{"id":"W2102838806","doi":"10.1016/j.ipm.2008.01.003","title":"Lexical cohesion and term proximity in document ranking","year":2008,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Query expansion; Ranking (information retrieval); Computer science; Cohesion (chemistry); Information retrieval; Collocation (remote sensing); Relevance (law); Term (time); Query optimization; Natural language processing; Artificial intelligence; Machine learning","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":[0.0002651107,0.00008452153,0.00009311524,0.0001730779,0.0001619949,0.0002187684,0.000243714,0.00002935479,0.000002173932],"category_scores_gemma":[0.00001240193,0.00007197628,0.00001328986,0.0002083195,0.00003938876,0.003244698,0.0002287384,0.00006273761,0.00001470481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004427266,"about_ca_system_score_gemma":0.00001949528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009078203,"about_ca_topic_score_gemma":0.00000200714,"domain_scores_codex":[0.9991701,0.00001536286,0.0002760715,0.0001249209,0.0002476645,0.000165942],"domain_scores_gemma":[0.9996899,0.0000119808,0.00009522391,0.0001471213,0.00002800339,0.00002777721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001060417,0.00003030939,0.007901972,0.0002830094,0.000005189123,0.0000220608,0.004815666,0.00009502771,0.000004868118,0.01822505,0.0001620469,0.9684442],"study_design_scores_gemma":[0.00245201,0.00008240648,0.8861958,0.0004736048,0.00001264237,0.0001053273,0.0008662398,0.07999527,0.000714547,0.0186357,0.009923565,0.0005429224],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3922166,0.0002039706,0.5881701,0.001575562,0.0001748682,0.0005273113,1.603097e-7,0.0003180383,0.01681342],"genre_scores_gemma":[0.9739259,0.00006474334,0.02544292,0.0004747853,0.000007247316,0.00002519408,0.000001663241,0.000001541723,0.00005597857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9679013,"threshold_uncertainty_score":0.2935107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0155754297426092,"score_gpt":0.2417716080082823,"score_spread":0.2261961782656731,"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."}}