{"id":"W2092500953","doi":"10.1007/s00454-009-9236-5","title":"VC Dimensions of Principal Component Analysis","year":2009,"lang":"en","type":"article","venue":"Discrete & Computational Geometry","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Combinatorics; Principal component analysis; Affine transformation; Upper and lower bounds; Dimension (graph theory); Eigenvalues and eigenvectors; Subspace topology; Simple (philosophy); VC dimension; Covariance; Discrete mathematics; Covariance matrix; Constant (computer programming); Sign (mathematics); Spectrum (functional analysis); Pure mathematics; Statistics; Mathematical analysis","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":[0.00006528457,0.000132951,0.0002612593,0.0004681771,0.00004619502,0.00001657805,0.0001264454,0.00004812397,0.00003903602],"category_scores_gemma":[0.00001091156,0.0001167109,0.000171504,0.0009391584,0.00003504421,0.00006017301,0.00002839364,0.000101831,0.000009207468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000264015,"about_ca_system_score_gemma":0.000009972267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009568117,"about_ca_topic_score_gemma":0.000001131519,"domain_scores_codex":[0.9991179,0.00001874486,0.0002737135,0.0001532128,0.000276642,0.000159787],"domain_scores_gemma":[0.9995205,0.00007713476,0.00005363428,0.0001900046,0.00009419772,0.00006450294],"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":[0.000006513827,0.00003684009,0.001673424,0.000004837626,0.0003017581,0.000005739605,0.00005746063,0.9903407,0.002200318,0.003069952,0.0004462172,0.001856215],"study_design_scores_gemma":[0.0001816026,0.000060817,0.2688366,0.00002884602,0.0002101161,0.000005013012,0.0000232016,0.7194721,0.003912572,0.006431605,0.0005975654,0.0002400118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7992861,0.0002571601,0.1980083,0.00005950679,0.00006893541,0.00008279006,0.00002637684,0.0003338005,0.001877041],"genre_scores_gemma":[0.9844631,0.00001478233,0.01525454,0.00007541721,0.00002989317,0.000001695964,0.0001339688,0.00001029719,0.00001630062],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2708686,"threshold_uncertainty_score":0.4759331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01145252916720602,"score_gpt":0.2531162487751962,"score_spread":0.2416637196079902,"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."}}