9441937,0.000553634,0.0004782618,0.0007429052,0.00007309732,0.0007082743,0.001986706],"genre_scores_gemma":[0.8089365,0.000005776019,0.1883473,0.00009494735,0.0001933193,0.000123505,0.002269798,0.00001524461,0.00001362584],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9873745,"threshold_uncertainty_score":0.4874895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5960908505467749,"score_gpt":0.4150876066118485,"score_spread":0.1810032439349264,"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."}}