{"id":"W1798235558","doi":"","title":"Evidence combination in hidden markov models for gene prediction","year":2006,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Genome; Hidden Markov model; Gene prediction; Probabilistic logic; Annotation; Computational biology; Computer science; Genome project; Sequence (biology); Gene; Markov chain; Gene Annotation; Identification (biology); Genetics; Biology; Artificial intelligence; Machine learning","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":[0.0001126355,0.0001482844,0.0002011255,0.0001079233,0.00007982729,0.000007042479,0.0001761466,0.0002602797,0.000003697678],"category_scores_gemma":[0.00001068773,0.0001882961,0.0001097215,0.00005740895,0.00003276474,0.000003671298,0.00004292204,0.00005770109,9.014558e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003376933,"about_ca_system_score_gemma":0.0000590673,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006325833,"about_ca_topic_score_gemma":0.02681143,"domain_scores_codex":[0.9992798,0.00002693391,0.0001169483,0.000320277,0.0001010883,0.0001549642],"domain_scores_gemma":[0.9994583,0.00001228104,0.0001505531,0.0001828567,0.0001705755,0.00002543002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001144322,0.0001989977,0.005071286,0.0005419656,0.0002206103,0.000004638166,0.01206234,0.001500096,0.9659761,0.0001086146,0.004501404,0.008669593],"study_design_scores_gemma":[0.01049438,0.003960895,0.4659638,0.001592044,0.001152796,0.000009144811,0.08433935,0.01567706,0.4035314,0.007547806,0.002979669,0.002751626],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973539,0.001452346,0.0001508249,0.0001021518,0.0001963222,0.000409678,0.0001259279,0.000003388826,0.0002054661],"genre_scores_gemma":[0.8850127,0.001688725,0.003308969,0.000007072716,0.00006840863,0.00000466971,0.00210201,0.00002324815,0.1077842],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5624447,"threshold_uncertainty_score":0.9909467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01420226556176271,"score_gpt":0.2062370289198014,"score_spread":0.1920347633580387,"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."}}