{"id":"W2113673066","doi":"10.1109/hicss.2008.129","title":"Document Retrieval Using Proximity-Based Phrase Searching","year":2008,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Phrase; Computer science; Section (typography); Information retrieval; Vector space model; Phrase search; Space (punctuation); Matching (statistics); Natural language processing; Artificial intelligence; Search engine; Web search query; Mathematics","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":[0.0003391011,0.00009184089,0.00009752658,0.00008677124,0.0002212115,0.00008349674,0.0004834157,0.00003160189,0.00003032087],"category_scores_gemma":[0.00003786148,0.00008131179,0.00004728038,0.0002328176,0.00002812459,0.0005005136,0.000188579,0.0001349647,0.00002577914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008381363,"about_ca_system_score_gemma":0.0002110451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008990483,"about_ca_topic_score_gemma":0.000001577671,"domain_scores_codex":[0.9987665,0.00006267423,0.0001705302,0.0003243568,0.0003973341,0.0002785845],"domain_scores_gemma":[0.9992769,0.00003937563,0.00003636729,0.000497492,0.00004532209,0.0001045538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001870078,0.0009700445,0.02450765,0.000322978,0.0001393657,0.002270119,0.0118045,0.4006764,0.1304161,0.367626,0.001111985,0.05996786],"study_design_scores_gemma":[0.0003054087,0.00002274023,0.0001124451,0.00001294619,0.000001566898,0.00003445111,0.000006854995,0.9766672,0.02106848,0.001356672,0.0002781479,0.0001330785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3431605,0.0000119917,0.6553093,0.0004166731,0.00009644962,0.00009299501,1.136707e-7,0.0001396948,0.000772183],"genre_scores_gemma":[0.615743,8.790489e-7,0.3836422,0.0003846904,0.0000443365,4.790069e-7,2.583407e-7,0.000004149664,0.0001800845],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5759908,"threshold_uncertainty_score":0.3315798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06451732651132608,"score_gpt":0.2951161408177277,"score_spread":0.2305988143064017,"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."}}