{"id":"W2593276484","doi":"10.22148/16.016","title":"Topic Modeling the Hàn diăn Ancient Classics","year":2017,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pinyin; Topic model; Pronunciation; Linguistics; Computer science; History; Natural language processing; Artificial intelligence; Chinese characters; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001319069,0.00006815958,0.0001761646,0.00003466016,0.001435074,0.0004254913,0.0006044455,0.00004085078,0.00005004725],"category_scores_gemma":[0.0007738468,0.000034962,0.0002705012,0.0001112466,0.0001853673,0.0003605428,0.000054539,0.000203509,0.000005857129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000764216,"about_ca_system_score_gemma":0.0001330459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000169159,"about_ca_topic_score_gemma":0.0003750077,"domain_scores_codex":[0.9987407,0.000124276,0.0003165121,0.00006792362,0.0005951392,0.0001554152],"domain_scores_gemma":[0.9984744,0.0001108397,0.0004910479,0.0001454762,0.0006783881,0.00009985106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009004735,0.0003372543,0.02641812,0.00003002636,0.001288899,0.0001267756,0.05581943,0.321116,0.0005980571,0.3245305,0.02052854,0.2491163],"study_design_scores_gemma":[0.0006736052,0.0001061344,0.0178511,0.00009472096,0.0006922308,0.00003331045,0.01846693,0.5675534,0.00005883458,0.09311102,0.3009696,0.0003891572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8986989,0.0006660022,0.03881774,0.03675672,0.001253313,0.00007800573,0.000001523036,0.00001156851,0.02371618],"genre_scores_gemma":[0.9932456,0.0002020364,0.002188646,0.0002263789,0.001157198,2.209622e-7,3.268915e-7,0.000002454441,0.002977112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.280441,"threshold_uncertainty_score":0.9998649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1623321213294615,"score_gpt":0.4360665115014897,"score_spread":0.2737343901720282,"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."}}