{"id":"W2029626238","doi":"10.1016/s0304-3975(02)00738-7","title":"Mining for empty spaces in large data sets","year":2003,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Focus (optics); Scalability; Computer science; Bounded function; Set (abstract data type); Data structure; Space (punctuation); Mathematics; Algorithm; Data mining; Theoretical computer science","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":[0.006506301,0.001149357,0.003415719,0.00488097,0.003412351,0.00568433,0.004965462,0.002621135,0.001616876],"category_scores_gemma":[0.04030149,0.00128249,0.002661444,0.006059836,0.003227538,0.0153707,0.00702293,0.00334277,0.0009011814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006817351,"about_ca_system_score_gemma":0.002360576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000900753,"about_ca_topic_score_gemma":0.001679232,"domain_scores_codex":[0.9925169,0.001584354,0.00135216,0.0013924,0.002452747,0.0007014796],"domain_scores_gemma":[0.9621026,0.02213097,0.003417826,0.006626619,0.00413691,0.00158513],"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":[0.003223091,0.001266101,0.1411399,0.002539841,0.0008908205,0.002945548,0.005341267,0.07077123,0.01561081,0.08401102,0.02110474,0.6511556],"study_design_scores_gemma":[0.0001032338,0.0005293912,0.00745227,0.0005014345,0.0003785929,0.002950978,0.004339639,0.6203331,0.02666717,0.3211696,0.01543765,0.0001370015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3091795,0.003121985,0.6784425,0.002035119,0.0002415051,0.0002079507,0.002926063,0.002578018,0.00126751],"genre_scores_gemma":[0.5851716,0.000814801,0.4023047,0.0002762075,0.0002606403,0.0002082585,0.008263156,0.0004293523,0.002271354],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006506301,"threshold_uncertainty_score":0.03440899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03465404803737175,"score_gpt":0.3047576255395932,"score_spread":0.2701035775022215,"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."}}