{"id":"W2035512259","doi":"10.1145/333135.333137","title":"Shortest-substring retrieval and ranking","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Computer science; Ranking (information retrieval); Information retrieval; Relevance (law); Boolean conjunctive query; Substring; Matching (statistics); Standard Boolean model; Phrase; Learning to rank; Simple (philosophy); Theoretical computer science; Data mining; Boolean expression; Algorithm; Boolean function; And-inverter graph; Search engine; Data structure; Artificial intelligence; Web search query; Mathematics; Statistics; Web query classification","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":[0.00305332,0.001060554,0.002009559,0.003345251,0.001411928,0.004687415,0.004409795,0.002426164,0.008790111],"category_scores_gemma":[0.01146009,0.0006662733,0.001850576,0.006578992,0.001609248,0.01044258,0.001803608,0.00178369,0.007405404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002358933,"about_ca_system_score_gemma":0.002143069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00709706,"about_ca_topic_score_gemma":0.005785719,"domain_scores_codex":[0.995939,0.001198167,0.0003603443,0.0006736077,0.001576151,0.0002526722],"domain_scores_gemma":[0.995965,0.001573466,0.0002772512,0.001379289,0.0006716146,0.000133345],"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":[0.0002854787,0.0002106427,0.00111584,0.0004926844,0.0001100935,0.0004128224,0.0003610577,0.1399338,0.005308171,0.6238289,0.01884488,0.2090956],"study_design_scores_gemma":[0.00005800656,0.000144021,0.0002059554,0.00003593201,0.00005597077,0.0004106542,0.00006401873,0.6507962,0.003365428,0.3156045,0.02918219,0.00007713698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003375084,0.0005634442,0.9890428,0.000484213,0.00007434467,0.0001946468,0.0005252195,0.001695304,0.004044909],"genre_scores_gemma":[0.1522639,0.001833814,0.8172408,0.0004620128,0.0004834269,0.0008589519,0.003558653,0.0006388969,0.0226595],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008790111,"threshold_uncertainty_score":0.02940583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01376031980485438,"score_gpt":0.2269255291116297,"score_spread":0.2131652093067753,"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."}}