{"id":"W3212315066","doi":"10.21105/joss.03756","title":"A flexible search system for high-accuracy identification of biological entities and molecules","year":2021,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; University Health Network; Mount Sinai Hospital; University of Toronto","funders":"National Institutes of Health","keywords":"Identification (biology); Computer science; Computational biology; Biology; Ecology","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":[],"consensus_categories":[],"category_scores_codex":[0.001355895,0.00008197317,0.0001977703,0.00003982595,0.0001196157,0.0001018152,0.0005384877,0.00009118468,0.00001033106],"category_scores_gemma":[0.001055487,0.00005160937,0.00007226494,0.00008217178,0.0002299522,0.0000109779,0.0004440625,0.00009704909,0.000001518981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001172122,"about_ca_system_score_gemma":0.0001868636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000169278,"about_ca_topic_score_gemma":0.000002464571,"domain_scores_codex":[0.9988759,0.0001485259,0.0004668022,0.0000974447,0.0002460571,0.0001652609],"domain_scores_gemma":[0.9986409,0.0001583879,0.0002652255,0.0002218459,0.0006307754,0.00008289349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008261012,0.0001489415,0.002340109,0.0007275431,0.0003147429,0.00000558608,0.00108827,0.000182255,0.9502008,0.0003119439,0.002656277,0.04119745],"study_design_scores_gemma":[0.0009310142,0.0006273943,0.003440342,0.0001134146,0.00005013679,0.0001618428,0.006696278,0.00008246311,0.9811506,0.0003364891,0.006296006,0.0001139846],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8909444,0.001787397,0.1064938,0.0003349687,0.00009710126,0.0002448482,0.00005476948,0.000003465892,0.00003931104],"genre_scores_gemma":[0.9932455,0.001122835,0.004774787,0.0000567453,0.000116298,0.000004920674,0.00004063787,0.000009736276,0.0006284718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1023012,"threshold_uncertainty_score":0.2104569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04142067478494253,"score_gpt":0.3269574112621697,"score_spread":0.2855367364772271,"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."}}