{"id":"W2015530630","doi":"10.1186/s13059-014-0462-7","title":"Toward better benchmarking: challenge-based methods assessment in cancer genomics","year":2014,"lang":"en","type":"article","venue":"Genome biology","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada; Government of Ontario; Canadian Institutes of Health Research; Genome Canada; National Cancer Institute; National Institutes of Health; Ontario Institute for Cancer Research; Movember Foundation","keywords":"Benchmarking; Genomics; Data science; Biology; Human genetics; Crowd sourcing; Genome Biology; Computational biology; Computer science; Genome; Genetics; Business; Gene","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":[0.0005662952,0.0002243684,0.0002937148,0.0001024034,0.000050174,0.00001867027,0.0002958418,0.0002916264,0.0001024096],"category_scores_gemma":[0.00005204843,0.0002258028,0.0001024468,0.00008171181,0.00009944308,0.000001652544,0.0001771109,0.0001719087,0.000007428016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001299962,"about_ca_system_score_gemma":0.0002624634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001637586,"about_ca_topic_score_gemma":0.0002928797,"domain_scores_codex":[0.9983984,0.0002179907,0.0003183306,0.0005697659,0.00004940124,0.0004460757],"domain_scores_gemma":[0.9992254,0.00007671759,0.0001160796,0.0004243969,0.00005663846,0.0001008161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001079646,0.0002014488,0.04228446,0.00005557279,0.0001084792,0.000004313681,0.0001223427,0.002233769,0.8410284,0.002546233,0.000348818,0.1109582],"study_design_scores_gemma":[0.002077476,0.001354732,0.05928247,0.00001371863,0.00004176992,0.000004851254,0.00003502879,0.00298587,0.02455255,0.002267062,0.9065769,0.0008076298],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8614959,0.003241406,0.1276979,0.002868244,0.001201423,0.0004068175,0.0001120586,0.00002002431,0.002956346],"genre_scores_gemma":[0.9543786,0.001345915,0.03991115,0.002719678,0.001097549,0.0001401519,0.0003390312,0.00003679623,0.00003112579],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.906228,"threshold_uncertainty_score":0.9207969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03123681804151992,"score_gpt":0.346673427813033,"score_spread":0.3154366097715131,"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."}}