{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003881741,0.0001452557,0.0001671046,0.0001994172,0.0002579677,0.0007904604,0.005112672,0.0000292193,0.00001891237],"category_scores_gemma":[0.0002390602,0.000123005,0.0000258661,0.001106697,0.0006065143,0.001964329,0.002512429,0.00009363716,0.0000265065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002494181,"about_ca_system_score_gemma":0.00008213288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001220881,"about_ca_topic_score_gemma":0.000002998412,"domain_scores_codex":[0.9975749,0.00008055365,0.0002227181,0.0009687125,0.0004466416,0.0007065028],"domain_scores_gemma":[0.9978689,0.0002495644,0.00004913969,0.001631361,0.00005647502,0.0001445816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001598498,0.00005541526,0.0002097966,0.000006304997,0.000001721313,0.000008117288,0.0001851394,0.00001514336,0.00001266717,0.9755455,0.0004706911,0.0234879],"study_design_scores_gemma":[0.0004464223,0.0000822728,0.0005549632,0.00002243366,0.000002757184,0.000006830758,0.00002214702,0.9057108,0.0003404034,0.08602481,0.006564492,0.0002216504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008046531,0.00002905494,0.9875485,0.0007240471,0.0006412781,0.0002307835,0.00001372151,0.00009519592,0.002670876],"genre_scores_gemma":[0.5205747,0.000002222763,0.4789763,0.0003827316,0.0000338783,0.000005537148,0.000007075313,0.000004220511,0.00001331229],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9056957,"threshold_uncertainty_score":0.9500702,"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."}}