{"id":"W4220686815","doi":"10.29173/cais1293","title":"Correlation of term usage and term indexing frequencies","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Zipf's law; Term (time); Search engine indexing; Information retrieval; Rank (graph theory); Computer science; Cluster analysis; Index (typography); Plot (graphics); Word (group theory); Data mining; Statistics; Mathematics; Artificial intelligence; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"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":[0.007730134,0.0002777051,0.0007103941,0.01026026,0.0004806593,0.002628736,0.0007767488,0.000436656,0.005018158],"category_scores_gemma":[0.09990515,0.0003251471,0.0007097749,0.01902774,0.0008616393,0.002171829,0.001237763,0.0009944765,0.0019774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009767895,"about_ca_system_score_gemma":0.0008983715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007966128,"about_ca_topic_score_gemma":0.007467536,"domain_scores_codex":[0.9845137,0.003304581,0.002679724,0.001794997,0.006940401,0.0007665999],"domain_scores_gemma":[0.7993309,0.1363302,0.03037205,0.009399674,0.02280416,0.001762948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002767644,0.00005162576,0.9641506,0.0002602278,0.0002245176,0.0001345055,0.00115634,0.0006699226,0.0009537442,0.0008602903,0.001580324,0.02968111],"study_design_scores_gemma":[0.000006132288,0.00009893726,0.9908553,0.00004537383,0.00006089852,0.0004309009,0.0007973971,0.002029338,0.0008403646,0.0006799109,0.004119655,0.00003575883],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9726703,0.002038708,0.006808303,0.0003001615,0.0001086291,0.0001123721,0.006510322,0.0003127395,0.01113846],"genre_scores_gemma":[0.9865428,0.0007068164,0.003477779,0.00003837498,0.00007893252,0.00012241,0.005882671,0.0001509057,0.00299942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01026026,"threshold_uncertainty_score":0.0408814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01800631411748159,"score_gpt":0.2486120745708668,"score_spread":0.2306057604533852,"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."}}