{"id":"W4386600212","doi":"10.12688/f1000research.140344.1","title":"NCBench: providing an open, reproducible, transparent, adaptable, and continuous benchmark approach for DNA-sequencing-based variant calling","year":2023,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Standards and Technology; Universität Duisburg-Essen; Deutsche Forschungsgemeinschaft","keywords":"Benchmarking; Computer science; Open source; Workflow; Merge (version control); Open science; Data science; Precision and recall; Data mining; Machine learning; Information retrieval; Database; Software; Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.02711049,0.004301815,0.002265343,0.006759048,0.002012097,0.007401606,0.009543403,0.002665036,0.007422869],"category_scores_gemma":[0.06916872,0.001697592,0.002794639,0.005506715,0.001746955,0.004197536,0.007143638,0.004457071,0.009406371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001695272,"about_ca_system_score_gemma":0.006129249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007214653,"about_ca_topic_score_gemma":0.007708304,"domain_scores_codex":[0.9716995,0.006984679,0.003731276,0.006303582,0.009873935,0.001406965],"domain_scores_gemma":[0.9581053,0.01529248,0.002475574,0.0129082,0.008923204,0.002295262],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004168149,0.001564439,0.03416435,0.006507258,0.002658326,0.001294322,0.002092252,0.08483595,0.1056143,0.02664132,0.3630355,0.3674239],"study_design_scores_gemma":[0.001217867,0.002041191,0.01876886,0.001301072,0.000694337,0.001891344,0.0006848691,0.3434685,0.2319969,0.04426088,0.3521589,0.001515242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04828957,0.002690991,0.5759173,0.001320011,0.00206147,0.001498569,0.07145939,0.2849834,0.01177927],"genre_scores_gemma":[0.08069491,0.0009608894,0.5350266,0.001162146,0.000340077,0.002993353,0.3208548,0.0536323,0.004334926],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9904566,"threshold_uncertainty_score":0.1433757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.212241329283231,"score_gpt":0.3629359888433186,"score_spread":0.1506946595600876,"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."}}