{"id":"W4385520436","doi":"10.1093/bioadv/vbad097","title":"Toward computing attributions for dimensionality reduction techniques","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; 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; Python (programming language); Computer science; Artificial intelligence; Curse of dimensionality; Benchmark (surveying); Computation; Machine learning; Context (archaeology); Data mining; Reduction (mathematics); Pattern recognition (psychology); Deep learning; Algorithm; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002061809,0.0001006568,0.0001026866,0.00004376856,0.0001913935,0.00002316695,0.0001010006,0.00007986416,0.000001629161],"category_scores_gemma":[0.00006550628,0.00009331399,0.00008178645,0.0001323453,0.00005830791,0.00001382632,0.00004336151,0.00004200215,0.000008651689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001250281,"about_ca_system_score_gemma":0.00003294358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002807843,"about_ca_topic_score_gemma":0.000002239465,"domain_scores_codex":[0.9993312,0.00000969488,0.0002479038,0.0001247609,0.00009075015,0.0001956397],"domain_scores_gemma":[0.9996085,0.00001763152,0.00008419302,0.0001416628,0.0001063648,0.00004168758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002097688,0.0001590033,0.001111676,0.0007191329,0.0001126,9.946591e-7,0.0006333692,0.001607076,0.7668,0.004932312,0.01801219,0.2057019],"study_design_scores_gemma":[0.0005313532,0.0003698005,0.0005337714,0.00005878931,0.00002539776,0.00001928266,0.0007081786,0.01419055,0.6296598,0.001627887,0.3518685,0.0004067456],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5439645,0.0008676226,0.4492766,0.0007873095,0.001508669,0.00106673,0.0003451341,0.0004511584,0.001732215],"genre_scores_gemma":[0.9220359,0.0006309971,0.0752738,0.0001245357,0.0004053511,0.00004127203,0.001249952,0.0000186313,0.0002195759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3780714,"threshold_uncertainty_score":0.3805234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03755720374093063,"score_gpt":0.2994449990200561,"score_spread":0.2618877952791255,"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."}}