{"id":"W4412368849","doi":"10.1101/2025.07.04.663250","title":"GAME: Genomic API for Model Evaluation","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Benchmarking; Computer science; Task (project management); Resource (disambiguation); Data science; Set (abstract data type); Machine learning; Artificial intelligence; Systems engineering; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005661527,0.004323824,0.00155494,0.002565508,0.00089041,0.003720756,0.005981583,0.001996313,0.05451871],"category_scores_gemma":[0.01653108,0.001692874,0.002582728,0.001753921,0.0008162725,0.004739328,0.00503426,0.004061638,0.03067257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00210076,"about_ca_system_score_gemma":0.002254606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00582458,"about_ca_topic_score_gemma":0.005407267,"domain_scores_codex":[0.9968274,0.0008910462,0.0003742127,0.0006666611,0.0009892854,0.0002513881],"domain_scores_gemma":[0.9950488,0.0022029,0.0002787315,0.001304575,0.0008616501,0.0003032674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001528732,0.000429282,0.00478042,0.001361148,0.0004077953,0.0005809587,0.0004456526,0.02645462,0.009019948,0.03495551,0.8043703,0.1156656],"study_design_scores_gemma":[0.0007952105,0.0002715145,0.003932558,0.0003086676,0.0001042729,0.0004235833,0.0001576638,0.5685564,0.02490653,0.0852141,0.3150013,0.0003281484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.002516654,0.0002075545,0.3234629,0.0004151398,0.0002237545,0.0003004355,0.02317071,0.643122,0.006580906],"genre_scores_gemma":[0.1067802,0.0006682293,0.3967315,0.002151735,0.0001802211,0.003941113,0.1980085,0.2763022,0.01523635],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.05451871,"threshold_uncertainty_score":0.1823833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02211133833213413,"score_gpt":0.2548328917142186,"score_spread":0.2327215533820844,"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."}}