{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002118559,0.001858273,0.0009661217,0.002281778,0.0005113271,0.001736067,0.002749352,0.0009243459,0.01234449],"category_scores_gemma":[0.004959395,0.0008885509,0.00228933,0.001140227,0.0007679716,0.002722062,0.00213718,0.001622192,0.008607515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007511785,"about_ca_system_score_gemma":0.002001672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001584542,"about_ca_topic_score_gemma":0.002244003,"domain_scores_codex":[0.9984409,0.0002994673,0.00012665,0.0005079803,0.0005312326,0.00009375923],"domain_scores_gemma":[0.9978585,0.001411555,0.0001377432,0.0002537799,0.0002803946,0.00005809464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004898984,0.0004115136,0.00386592,0.002548329,0.0002950258,0.000785556,0.0007415773,0.01370923,0.08659604,0.01593209,0.04390229,0.8307226],"study_design_scores_gemma":[0.0002018158,0.0003841415,0.004828051,0.000421975,0.0002478653,0.001297066,0.0002391788,0.4633847,0.299208,0.06208891,0.1675175,0.0001808861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005329921,0.0001711147,0.9148913,0.0001697451,0.00004166338,0.0002261688,0.002279482,0.07524672,0.001643952],"genre_scores_gemma":[0.03346621,0.0003574714,0.9491629,0.0003393769,0.0000497593,0.0005630926,0.008894397,0.003456578,0.003710152],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01234449,"threshold_uncertainty_score":0.04129642,"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."}}