{"id":"W1978265849","doi":"10.1108/00220410610688750","title":"Aggregation consistency and frequency of Chinese words and characters","year":2006,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Zipf's law; Consistency (knowledge bases); Syllable; Romanization; Vernacular; Distribution (mathematics); Frequency distribution; Set (abstract data type); Mathematics; Computer science; Econometrics; Natural language processing; Data set; Statistics; Linguistics; Artificial intelligence; Speech recognition","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":[0.0001999274,0.00005924199,0.0001350841,0.0001796965,0.00003074992,0.00005458682,0.00009164113,0.00002065742,0.000002876884],"category_scores_gemma":[0.0000276657,0.00004808492,0.00003222767,0.0001866994,0.00003850261,0.001562952,0.00002120227,0.00005197687,2.037441e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002607155,"about_ca_system_score_gemma":0.00001691749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003124856,"about_ca_topic_score_gemma":0.00001244811,"domain_scores_codex":[0.9993049,0.00003176427,0.0003579871,0.00007692782,0.0001754743,0.00005294403],"domain_scores_gemma":[0.9991432,0.00004396682,0.000593301,0.00007797989,0.0001168838,0.00002463713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002684843,0.0001488671,0.4935846,0.0000711653,0.00009765866,0.00002807583,0.002515829,0.00006309533,0.2505383,0.06395222,0.00007573554,0.1888975],"study_design_scores_gemma":[0.0009830666,0.0002876534,0.5857285,0.0001087095,0.00005335081,0.0001827057,0.0001103169,0.001217088,0.02738118,0.3837453,0.00002520599,0.0001769193],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.794077,0.000387229,0.2050634,0.000263213,0.00003291442,0.00004116852,2.660559e-7,0.000009367539,0.0001254419],"genre_scores_gemma":[0.9128029,0.0001133975,0.08700774,0.00002658239,0.00002806501,8.085792e-7,9.824826e-7,0.000002305514,0.00001721027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.319793,"threshold_uncertainty_score":0.1960846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004694726306288027,"score_gpt":0.2702126740971309,"score_spread":0.2655179477908429,"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."}}