{"id":"W2147440220","doi":"10.1007/s007780000029","title":"One-dimensional and multi-dimensional substring selectivity estimation","year":2000,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Substring; Computer science; String (physics); Context (archaeology); Matching (statistics); String searching algorithm; Constraint (computer-aided design); Theoretical computer science; Algorithm; Data structure; Mathematics; Pattern matching; Artificial intelligence; Statistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001139288,0.0003868374,0.0008862528,0.001482466,0.0003773544,0.0008367156,0.0008822953,0.0008137988,0.001846734],"category_scores_gemma":[0.005531182,0.0002651454,0.0004396738,0.001854872,0.0003719233,0.001523749,0.001204274,0.000601887,0.001119705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000323575,"about_ca_system_score_gemma":0.0006268462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001488841,"about_ca_topic_score_gemma":0.002593106,"domain_scores_codex":[0.9992087,0.000133289,0.00005980219,0.0001393687,0.0003417246,0.0001170997],"domain_scores_gemma":[0.996612,0.001816886,0.0002627646,0.0007149627,0.0004648532,0.0001283826],"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":[0.001133608,0.0001959678,0.01881465,0.0002390976,0.0001090613,0.000413215,0.0001163405,0.07108977,0.06565055,0.01179903,0.003096979,0.8273417],"study_design_scores_gemma":[0.00002064124,0.00008449229,0.009883365,0.00001586883,0.00004656679,0.0007437708,0.00009802698,0.9378821,0.04223669,0.006845319,0.002104762,0.0000383318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1274479,0.001240831,0.8679289,0.0002794506,0.00006943396,0.00003256906,0.0005910651,0.0007558807,0.001653955],"genre_scores_gemma":[0.6536906,0.001425756,0.337769,0.0001507876,0.0002370064,0.0000690936,0.001930933,0.0001032469,0.004623554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001846734,"threshold_uncertainty_score":0.006177902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02152338838573285,"score_gpt":0.2492014349661,"score_spread":0.2276780465803671,"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."}}