{"id":"W2779944493","doi":"10.24124/2010/bpgub700","title":"Study of document retrieval using Latent Semantic Indexing (LSI) on a very large data set.","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Northern British Columbia","keywords":"Information retrieval; Computer science; Set (abstract data type); Search engine indexing; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01205152,0.0006341049,0.001801206,0.005268139,0.0009204886,0.002472744,0.001476885,0.001027694,0.001469656],"category_scores_gemma":[0.05073572,0.0003637986,0.001300698,0.005349217,0.001175053,0.005602155,0.0009720043,0.001449768,0.0006066565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001820113,"about_ca_system_score_gemma":0.001512135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007591468,"about_ca_topic_score_gemma":0.007944163,"domain_scores_codex":[0.993974,0.003570643,0.0005284297,0.0006474042,0.001043596,0.0002359424],"domain_scores_gemma":[0.9104099,0.07967669,0.002017936,0.004671729,0.002529014,0.0006947258],"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":[0.00386327,0.004845774,0.09517097,0.003926185,0.002559185,0.0012071,0.002293107,0.1456007,0.01493947,0.04162515,0.05889675,0.6250723],"study_design_scores_gemma":[0.000174742,0.0007051301,0.02056105,0.00007297529,0.0002337152,0.0006965772,0.0007069471,0.9588546,0.003684184,0.009905908,0.004343953,0.00006028831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8205532,0.02961564,0.1316401,0.004632481,0.0003452268,0.000577576,0.005947932,0.001658599,0.005029146],"genre_scores_gemma":[0.9079726,0.002698746,0.07699034,0.0001821715,0.0004959371,0.0002950779,0.00904086,0.0001745579,0.00214974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01205152,"threshold_uncertainty_score":0.06373531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08128817225861587,"score_gpt":0.3508740158644802,"score_spread":0.2695858436058644,"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."}}