{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002292458,0.0001521088,0.0001350061,0.0002052059,0.00006219235,0.0002997101,0.001141842,0.00007586273,0.000273889],"category_scores_gemma":[0.000004902065,0.0001344,0.00005430208,0.0002705672,0.000004308269,0.0008392091,0.0002013593,0.0001737074,0.0005926453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000174364,"about_ca_system_score_gemma":0.00004145043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002220299,"about_ca_topic_score_gemma":0.00002496077,"domain_scores_codex":[0.9989431,0.00001577104,0.0001335798,0.0002957383,0.0003052586,0.0003065699],"domain_scores_gemma":[0.9993121,0.00001868735,0.00003864643,0.0005123438,0.00004333443,0.0000748594],"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":[0.000005348079,0.0001222656,0.00002321243,0.0002505795,0.000112653,0.00002732737,0.001682692,0.00005014157,0.0004374307,0.111679,0.028987,0.8566224],"study_design_scores_gemma":[0.001054567,0.0001297657,0.002738266,0.0002804019,0.0001073199,0.000007171242,0.001118388,0.6029209,0.006105942,0.0006609314,0.3826143,0.002262033],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.001635658,0.000958661,0.423493,0.0003093901,0.003708962,0.0004000052,0.000009435314,0.0007409381,0.568744],"genre_scores_gemma":[0.0298955,0.0002244687,0.4929349,0.0001835448,0.0006967137,0.0000439012,0.001964958,0.00004856725,0.4740075],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8543603,"threshold_uncertainty_score":0.7617453,"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."}}