{"id":"W1828854590","doi":"10.48550/arxiv.1306.3476","title":"Hyperparameter Optimization and Boosting for Classifying Facial Expressions: How good can a \"Null\" Model be?","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Rowland Institute at Harvard; National Science Foundation","keywords":"Hyperparameter; Hyperparameter optimization; Computer science; Artificial intelligence; Machine learning; Normalization (sociology); Benchmark (surveying); Data set; Boosting (machine learning); Set (abstract data type); Test set; Pattern recognition (psychology); Support vector machine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001352107,0.0003050193,0.0002970761,0.0002318968,0.0003605639,0.0003957867,0.000664424,0.0003739292,0.000009307575],"category_scores_gemma":[0.00008850815,0.0003212773,0.0001385239,0.0001727547,0.00006470664,0.0007598621,0.001234958,0.0003580054,0.000003860139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000867561,"about_ca_system_score_gemma":0.0001304152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004961291,"about_ca_topic_score_gemma":0.000009721515,"domain_scores_codex":[0.9982803,0.00008115377,0.0001682029,0.001018279,0.00009681713,0.000355221],"domain_scores_gemma":[0.9986456,0.0001562597,0.0002634418,0.0005483031,0.000201972,0.0001844069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000177744,0.00004507248,0.0001914886,0.0001090209,0.00003611321,0.00001000971,0.0004755517,0.9916095,0.0007642881,0.00380982,0.0008202976,0.002111044],"study_design_scores_gemma":[0.0005335389,0.00003133611,0.00001786962,0.0002284146,0.00004673314,0.000002265149,0.0001477938,0.9876295,0.0004649857,0.01034598,0.0001614141,0.0003901409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.14534,0.0000312322,0.8527942,0.0005169724,0.0002406449,0.0005656524,0.00005176355,0.0001712914,0.000288288],"genre_scores_gemma":[0.8883297,0.0001436857,0.1100238,0.0002392989,0.00005336805,0.00001836065,0.00006052634,0.00002227239,0.001108981],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7429897,"threshold_uncertainty_score":0.9999239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1419964238419821,"score_gpt":0.2019629073046231,"score_spread":0.059966483462641,"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."}}