{"id":"W2070507812","doi":"10.1145/1148170.1148285","title":"Term proximity scoring for ad-hoc retrieval on very large text collections","year":2006,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Term (time); Term Discrimination; Artificial intelligence; Natural language processing; Search engine; Concept search; Web search query","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":[0.0003312195,0.0001057461,0.000106599,0.0001800914,0.000584682,0.0003091421,0.0003465326,0.00006036475,0.00005723083],"category_scores_gemma":[0.00005077591,0.00008795669,0.00009057885,0.0007366078,0.00002050361,0.0007665688,0.00009917783,0.0001218169,0.00009944964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001049255,"about_ca_system_score_gemma":0.0001132203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009035701,"about_ca_topic_score_gemma":0.00001803715,"domain_scores_codex":[0.9988431,0.00001903253,0.0002343804,0.0002149502,0.0003296205,0.0003588884],"domain_scores_gemma":[0.9993223,0.00008959973,0.00005383796,0.0002935976,0.0001707299,0.00006991612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007883183,0.002131375,0.004162575,0.0002028523,0.00004822593,0.00002524233,0.001222472,0.0002283428,0.007838956,0.8025058,0.1210715,0.05977436],"study_design_scores_gemma":[0.009250958,0.003642275,0.09056766,0.0001418825,0.00004395052,0.00006400444,0.000229524,0.1622242,0.2252202,0.01171936,0.4949381,0.001957951],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1778841,0.00004015135,0.7623307,0.001107372,0.001124414,0.001609773,0.00004948156,0.0007487216,0.05510531],"genre_scores_gemma":[0.8920786,0.00001121707,0.02643081,0.0007339991,0.0002226504,0.00009347072,0.00002771138,0.00001716831,0.08038439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7907864,"threshold_uncertainty_score":0.449696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02238626999339941,"score_gpt":0.2708168976675244,"score_spread":0.248430627674125,"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."}}