{"id":"W2101436724","doi":"10.20381/ruor-4947","title":"ModuleInducer: Automating the Extraction of Knowledge from Biological Sequences","year":2011,"lang":"en","type":"dissertation","venue":"Library and Archives Canada (Government of Canada)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Bottleneck; Data mining; Knowledge extraction; Set (abstract data type); Biological data; Java; Information retrieval; Artificial intelligence; Machine learning; Bioinformatics; Biology; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00001512735,0.0001788268,0.0002493579,0.00001854496,0.0001777036,0.0000277978,0.0007467989,0.00005872005,0.00002380987],"category_scores_gemma":[0.00000416127,0.0001205369,0.00003263255,0.00007295034,0.00004622062,0.0004621879,0.0001898106,0.0001886703,3.202952e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003704015,"about_ca_system_score_gemma":0.001189957,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01179156,"about_ca_topic_score_gemma":0.02057441,"domain_scores_codex":[0.9983367,0.00009081695,0.0003229234,0.0002948071,0.0007905518,0.0001641526],"domain_scores_gemma":[0.9988412,0.0003415153,0.0004075847,0.0003166895,0.00000123894,0.0000917942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003498544,0.0001524425,0.005127408,0.0004317955,0.0002847025,0.00007745423,0.002434328,0.00004794462,0.1249165,0.2981844,0.001764404,0.5662287],"study_design_scores_gemma":[0.0004418051,0.0002403831,0.3247868,0.001226304,0.00006172789,0.00001105361,0.006857317,0.08423357,0.5389766,0.02654391,0.01568635,0.0009342165],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6062579,0.004570665,0.006019189,0.0007722786,0.002989377,0.0005320185,0.0007963147,0.00006574225,0.3779965],"genre_scores_gemma":[0.9884121,0.0002762237,0.008465641,0.00008593396,0.0000828856,0.000009518859,0.0000826292,0.00001022904,0.002574797],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5652945,"threshold_uncertainty_score":0.9972975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0104115523803571,"score_gpt":0.1843919104333832,"score_spread":0.1739803580530261,"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."}}