{"id":"W2045517286","doi":"10.1109/icdim.2010.5664669","title":"Latent semantic indexing and large dataset: Study of term-weighting schemes","year":2010,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Computer science; Weighting; Information retrieval; Term (time); Search engine indexing; Precision and recall; Document retrieval; Latent semantic analysis; Graph; Term Discrimination; Data mining; Search engine; Concept search; Web search query","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":[0.0003038578,0.00006929458,0.0001063208,0.00005728885,0.00007075271,0.00006372138,0.0003690967,0.00002710222,0.00001510978],"category_scores_gemma":[0.00002198942,0.0000552182,0.000009540207,0.00008204329,0.00001055856,0.0002716378,0.000556219,0.0001292164,0.000003230824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002388864,"about_ca_system_score_gemma":0.00001131099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007043433,"about_ca_topic_score_gemma":0.0001400844,"domain_scores_codex":[0.9992435,0.00001669368,0.00017939,0.0002536802,0.0001534621,0.0001532758],"domain_scores_gemma":[0.9993604,0.00003344364,0.00005539428,0.0004862369,0.00002240575,0.00004214658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003565494,0.000818429,0.8167088,0.00009732522,0.00006804225,0.00004204525,0.007390766,0.00002727093,0.03439948,0.08164018,0.0001933123,0.0586108],"study_design_scores_gemma":[0.002291245,0.0002083425,0.07878196,0.00005061217,0.00002954014,0.00003714182,0.0006913652,0.903057,0.01015195,0.001427675,0.002764395,0.0005087241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8867452,0.00001193475,0.1127688,0.00007102806,0.0001116108,0.000101801,0.00000281259,0.00003963754,0.0001472477],"genre_scores_gemma":[0.9729326,8.162131e-7,0.0269439,0.00005537683,0.0000253649,0.000002120468,0.000002539906,0.000003322735,0.00003389614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9030298,"threshold_uncertainty_score":0.2251733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02180303817818376,"score_gpt":0.2713560739859011,"score_spread":0.2495530358077173,"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."}}