{"id":"W2344430697","doi":"10.3233/web-160335","title":"Accurate and efficient query clustering via top ranked search results","year":2016,"lang":"en","type":"article","venue":"Web Intelligence","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Science Foundation","keywords":"Computer science; Cluster analysis; Data mining; Information retrieval; DBSCAN; Search engine; Web search query; Metric (unit); Feature (linguistics); Hierarchical clustering; Similarity (geometry); Query expansion; Fuzzy clustering; CURE data clustering algorithm; Machine learning; Artificial intelligence","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":[0.0006732636,0.0001298109,0.0001147464,0.000117887,0.0001056137,0.0002309028,0.0009709033,0.00003346146,0.00001854077],"category_scores_gemma":[0.00006952584,0.00008859691,0.00002915161,0.0002981586,0.00008799719,0.0004772676,0.001067801,0.00007720977,0.000305489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002792017,"about_ca_system_score_gemma":0.00002490845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003442612,"about_ca_topic_score_gemma":0.0000141481,"domain_scores_codex":[0.9985529,0.00005487432,0.0002641569,0.0005184874,0.0002662386,0.0003433716],"domain_scores_gemma":[0.9989797,0.0001756137,0.00005370794,0.0006340949,0.00005603527,0.0001008532],"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":[0.00003959965,0.00004424366,0.00006725427,0.00002751387,0.00002091519,0.00004943514,0.0005395186,0.0006897449,0.003474839,0.01414603,0.0005467886,0.9803541],"study_design_scores_gemma":[0.0003256474,0.00009694556,0.0007460406,0.0001289141,0.000004546774,0.00001597228,0.00005307178,0.970587,0.01823302,0.0007123204,0.008773589,0.0003229947],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009742327,0.00007816423,0.985395,0.001923708,0.0004060575,0.0001586286,0.00001033051,0.000135358,0.002150477],"genre_scores_gemma":[0.9853799,0.0001881829,0.01296249,0.0001460933,0.00006803114,0.000007692499,0.000001756855,0.000007108962,0.001238732],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9800311,"threshold_uncertainty_score":0.3926544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03174857622042965,"score_gpt":0.2767855005657308,"score_spread":0.2450369243453011,"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."}}