{"id":"W2048476252","doi":"10.1016/j.ins.2011.03.007","title":"Modeling term proximity for probabilistic information retrieval models","year":2011,"lang":"en","type":"article","venue":"Information Sciences","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Term (time); Divergence-from-randomness model; Computer science; Probabilistic logic; Term Discrimination; Probabilistic relevance model; Information retrieval; Data mining; Artificial intelligence; Probabilistic analysis of algorithms; Search engine; Concept search","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016957,0.0001508608,0.0001418321,0.0004259717,0.0006014589,0.0007944013,0.001164265,0.00008551559,0.00001755547],"category_scores_gemma":[0.0002774484,0.0001200272,0.00008251475,0.0008725254,0.0001362779,0.04896191,0.0001771045,0.0001132303,0.0001391982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007082627,"about_ca_system_score_gemma":0.0003408958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003985027,"about_ca_topic_score_gemma":0.000001946137,"domain_scores_codex":[0.9978327,0.00002607002,0.0007753436,0.0001393091,0.0008205794,0.0004059996],"domain_scores_gemma":[0.9984921,0.00004706626,0.0002428702,0.0003017888,0.0007886574,0.000127561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001084817,0.00006362472,0.0001282543,0.0001884703,0.00000982233,2.572116e-7,0.03633067,0.04268863,0.00002511681,0.8350751,0.0002377223,0.08514386],"study_design_scores_gemma":[0.0003143122,0.0001630335,0.0002028037,0.00001419656,0.000003692129,0.000007402828,0.0003464707,0.9716008,0.0004992166,0.02622872,0.0004326719,0.0001866266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03129516,0.000004043897,0.9540742,0.0001598795,0.0003358236,0.0009215252,0.00001881939,0.0002412686,0.01294927],"genre_scores_gemma":[0.9307245,0.000005172716,0.06855341,0.0005689256,0.00002045398,0.00007765043,0.00002588629,0.000002165509,0.00002184835],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9289122,"threshold_uncertainty_score":0.9643398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1286481222828739,"score_gpt":0.2964142241644975,"score_spread":0.1677661018816236,"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."}}