{"id":"W3004478131","doi":"10.22148/001c.11882","title":"Topic Modeling the Hàn diăn Ancient Classics (汉典古籍)","year":2017,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"College of Humanities and Social Sciences, United Arab Emirates University; Xi’an Jiaotong University; National Endowment for the Humanities","keywords":"Pinyin; Pronunciation; Topic model; 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":[0.001455591,0.00007722439,0.0001982677,0.00003809879,0.001503642,0.0004604319,0.000652978,0.00004635432,0.00005583189],"category_scores_gemma":[0.0008231798,0.00004007177,0.0002991326,0.0001252339,0.0002045401,0.0003887159,0.00006125173,0.000226364,0.000006631648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008901495,"about_ca_system_score_gemma":0.0001472437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001889809,"about_ca_topic_score_gemma":0.000413618,"domain_scores_codex":[0.9985998,0.000141235,0.0003555294,0.00007797447,0.0006517863,0.0001736299],"domain_scores_gemma":[0.9983306,0.0001214727,0.0005386642,0.000162984,0.0007348202,0.0001114831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001052351,0.000391124,0.02890623,0.00003550165,0.001442871,0.0001446892,0.0554087,0.3216767,0.0006908217,0.3114704,0.02102486,0.2587028],"study_design_scores_gemma":[0.0007405771,0.0001166332,0.01991513,0.0001058499,0.0007741136,0.00003724411,0.01902127,0.5737813,0.00006901726,0.09536629,0.2896356,0.0004369963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8995827,0.0006862548,0.0378389,0.03716088,0.001299613,0.00008654252,0.000001841663,0.00001289114,0.02333033],"genre_scores_gemma":[0.9929696,0.0002116014,0.002257387,0.0002467601,0.001225208,2.693019e-7,4.125116e-7,0.000002818075,0.00308594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2686107,"threshold_uncertainty_score":0.9997963,"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."}}