{"id":"W2103615139","doi":"10.14778/1453856.1453955","title":"Keyword query cleaning","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Ontario Tech University","funders":"","keywords":"Computer science; Query optimization; Query expansion; Web query classification; Web search query; Sargable; Query language; Information retrieval; Online aggregation; View; Set (abstract data type); Context (archaeology); Database; Query by Example; Data mining; Search engine","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":[0.0002109334,0.0001069226,0.0001188445,0.00006666684,0.0001708371,0.00006966339,0.001568378,0.0000191867,0.000008429159],"category_scores_gemma":[0.00002971428,0.00007393552,0.00007742079,0.0003544748,0.00005908958,0.0006833617,0.001069362,0.00008772908,0.00002415723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002986865,"about_ca_system_score_gemma":0.00001317472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002335668,"about_ca_topic_score_gemma":4.347132e-7,"domain_scores_codex":[0.998961,0.00000313256,0.0001920763,0.0002466865,0.0003737544,0.0002232892],"domain_scores_gemma":[0.9995182,0.00001365306,0.0001486341,0.000208394,0.00006935916,0.00004181433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002285406,0.0004523463,0.02427941,0.0001983712,0.0001707058,0.00001260576,0.004358342,0.00003595408,0.01900274,0.722929,0.1320572,0.09648048],"study_design_scores_gemma":[0.003914164,0.0006524503,0.07262436,0.0006264704,0.0001179735,0.0002638663,0.00118348,0.0327918,0.5073615,0.05388988,0.3246765,0.001897587],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6083131,0.0005791755,0.02941711,0.01320759,0.003149246,0.001877316,0.00001094905,0.001018458,0.342427],"genre_scores_gemma":[0.969889,0.00009433112,0.0265381,0.000390835,0.00009916972,0.00002061393,5.441161e-7,0.00000937941,0.002957986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6690391,"threshold_uncertainty_score":0.3015003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01646142064894577,"score_gpt":0.1908917334095587,"score_spread":0.1744303127606129,"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."}}