{"id":"W7116834253","doi":"10.1214/25-aos2558","title":"Optimal sequencing depth for single-cell RNA-sequencing in Wasserstein space","year":2025,"lang":"","type":"article","venue":"The Annals of Statistics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nonparametric statistics; Context (archaeology); Empirical distribution function; Upper and lower bounds; Probability distribution; Distribution (mathematics); Space (punctuation)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009002257,0.0004437798,0.0005894495,0.0001599712,0.0002076046,0.00008632493,0.0006351492,0.0003553133,0.00001018384],"category_scores_gemma":[0.0005678147,0.0004139727,0.0002315321,0.0003439421,0.0003825154,0.00001250926,0.000150405,0.0003236572,0.000002324779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000163324,"about_ca_system_score_gemma":0.001215893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004004258,"about_ca_topic_score_gemma":0.0004899876,"domain_scores_codex":[0.9972448,0.0001910959,0.0009655627,0.0005821253,0.0002404208,0.0007759477],"domain_scores_gemma":[0.9978721,0.0004209411,0.000412205,0.0006552065,0.0005300981,0.0001094992],"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":[0.0008189463,0.0002172743,0.0003052443,0.0008760887,0.0001965705,0.00001543485,0.0009352351,0.01599479,0.9673089,0.004065881,0.002385746,0.006879816],"study_design_scores_gemma":[0.001536189,0.0009723846,0.00005650067,0.0003834505,0.0001765752,0.000004821516,0.002138028,0.01841513,0.9698164,0.001967721,0.004056917,0.0004758903],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.598556,0.006197954,0.3842644,0.001097254,0.0007508147,0.001047585,0.001047656,0.00001343904,0.007024907],"genre_scores_gemma":[0.9659973,0.002355903,0.02926614,0.00066327,0.0001564571,0.00002440334,0.0001458141,0.00005639565,0.001334266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3674414,"threshold_uncertainty_score":0.9998312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07784741182568422,"score_gpt":0.3091679179887126,"score_spread":0.2313205061630284,"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."}}