{"id":"W4389156510","doi":"10.48550/arxiv.2311.16375","title":"Testing for a difference in means of a single feature after clustering","year":2023,"lang":"en","type":"preprint","venue":"PubMed","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Cluster analysis; Type I and type II errors; Feature (linguistics); Hierarchical clustering; Computer science; Data mining; Statistical hypothesis testing; Word error rate; Pattern recognition (psychology); Algorithm; Type (biology); Artificial intelligence; Mathematics; Statistics","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":[0.0001760503,0.0001880296,0.0002551322,0.00007049453,0.00001584919,0.00002535371,0.0002203436,0.0003487789,4.100151e-7],"category_scores_gemma":[0.0003007378,0.0001895773,0.0001244277,0.00007458794,0.00003792492,0.000001022048,0.0002725279,0.0001742322,1.988259e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002608483,"about_ca_system_score_gemma":0.0000382354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007923413,"about_ca_topic_score_gemma":0.0008273386,"domain_scores_codex":[0.9989222,0.0000261125,0.0002326846,0.0004209361,0.0000836002,0.000314514],"domain_scores_gemma":[0.9994437,0.00003900293,0.0001044837,0.0002884408,0.00007375553,0.00005061479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001052688,0.000403341,0.1287442,0.002808854,0.0002031519,0.00001746823,0.0004656372,0.002560706,0.7426851,0.000003918298,0.0002849681,0.1207699],"study_design_scores_gemma":[0.001485367,0.000195345,0.9110516,0.0004573209,0.0000872227,0.000005187118,0.00004835202,0.002166299,0.08214436,0.0006101216,0.0009867832,0.0007619985],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904957,0.0004536114,0.006879688,0.0001304762,0.0005769624,0.001082923,0.0001581434,0.00002512138,0.0001973439],"genre_scores_gemma":[0.9940339,0.00001651163,0.002570642,0.0000546314,0.0002180063,0.002285464,0.0001127813,0.0000454994,0.0006625719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7823074,"threshold_uncertainty_score":0.7730738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05768386874744054,"score_gpt":0.2372256609971068,"score_spread":0.1795417922496663,"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."}}