{"id":"W2052842594","doi":"10.1145/2590988","title":"Modeling Term Associations for Probabilistic Information Retrieval","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; International Business Machines Corporation","keywords":"Term Discrimination; Computer science; Term (time); Bigram; Divergence-from-randomness model; Probabilistic logic; Ranking (information retrieval); Query expansion; Information retrieval; Data mining; Artificial intelligence; Web search query; Search engine; Concept search; Trigram","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":[0.001219324,0.0001995351,0.0002320358,0.0005481443,0.0006910927,0.001033953,0.0008097646,0.000172139,0.000008193233],"category_scores_gemma":[0.0005072763,0.0001861337,0.000150792,0.0006404936,0.00002262715,0.01058997,0.00001730006,0.000226946,0.0004595486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002600379,"about_ca_system_score_gemma":0.0001402956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003348617,"about_ca_topic_score_gemma":0.000001903244,"domain_scores_codex":[0.9975811,0.00007875726,0.001101554,0.0001327279,0.0007431466,0.000362731],"domain_scores_gemma":[0.9975281,0.0002702194,0.000313877,0.0007488562,0.0009936354,0.0001453374],"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":[0.0001217862,0.0001196922,0.00003975174,0.0004687152,0.00007453164,9.868288e-8,0.008178724,0.7106193,0.00003578198,0.1523962,0.0005112718,0.1274341],"study_design_scores_gemma":[0.0009147583,0.0001905312,0.0001576936,0.00003878732,0.0000172248,0.000007081514,0.0002538302,0.9852974,0.0001616613,0.0007059237,0.01199703,0.0002580488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003204045,0.000002462561,0.9919385,0.0004732589,0.0011338,0.001287036,0.0001477747,0.0004174098,0.001395737],"genre_scores_gemma":[0.9880298,0.000005046729,0.01077511,0.0004752988,0.00006085423,0.0002938729,0.0002447093,0.00000764164,0.0001076571],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9848258,"threshold_uncertainty_score":0.9970433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03054072446624775,"score_gpt":0.267857013344392,"score_spread":0.2373162888781443,"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."}}