{"id":"W1994604287","doi":"10.1145/1244002.1244186","title":"Log-based indexing to improve web site search","year":2007,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Search engine indexing; Computer science; Information retrieval; Search engine; Index (typography); Web site; World Wide Web; Web server; Web search engine; Web log analysis software; Web page; Static web page; Web search query; Data mining; The Internet","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":[0.0009129946,0.00007895762,0.00009765534,0.0002442072,0.0000828143,0.0001666858,0.0006318917,0.0000355885,0.00004286994],"category_scores_gemma":[0.00003999586,0.00006662693,0.00004864247,0.0007812697,0.0000140914,0.0001938824,0.0002547287,0.0000991557,0.000498114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002858897,"about_ca_system_score_gemma":0.0000765584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002364522,"about_ca_topic_score_gemma":0.0001942433,"domain_scores_codex":[0.9988797,0.00002048335,0.0001449948,0.0003461921,0.0002698494,0.0003387331],"domain_scores_gemma":[0.9990643,0.0001041619,0.00001894413,0.0005786013,0.00006123177,0.0001728063],"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":[0.00003386833,0.0002628839,0.06851459,0.00003812836,0.00008821615,0.0002179224,0.001749089,0.00352342,0.1990724,0.02183821,0.01397172,0.6906896],"study_design_scores_gemma":[0.000582714,0.0002231272,0.008514881,0.00002743184,0.00001221113,0.000003985291,0.0001285705,0.8817611,0.08556715,0.00009374702,0.02258088,0.0005042208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1296518,0.000005570451,0.8631502,0.001067656,0.00007712969,0.00003942394,0.000003229723,0.0001423757,0.005862575],"genre_scores_gemma":[0.8899115,2.299939e-7,0.1066498,0.001688241,0.0000601712,0.000001246486,0.000003923112,0.000004349438,0.001680628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8782377,"threshold_uncertainty_score":0.6402414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01830160433084393,"score_gpt":0.27956850929282,"score_spread":0.261266904961976,"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."}}