{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002360402,0.0004952038,0.0005411575,0.001909216,0.0008280003,0.002365506,0.0009484477,0.0005858517,0.002281055],"category_scores_gemma":[0.007486379,0.0003098025,0.0008918096,0.002909106,0.0007588056,0.001925875,0.0007843031,0.0008386907,0.0005360242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001248418,"about_ca_system_score_gemma":0.001161172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01637367,"about_ca_topic_score_gemma":0.01273286,"domain_scores_codex":[0.9991685,0.0003528169,0.00004818153,0.000251315,0.0001100914,0.0000690599],"domain_scores_gemma":[0.9967884,0.002533666,0.0001345522,0.00020503,0.0002546034,0.00008373809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005134234,0.0002284608,0.04812582,0.0009781626,0.0005652776,0.0009605066,0.01129639,0.2371113,0.004115537,0.2872201,0.03088236,0.3780027],"study_design_scores_gemma":[0.00003534621,0.00003842265,0.01391006,0.00008738923,0.0001025593,0.0002291878,0.001237704,0.8777019,0.001390268,0.07961053,0.02560622,0.0000503768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3329178,0.005523936,0.6369173,0.003761322,0.0002610083,0.0003089148,0.004739705,0.001000684,0.01456926],"genre_scores_gemma":[0.8806245,0.002187632,0.1021218,0.0001800539,0.0003105627,0.0003958392,0.003586297,0.0001701401,0.01042324],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01637367,"threshold_uncertainty_score":0.03255671,"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."}}