{"id":"W1963912989","doi":"10.1145/1236181.1236183","title":"Inferential language models for information retrieval","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Inference; Language model; Smoothing; Term (time); Natural language processing; Artificial intelligence; Query language; Machine learning; Information retrieval; Data mining","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":[0.0002478751,0.0001833391,0.0001490357,0.0004468889,0.000352691,0.000743264,0.0006222255,0.0001273844,0.00002029565],"category_scores_gemma":[0.00005323513,0.0001831405,0.00009500488,0.0004534997,0.00002210227,0.01255356,0.00001692909,0.0002010901,0.00005445665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001013642,"about_ca_system_score_gemma":0.0001338854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006265198,"about_ca_topic_score_gemma":0.0000145029,"domain_scores_codex":[0.9985428,0.00002069635,0.0005874255,0.0001539545,0.0003917551,0.0003033742],"domain_scores_gemma":[0.9989148,0.00004103365,0.0002501284,0.0005352602,0.0001941861,0.00006459453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003705802,0.00003426076,0.000001556149,0.0001407323,0.000008817244,7.252523e-7,0.0166693,0.04016806,0.0001417996,0.005880951,0.00006011988,0.9368566],"study_design_scores_gemma":[0.001428849,0.00007171695,0.00005477922,0.00009262866,0.0000230998,0.00002513424,0.004315624,0.9766793,0.009512666,0.005394189,0.001982189,0.0004197795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003629196,0.0000335685,0.9890388,0.0006710191,0.000234231,0.0003834928,0.00003379357,0.0004863176,0.005489633],"genre_scores_gemma":[0.8519548,0.000001350626,0.1472263,0.0005027414,0.00006801238,0.00004080264,0.0001085197,0.000008121058,0.00008937676],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9365113,"threshold_uncertainty_score":0.9101031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01074942129375895,"score_gpt":0.2498861546723253,"score_spread":0.2391367333785664,"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."}}