{"id":"W2111044311","doi":"10.1093/bioinformatics/bts593","title":"SCALCE: boosting sequence compression algorithms using locally consistent encoding","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":158,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; ExxonMobil Research and Engineering Company","keywords":"Boosting (machine learning); Encoding (memory); Computer science; Algorithm; Sequence (biology); Data compression; Compression (physics); Artificial intelligence","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":[0.0005529899,0.0002186725,0.0002246641,0.0001147398,0.0004313738,0.000280014,0.0007810478,0.0001030753,0.00001268978],"category_scores_gemma":[0.000075468,0.0001778625,0.00007204158,0.0003075712,0.00007516307,0.002973367,0.0009538991,0.0001980353,0.00008781949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001091662,"about_ca_system_score_gemma":0.00009455502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002590806,"about_ca_topic_score_gemma":2.361942e-7,"domain_scores_codex":[0.9980853,0.00004511655,0.0005603871,0.0001774751,0.0005204983,0.0006112811],"domain_scores_gemma":[0.9985444,0.0001187491,0.0002989297,0.0006333629,0.0001148338,0.0002897028],"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":[0.00001795611,0.0005325272,0.007545118,0.000794589,0.0001114274,0.00005260268,0.01289847,0.005487966,0.03012035,0.03243376,0.006466916,0.9035383],"study_design_scores_gemma":[0.0002320954,0.00002646766,0.0004018914,0.0002699235,0.000009116056,0.0001415485,0.0001763543,0.991502,0.002525733,0.00008464232,0.004350548,0.0002796676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006716708,0.000303426,0.9895922,0.00004388452,0.000981133,0.0001849794,0.00001369808,0.0002255267,0.001938446],"genre_scores_gemma":[0.1924294,0.00002801652,0.8069463,0.0003533696,0.0001826346,0.000003968202,0.00001668309,0.00001079889,0.00002877481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9860141,"threshold_uncertainty_score":0.7253024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08296651646590367,"score_gpt":0.3066863161757942,"score_spread":0.2237197997098906,"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."}}