{"id":"W2145050101","doi":"10.1109/cnsr.2007.5","title":"A Novel Approach for Frequent Phrase Mining in Web Search Engine Query Streams","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Atlantic Canada Opportunities Agency","keywords":"Computer science; Phrase; Set (abstract data type); Data stream mining; Data mining; Information retrieval; Recommender system; Phrase search; Data stream; Web query classification; Web search query; Search engine; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0008241566,0.00009408851,0.000105151,0.0001474427,0.00006215917,0.00009058385,0.0005599647,0.00004244695,0.000004688248],"category_scores_gemma":[0.00002416575,0.00008455128,0.00003270217,0.0004603959,0.00002116448,0.000233409,0.000143187,0.00008542674,0.000005570413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004458495,"about_ca_system_score_gemma":0.00007527207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001594635,"about_ca_topic_score_gemma":0.00008491048,"domain_scores_codex":[0.9989198,0.000006017761,0.0002079105,0.0003654728,0.0001575092,0.0003432612],"domain_scores_gemma":[0.9992927,0.0001232891,0.00002619149,0.0004198363,0.0000421514,0.00009587195],"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":[0.000006661128,0.0007903019,0.000500081,0.0000305622,0.00001562622,0.000006077344,0.001176085,0.0007978242,0.01062882,0.0742287,0.001574206,0.9102451],"study_design_scores_gemma":[0.0005280976,0.00003775519,0.0006000501,0.000009604204,0.000001708635,0.000009968875,0.0003779454,0.9939983,0.002288253,0.0000540496,0.001952342,0.00014192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02570331,0.00002315271,0.9703268,0.0002440916,0.00003505087,0.0002472867,0.00002797396,0.00009491375,0.003297422],"genre_scores_gemma":[0.1614202,0.000002204504,0.83794,0.0001184285,0.00005807857,0.00006291697,0.00004107545,0.000007122439,0.0003499693],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9932005,"threshold_uncertainty_score":0.3447901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04000222621762329,"score_gpt":0.2943553656368082,"score_spread":0.2543531394191849,"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."}}