{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006496315,0.0001951054,0.0004158403,0.0002698633,0.0001993212,0.0006806156,0.002177363,0.00007050351,0.00001221201],"category_scores_gemma":[0.003055351,0.0001678357,0.000124412,0.0006541689,0.0003635799,0.007958381,0.001777542,0.0002926975,2.127274e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006782902,"about_ca_system_score_gemma":0.0001333904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007274271,"about_ca_topic_score_gemma":0.000004342655,"domain_scores_codex":[0.9983007,0.00003183332,0.0005113952,0.0003389099,0.0005600674,0.0002571314],"domain_scores_gemma":[0.9886244,0.0001329042,0.001071265,0.0002702798,0.009837379,0.00006377054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005657315,0.0001716405,0.5848889,0.0002871146,0.0001172271,0.000002274714,0.04987735,0.00006108738,0.2314099,0.1047674,0.0003674911,0.02799308],"study_design_scores_gemma":[0.001148879,0.001216718,0.5076048,0.0005572981,0.0002180607,0.0001459643,0.004505299,0.01742326,0.3605789,0.09862392,0.006942261,0.001034569],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900582,0.0001509072,0.006202579,0.0004660609,0.00006510258,0.0002493574,0.00003946646,0.00007732966,0.002690964],"genre_scores_gemma":[0.993354,0.0000474067,0.006280183,0.00007263976,0.0000167613,0.0000309864,0.000001863426,0.00001188259,0.000184282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.129169,"threshold_uncertainty_score":0.684414,"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."}}