{"id":"W2033583474","doi":"10.1364/josaa.31.001445","title":"Outlier modeling for spectral data reduction","year":2014,"lang":"en","type":"article","venue":"Journal of the Optical Society of America A","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mahalanobis distance; Outlier; Principal component analysis; Pattern recognition (psychology); Anomaly detection; Estimator; Covariance; Computer science; Artificial intelligence; Mathematics; Basis (linear algebra); Algorithm; Statistics","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":[0.0002753676,0.00008540374,0.0002875066,0.00001476568,0.00007883088,0.00001796799,0.0006172753,0.00006621239,0.0001044731],"category_scores_gemma":[0.000319841,0.00005528535,0.0004537502,0.0001910035,0.0001499247,0.0001044124,0.0001012435,0.0002558363,9.242905e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005507489,"about_ca_system_score_gemma":0.00004510795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001015183,"about_ca_topic_score_gemma":5.338332e-8,"domain_scores_codex":[0.9990779,0.000008849591,0.0003590047,0.000120171,0.0002705359,0.0001636066],"domain_scores_gemma":[0.9989904,0.0001100686,0.0003484662,0.0003639417,0.0001222359,0.00006486414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004735999,0.001051256,0.0006267244,0.0004282861,0.002426398,4.732073e-7,0.001253419,0.01990821,0.8729659,0.0005964598,0.07919621,0.02107308],"study_design_scores_gemma":[0.001380509,0.0002720639,0.00004687989,0.00009073047,0.001536783,0.000091272,0.004831901,0.763115,0.2130328,0.004418661,0.01089087,0.0002925771],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3520365,0.0006321479,0.629375,0.01183488,0.0003380822,0.00009223738,0.0000291583,0.00002392809,0.005638063],"genre_scores_gemma":[0.8862131,0.0001120343,0.112463,0.000154674,0.0006886071,6.336206e-7,0.000002668366,0.00001271777,0.0003525871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7432068,"threshold_uncertainty_score":0.2254471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03868015907259537,"score_gpt":0.3066531486263578,"score_spread":0.2679729895537625,"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."}}