{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005727402,0.00009876985,0.000105323,0.00005249223,0.0006865028,0.000228569,0.0003622432,0.00003727535,0.00009228181],"category_scores_gemma":[0.00002028085,0.00006669457,0.00003498557,0.0001544467,0.00004733402,0.000731625,0.0001546868,0.0003250529,0.00003313093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002884546,"about_ca_system_score_gemma":0.00006256317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002243217,"about_ca_topic_score_gemma":0.000002730457,"domain_scores_codex":[0.9989618,0.000104437,0.0001757709,0.0001875331,0.0003621086,0.0002083477],"domain_scores_gemma":[0.9994367,0.00009401051,0.00007893919,0.000223986,0.0000537099,0.0001126314],"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":[0.00003813404,0.0001629277,0.0004247605,0.000003588068,0.00002513881,0.000024945,0.000319446,0.02956486,0.002908188,0.0008000568,0.001531055,0.9641969],"study_design_scores_gemma":[0.0005017431,0.00004381552,0.04055607,0.00004270785,0.000007538789,0.0008143003,0.000002145352,0.9534601,0.0006595825,0.003173517,0.0006227945,0.0001157032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6888267,0.0005003804,0.3088831,0.001318486,0.0002280472,0.00008448188,0.000002882386,0.00006293073,0.00009301303],"genre_scores_gemma":[0.8272772,0.00004147455,0.1719618,0.000352988,0.0001666359,0.00000187503,0.000002310733,0.000007700995,0.0001879989],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9640812,"threshold_uncertainty_score":0.5280094,"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."}}