{"id":"W2030760474","doi":"10.1145/1076034.1076085","title":"Linear discriminant model for information retrieval","year":2005,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Discriminative model; Artificial intelligence; Language model; Linear discriminant analysis; Rank (graph theory); Pattern recognition (psychology); Probabilistic logic; Natural language processing; Hidden Markov model; Component (thermodynamics); Machine learning; 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":[0.0001536483,0.00005950361,0.00005579992,0.0000611685,0.00005819791,0.00009767315,0.0004252621,0.00004142744,0.000001740294],"category_scores_gemma":[0.0000673645,0.0000432097,0.00002971451,0.0001102781,0.000009335663,0.002096102,0.0001022668,0.00005312778,0.00001615492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000298025,"about_ca_system_score_gemma":0.00003675895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002859796,"about_ca_topic_score_gemma":0.000002339727,"domain_scores_codex":[0.9995126,0.000003421971,0.0001362533,0.00009260231,0.0001241569,0.0001310129],"domain_scores_gemma":[0.9996058,0.00001734923,0.00004376537,0.0002037672,0.00009872644,0.00003063964],"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":[0.00002081882,0.00002404099,0.000002693457,0.00003535299,0.000002945159,2.497849e-7,0.001534726,0.00077236,0.001584258,0.6917675,0.006818428,0.2974366],"study_design_scores_gemma":[0.00008650108,0.00001928826,0.000001325355,0.000005177572,0.000001378321,0.000002377564,0.000003827872,0.9366773,0.04038686,0.01922717,0.003514833,0.00007399353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002155915,0.00007237704,0.996105,0.002198234,0.00003349171,0.0001354758,0.000001728345,0.0005268621,0.0007112233],"genre_scores_gemma":[0.1947082,0.000002222939,0.8038097,0.0008632945,0.00003545597,0.000005700948,0.000003670887,0.000002198668,0.000569482],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9359049,"threshold_uncertainty_score":0.1762041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02011058129652285,"score_gpt":0.2907212348309982,"score_spread":0.2706106535344753,"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."}}