{"id":"W4283820596","doi":"10.1109/dcc52660.2022.00017","title":"CSTs for Terabyte-Sized Data","year":2022,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Terabyte; Computer science; Scalability; Parsing; Suffix; Trie; String (physics); Phrase; Prefix; Information retrieval; Data mining; Artificial intelligence; Data structure; Database; Programming language","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":[0.001263474,0.0009648146,0.0008336267,0.003007072,0.001037391,0.002403492,0.001583164,0.001330828,0.0142722],"category_scores_gemma":[0.01870802,0.0005541494,0.001391006,0.007922674,0.0007568799,0.00455879,0.002724547,0.002435025,0.01306704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007242254,"about_ca_system_score_gemma":0.001966795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001256343,"about_ca_topic_score_gemma":0.002706887,"domain_scores_codex":[0.9983432,0.0001971886,0.0002693411,0.0004049444,0.0006706992,0.0001146078],"domain_scores_gemma":[0.9903162,0.003143725,0.0005725044,0.003848928,0.001897297,0.0002214999],"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":[0.0006640893,0.0001483882,0.003623325,0.001346381,0.0002189323,0.0008758,0.001018117,0.02429491,0.0597537,0.04373128,0.1619647,0.7023605],"study_design_scores_gemma":[0.0002047485,0.0003018364,0.003965276,0.0003557431,0.0001137933,0.002503335,0.001259393,0.3194804,0.1590428,0.1580896,0.3545143,0.000168893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03243187,0.001146543,0.8559415,0.001408702,0.0008681912,0.0004247163,0.04269841,0.05867032,0.006409824],"genre_scores_gemma":[0.07013741,0.0009393962,0.8292441,0.0004788107,0.0002521772,0.0008633836,0.08763228,0.004728196,0.005724098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0142722,"threshold_uncertainty_score":0.04774529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06483453739719433,"score_gpt":0.303747243356867,"score_spread":0.2389127059596726,"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."}}