{"id":"W4382893966","doi":"10.5121/ijnlc.2023.12301","title":"Testing Different Log Bases for Vector Model Weighting Technique","year":2023,"lang":"en","type":"article","venue":"International Journal on Natural Language Computing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Workers Compensation Board of Alberta; Alberta Biodiversity Monitoring Institute","funders":"","keywords":"Weighting; tf–idf; Computer science; Term (time); Logarithm; Information retrieval; Vector space model; Range (aeronautics); Data mining; Base (topology); Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006801303,0.0008529514,0.0007296588,0.002151928,0.0006952875,0.001496463,0.001498527,0.001304356,0.002767462],"category_scores_gemma":[0.05305521,0.0003118288,0.0006936309,0.002312879,0.0007098953,0.003450646,0.001344232,0.001559114,0.0009641856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001167887,"about_ca_system_score_gemma":0.0009790657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005425026,"about_ca_topic_score_gemma":0.003413467,"domain_scores_codex":[0.9939944,0.002539554,0.0005261831,0.0007052721,0.001934434,0.0003001457],"domain_scores_gemma":[0.9675983,0.0224866,0.001115287,0.003818604,0.004582958,0.0003982215],"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":[0.006551529,0.004130641,0.03216617,0.001248808,0.000625508,0.0003105731,0.0006484342,0.2011108,0.03093769,0.01379493,0.01825939,0.6902155],"study_design_scores_gemma":[0.0003996847,0.003060543,0.01541716,0.0001212428,0.0001650789,0.0004814015,0.0006994578,0.9232418,0.03864157,0.01031295,0.007318796,0.0001403399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8273398,0.001771342,0.1545613,0.0008218553,0.0003534853,0.0006598325,0.001771801,0.004484406,0.008236199],"genre_scores_gemma":[0.8601011,0.0005316556,0.1306603,0.0002275066,0.00007225935,0.0005489158,0.004026887,0.0003977029,0.003433587],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006801303,"threshold_uncertainty_score":0.0359692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02888458705003525,"score_gpt":0.3181266725152209,"score_spread":0.2892420854651856,"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."}}