{"id":"W3029996834","doi":"","title":"Corpus of Chinese Dynastic Histories: Gender Analysis over Two Millennia.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Chinese history and philosophy","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Lexicon; Computer science; Dominance (genetics); License; Focus (optics); Semantics (computer science); Linguistics; Natural language processing; History; Classical Chinese; Space (punctuation); Corpus linguistics; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001047969,0.0004037064,0.0003172462,0.007342028,0.001881488,0.0008396843,0.0006932876,0.0003010491,0.01098729],"category_scores_gemma":[0.005107099,0.0001640052,0.0001551563,0.01444851,0.0007114673,0.001120226,0.001684008,0.0004161498,0.001835542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002408003,"about_ca_system_score_gemma":0.006122392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1148642,"about_ca_topic_score_gemma":0.1620353,"domain_scores_codex":[0.9995894,0.0000840613,0.0000580987,0.00008718431,0.0001201457,0.00006108245],"domain_scores_gemma":[0.9971975,0.001018547,0.0002970941,0.0003099107,0.0008871655,0.0002897708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007947475,0.0001477549,0.1401307,0.004805839,0.0001476953,0.003021221,0.08201265,0.0006237265,0.00935282,0.0319869,0.3378414,0.3891346],"study_design_scores_gemma":[0.00002813734,0.000034289,0.4969927,0.0003981816,0.0001021866,0.0005510287,0.01212575,0.0006628698,0.002490754,0.001465825,0.4851079,0.00004044893],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.478618,0.007927224,0.003962149,0.002237449,0.0004688404,0.0003767746,0.4175583,0.0003756185,0.08847569],"genre_scores_gemma":[0.7250482,0.003032029,0.003477114,0.0002139477,0.0002002737,0.000973646,0.2365594,0.0002380946,0.03025736],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1148642,"threshold_uncertainty_score":0.2283912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03543237694785305,"score_gpt":0.3434333187503363,"score_spread":0.3080009418024832,"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."}}