{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001136066,0.0007434042,0.0007818696,0.001143777,0.0005325642,0.0008230582,0.00171114,0.0009251098,0.002977152],"category_scores_gemma":[0.003878002,0.0002731679,0.0005396414,0.001373934,0.0008825218,0.001326089,0.001243823,0.001645308,0.001835579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007019218,"about_ca_system_score_gemma":0.00100774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00252289,"about_ca_topic_score_gemma":0.002297467,"domain_scores_codex":[0.9993893,0.0001059662,0.00003702645,0.00009191695,0.0003089935,0.00006666286],"domain_scores_gemma":[0.9986547,0.0005528362,0.000110542,0.0002921071,0.0003269042,0.00006275735],"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":[0.0008025577,0.000223342,0.002414393,0.0002858059,0.00007268279,0.0003328726,0.0003101166,0.1743041,0.05288671,0.02911741,0.01880398,0.7204459],"study_design_scores_gemma":[0.00007370277,0.0002316163,0.0005238502,0.0000343046,0.00002061756,0.0002121663,0.00005285556,0.9380634,0.03338635,0.01794322,0.009420172,0.00003774903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02815193,0.0007519269,0.9618449,0.000253575,0.0001531205,0.0001501579,0.0002382333,0.006206397,0.002249726],"genre_scores_gemma":[0.2109031,0.0005344778,0.7799087,0.0006136544,0.0001737837,0.0003101907,0.001616393,0.0007584445,0.005181306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002977152,"threshold_uncertainty_score":0.009959579,"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."}}