{"id":"W2332964166","doi":"10.1515/cllt-2013-0014","title":"Topic marking in a Shanghainese corpus: from observation to prediction","year":2013,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Polytomous Rasch model; Computer science; Natural language processing; Logistic regression; Artificial intelligence; Multivariate statistics; Selection (genetic algorithm); Computational linguistics; Machine learning; Statistics; Item response theory; Mathematics; Psychometrics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001063074,0.0001877822,0.0002728918,0.0001907978,0.0003248224,0.0001587412,0.0002216078,0.0001908697,0.0005658868],"category_scores_gemma":[0.0581192,0.0001968875,0.00004101362,0.0002904916,0.000156055,0.0000205057,0.00009209584,0.0002161555,0.00008095481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001474784,"about_ca_system_score_gemma":0.000186028,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01306833,"about_ca_topic_score_gemma":0.002140486,"domain_scores_codex":[0.9981308,0.0002864179,0.0004781744,0.0004304127,0.0002603292,0.0004138913],"domain_scores_gemma":[0.9974669,0.00121275,0.0001496171,0.0002571269,0.0006386986,0.0002749652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004520667,0.00006711382,0.06143383,0.00001648189,0.00001768125,0.00003138944,0.01568255,0.00001597955,0.0001352327,0.9117686,0.0003930829,0.01039286],"study_design_scores_gemma":[0.0007503488,0.00008653333,0.126793,0.0001448779,0.0000540501,0.000001269925,0.001672223,0.001515228,0.00001984796,0.6081796,0.2604068,0.0003762263],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7398633,0.001288996,0.01722381,0.001006655,0.02291995,0.002202619,0.0001674533,0.0005156207,0.2148115],"genre_scores_gemma":[0.9879003,0.00008918421,0.004261798,0.001112585,0.004843429,0.00007000991,0.00005237212,0.0000252884,0.001645015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.303589,"threshold_uncertainty_score":0.9935037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02289286924627669,"score_gpt":0.2744754931635357,"score_spread":0.251582623917259,"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."}}