{"id":"W2160825952","doi":"10.1145/1008992.1009024","title":"Dependence language model for information retrieval","year":2004,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":261,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Language model; Term (time); Smoothing; Linkage (software); Divergence-from-randomness model; Artificial intelligence; Probabilistic logic; Independence (probability theory); Graph; Sentence; Term Discrimination; Axiom; Natural language processing; Theoretical computer science; Visual Word; Mathematics; Image retrieval","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":[0.0001263638,0.00004108004,0.00003986346,0.00003687367,0.00003954088,0.00007579214,0.0003252503,0.00002806456,0.000001704407],"category_scores_gemma":[0.00004095058,0.000036277,0.00002239133,0.00007401196,0.000004074714,0.001192651,0.00006629439,0.00003385191,0.00002896464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003287706,"about_ca_system_score_gemma":0.00006539183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002249913,"about_ca_topic_score_gemma":0.000008563659,"domain_scores_codex":[0.9995573,0.000002140539,0.0001076543,0.00008911034,0.0001296045,0.0001142445],"domain_scores_gemma":[0.9996533,0.00001194567,0.00002507133,0.0002355811,0.00004306196,0.00003098585],"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":[0.000004802123,0.000008045926,0.000007797454,0.00001192357,0.000002260855,6.270314e-7,0.003888129,0.2486794,0.0005521706,0.7262545,0.00005846404,0.02053191],"study_design_scores_gemma":[0.0002405943,0.00001008607,0.00001092018,0.000003018303,6.910477e-7,0.000002738424,0.0000332681,0.9798227,0.003656473,0.01610895,0.0000576384,0.00005294794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01310052,0.000008582751,0.9837121,0.0004880262,0.00007387193,0.0001121002,8.896542e-7,0.0001388415,0.002365112],"genre_scores_gemma":[0.5996966,5.73842e-7,0.3996842,0.0004404172,0.00001159527,0.000002585849,9.531121e-7,9.902401e-7,0.000162113],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7311433,"threshold_uncertainty_score":0.1479333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02058730128944972,"score_gpt":0.2583534641804145,"score_spread":0.2377661628909648,"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."}}