{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002274447,0.0001028725,0.0001115803,0.00014334,0.0003099849,0.0004435837,0.0004054965,0.00006245962,0.00004363625],"category_scores_gemma":[0.000008642032,0.00009163724,0.00003043013,0.0002940403,0.00001604325,0.003518134,0.000009782622,0.0001341176,0.000173394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003027514,"about_ca_system_score_gemma":0.00002094141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004718519,"about_ca_topic_score_gemma":6.068114e-7,"domain_scores_codex":[0.9990626,0.00002993268,0.0003299717,0.0001316666,0.0002943733,0.0001514871],"domain_scores_gemma":[0.9991835,0.00007796292,0.00006443737,0.0005476446,0.00005208332,0.00007438549],"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":[0.00004325335,0.00002521661,0.00003579896,0.00003661267,0.00002127981,0.000001843004,0.001730597,0.01631349,0.00003932846,0.001622459,0.0001940818,0.9799361],"study_design_scores_gemma":[0.001975418,0.0002377115,0.003681121,0.0003806465,0.00002477649,0.0003143224,0.0005997243,0.7743312,0.001536198,0.0004828653,0.2157034,0.0007326474],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01300275,0.00006021274,0.9836421,0.0001272296,0.0004076779,0.0001925299,0.00001508221,0.0002180795,0.002334339],"genre_scores_gemma":[0.9920301,0.00009732664,0.007531668,0.0001168337,0.00003437559,0.000013735,0.000009933687,0.000004037636,0.000161988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9792034,"threshold_uncertainty_score":0.4277488,"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."}}