{"id":"W1981890639","doi":"10.1186/1471-2105-10-206","title":"Representative transcript sets for evaluating a translational initiation sites predictor","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Calgary Laboratory Services","keywords":"Benchmark (surveying); Set (abstract data type); Population; Computer science; Data mining; Data set; Expression (computer science); Sequence (biology); Test set; Computational biology; Algorithm; Biology; Machine learning; Artificial intelligence; Genetics","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":[0.0005180321,0.0002081573,0.0001731993,0.00008321861,0.0001692279,0.00006736937,0.0001975981,0.0001756087,0.00002749576],"category_scores_gemma":[0.0005636493,0.0001984985,0.0001549994,0.0001196978,0.00004966557,0.00004229015,0.00001824767,0.0001178754,0.00001338999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001548398,"about_ca_system_score_gemma":0.0001419357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.316523e-7,"about_ca_topic_score_gemma":0.000006813334,"domain_scores_codex":[0.9985537,0.00005245131,0.0006305254,0.0001657506,0.0003115002,0.0002860789],"domain_scores_gemma":[0.9990659,0.00008340037,0.0002701193,0.000284766,0.0002102006,0.00008565836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006745152,0.001641948,0.06665986,0.005531774,0.001230439,0.000003457244,0.08106658,0.2104223,0.2643605,0.02363402,0.1293184,0.2093856],"study_design_scores_gemma":[0.002289385,0.001187974,0.009681324,0.00003656966,0.00007765533,0.00001866613,0.0005656611,0.9707927,0.008292267,0.001318535,0.005349742,0.0003895675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1621888,0.0001414248,0.8303544,0.0003359622,0.0001519995,0.001164082,0.0002518817,0.00008173009,0.005329744],"genre_scores_gemma":[0.3300297,0.00002306734,0.6654412,0.0009961196,0.000200757,0.00006008687,0.00298486,0.00002312421,0.0002410954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7603704,"threshold_uncertainty_score":0.8094534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04719615713034547,"score_gpt":0.3568267596750517,"score_spread":0.3096306025447063,"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."}}