{"id":"W4376618193","doi":"10.1101/2023.05.12.540592","title":"Towards Computing Attributions for Dimensionality Reduction Techniques","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université de Montréal; Montreal Heart Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données","keywords":"Dimensionality reduction; MNIST database; Computer science; Benchmark (surveying); Curse of dimensionality; Artificial intelligence; Context (archaeology); Reduction (mathematics); Computation; Machine learning; Pattern recognition (psychology); Data mining; Algorithm; Deep learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009785839,0.001317987,0.001439362,0.004094382,0.001118391,0.004173568,0.002352202,0.001931469,0.002964404],"category_scores_gemma":[0.05613208,0.0007822459,0.002065772,0.003830747,0.00384106,0.005480319,0.005235101,0.004967866,0.001138274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001840818,"about_ca_system_score_gemma":0.002042639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001306341,"about_ca_topic_score_gemma":0.001159966,"domain_scores_codex":[0.9908469,0.003985784,0.0006778393,0.001701676,0.002459401,0.0003283032],"domain_scores_gemma":[0.9753103,0.01265132,0.002265612,0.006029687,0.003310739,0.0004323008],"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":[0.0002160307,0.0001637161,0.007696209,0.000408089,0.0002381163,0.0002229197,0.0007223189,0.1489618,0.005478628,0.393476,0.01030248,0.4321137],"study_design_scores_gemma":[0.00002279041,0.0000434127,0.0008392793,0.00006757215,0.0000222618,0.00006026228,0.0001327832,0.5083565,0.003005462,0.4834759,0.003942483,0.0000313065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006182459,0.000196162,0.9917448,0.0004346235,0.00003491559,0.00004495872,0.0001511069,0.0006674667,0.0005435388],"genre_scores_gemma":[0.1770301,0.0003274369,0.8198105,0.000221376,0.0001441148,0.0002596383,0.0008029151,0.0003913928,0.001012576],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009785839,"threshold_uncertainty_score":0.0517531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02197204608997497,"score_gpt":0.2802587829986533,"score_spread":0.2582867369086783,"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."}}