{"id":"W2293475867","doi":"","title":"Towards web search engine scale data mining","year":2009,"lang":"en","type":"article","venue":"Australasian Data Mining Conference","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Adaptability; Search engine; Web mining; Data science; Data mining; Context (archaeology); Web search query; Web crawler; Web search engine; Metasearch engine; Search analytics; Construct (python library); Big data; Information retrieval; World Wide Web; Database; Web service","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001124394,0.0003345875,0.0003316863,0.0002324619,0.0002026675,0.001397634,0.01519033,0.00009664104,0.0001528119],"category_scores_gemma":[0.000140725,0.0003351947,0.00002897187,0.0007453918,0.0001099339,0.005879886,0.006175507,0.000306537,0.0001799481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002504665,"about_ca_system_score_gemma":0.0003198091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004536323,"about_ca_topic_score_gemma":0.00004323543,"domain_scores_codex":[0.996307,0.00008653157,0.0004314037,0.001669084,0.0006730146,0.0008329715],"domain_scores_gemma":[0.9922827,0.00007112055,0.0001166341,0.007171733,0.00008556889,0.0002722383],"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":[0.000004251974,0.00008069877,0.0006312301,0.00001855139,0.00002958299,0.000110302,0.0004280554,0.000004124202,0.0001859971,0.002210233,0.05208311,0.9442139],"study_design_scores_gemma":[0.001074377,0.0003205574,0.02026471,0.0003027392,0.0000671983,0.00007532038,0.0009543234,0.895548,0.0004617035,0.000237879,0.07958547,0.001107738],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05486906,0.0002083934,0.8605431,0.02536347,0.00180343,0.0008983171,0.003645715,0.001645444,0.05102302],"genre_scores_gemma":[0.5992321,0.00006302429,0.3954629,0.0002864459,0.0002292966,0.000002752729,0.003162615,0.00001434466,0.00154655],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9431061,"threshold_uncertainty_score":0.99991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1295590154397186,"score_gpt":0.3325322425937539,"score_spread":0.2029732271540353,"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."}}