{"id":"W7081577906","doi":"10.5281/zenodo.17109725","title":"tbrowne5/Better-data-for-better-predictions-data-curation-improves-deep-learning-for-sgRNA-Cas9-prediction: v1.0.0","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Deep learning; Identification (biology); Data collection; Raw data","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":[],"consensus_categories":[],"category_scores_codex":[0.003495736,0.0039445,0.001571966,0.002708239,0.0009259193,0.002535538,0.004090763,0.003016793,0.1159791],"category_scores_gemma":[0.0104384,0.00173334,0.001897938,0.001685106,0.0009408447,0.003198548,0.005048881,0.003625132,0.1592412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001350277,"about_ca_system_score_gemma":0.002069628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006786074,"about_ca_topic_score_gemma":0.01028215,"domain_scores_codex":[0.9973609,0.0003337051,0.0001724939,0.000939279,0.0009395281,0.0002541451],"domain_scores_gemma":[0.9964897,0.0009316377,0.0001676507,0.001507866,0.0005736026,0.0003295399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003122976,0.00009216854,0.0009063335,0.0007406659,0.0001614957,0.0001005208,0.00006318306,0.003145121,0.006711612,0.003563883,0.9210915,0.06311131],"study_design_scores_gemma":[0.0006772491,0.0001492535,0.001954048,0.0003184876,0.0001207841,0.0003225828,0.0000570362,0.07985312,0.07339582,0.02830296,0.8145741,0.0002745967],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"dataset","genre_scores_codex":[0.003400834,0.001081013,0.1243722,0.001599234,0.0009248754,0.0002454543,0.2062688,0.648007,0.01410061],"genre_scores_gemma":[0.02350765,0.0009199445,0.188541,0.002292345,0.0002356965,0.0008222637,0.5829148,0.1706037,0.03016268],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.1159791,"threshold_uncertainty_score":0.3879889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04029719315923255,"score_gpt":0.2510219536944264,"score_spread":0.2107247605351938,"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."}}