{"id":"W4390449572","doi":"10.2139/ssrn.4679655","title":"Depth--A Novel Data Complexity Metric for Biological High-Dimensional Data","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Metric (unit); Computer science; Algorithm; Mathematics; Engineering","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","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004776595,0.0004621492,0.000603971,0.0002838426,0.0002361968,0.00013334,0.004915309,0.0006330779,0.00001624566],"category_scores_gemma":[0.001185979,0.0004036993,0.0002878454,0.0002573346,0.0001876652,0.00001549037,0.009943238,0.002512597,0.0000151067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002689032,"about_ca_system_score_gemma":0.002805087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003234222,"about_ca_topic_score_gemma":0.003054483,"domain_scores_codex":[0.9950916,0.0001489523,0.0006891228,0.001686098,0.000382179,0.002002077],"domain_scores_gemma":[0.995233,0.00008873267,0.0005509139,0.003693281,0.0002994045,0.0001346844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002037906,0.003070535,0.004569395,0.000335183,0.02087028,0.00006434841,0.00002245242,0.001339202,0.4793709,0.02310858,0.3731887,0.09202249],"study_design_scores_gemma":[0.007667793,0.004062002,0.005483794,0.0002977328,0.004018157,0.002253378,0.0003599984,0.04405097,0.04420836,0.7063995,0.1750247,0.006173589],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06516871,0.01146757,0.9173979,0.001388923,0.0005064806,0.001056535,0.00272182,0.0001831953,0.0001088813],"genre_scores_gemma":[0.8280963,0.02069595,0.04599349,0.0004028823,0.003164161,0.00006280963,0.09963666,0.0001907061,0.001757028],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8714044,"threshold_uncertainty_score":0.9998415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1417699965224893,"score_gpt":0.365884151111053,"score_spread":0.2241141545885637,"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."}}