{"id":"W2156171684","doi":"10.31979/etd.hwkh-5782","title":"Optimizing a Web Search Engine","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Bigram; Search engine; Information retrieval; Search analytics; Computer science; Spamdexing; Metasearch engine; Web search engine; Weighting; Web crawler; Web search query; Relevance (law); Organic search; Word (group theory); Search-oriented architecture; Inverted index; World Wide Web; Phrase search; Search engine indexing; Artificial intelligence; Trigram; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001487905,0.001060217,0.001299348,0.0021757,0.0007079978,0.002133462,0.001661185,0.0009246542,0.007458885],"category_scores_gemma":[0.006400842,0.0006202579,0.0008071724,0.003595415,0.0003078971,0.003298538,0.0009847531,0.0009009797,0.006437135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001457897,"about_ca_system_score_gemma":0.002040506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01148757,"about_ca_topic_score_gemma":0.01740829,"domain_scores_codex":[0.9979731,0.0005292231,0.0001895298,0.0003405181,0.0007281012,0.000239515],"domain_scores_gemma":[0.9977978,0.0006884363,0.00007717004,0.0002777378,0.001033178,0.0001256323],"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":[0.001021244,0.0006348551,0.006394599,0.001032633,0.0003554771,0.0004040714,0.0002373973,0.08796461,0.04691415,0.009530186,0.08249528,0.7630154],"study_design_scores_gemma":[0.0002308588,0.0002633696,0.002898327,0.00005058422,0.0002368409,0.0004006129,0.0003666968,0.9224746,0.02416365,0.009342607,0.03951382,0.00005799366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1413545,0.004057842,0.7375779,0.001899424,0.0003928224,0.002108708,0.004085951,0.05220006,0.05632281],"genre_scores_gemma":[0.251288,0.001144678,0.7193966,0.0004892994,0.0001194986,0.0007278071,0.00506811,0.002009707,0.01975631],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01148757,"threshold_uncertainty_score":0.02495247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02202995629125434,"score_gpt":0.2737703428432567,"score_spread":0.2517403865520024,"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."}}