{"id":"W3129502039","doi":"10.1002/cjs.11765","title":"PCA Rerandomization","year":2023,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mahalanobis distance; Covariate; Principal component analysis; Curse of dimensionality; Computer science; Linear subspace; Pattern recognition (psychology); Simplicity; Data mining; Artificial intelligence; Mathematics; Algorithm; Statistics; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001122771,0.0002163598,0.0006485269,0.0003753532,0.00009643943,0.0001452407,0.0003731502,0.0002327437,0.000451267],"category_scores_gemma":[0.01885112,0.0001994853,0.000102609,0.0001337272,0.0001267197,0.00002786334,0.00004865172,0.000850039,0.00002867189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002145107,"about_ca_system_score_gemma":0.002892148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001729962,"about_ca_topic_score_gemma":0.008617833,"domain_scores_codex":[0.9980265,0.0002128606,0.0009669523,0.0001659175,0.0003073229,0.000320377],"domain_scores_gemma":[0.9947838,0.00251999,0.0008161325,0.0002772704,0.000919888,0.0006829376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003841036,0.00001531795,0.0004743488,0.0005358253,0.000184587,0.0009344925,0.0006871453,0.000261149,0.000004228331,0.6915089,0.2880666,0.017289],"study_design_scores_gemma":[0.000509857,0.00006943235,0.0008595167,0.0004597183,0.0001862811,0.00003728671,0.00005838277,0.001718011,0.00001130275,0.9931968,0.002680724,0.0002126372],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007534801,0.0001203842,0.9921119,0.0003541271,0.002853507,0.0001793512,0.002624463,0.00001505472,0.000987733],"genre_scores_gemma":[0.01528939,0.0001298683,0.9829325,0.0001009032,0.0005236672,0.000005327313,0.00004543007,0.00007598197,0.0008969115],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3016879,"threshold_uncertainty_score":0.9894135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1926287538999322,"score_gpt":0.3641936247520571,"score_spread":0.1715648708521249,"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."}}