{"id":"W2077469553","doi":"10.3366/cor.2013.0032","title":"Challenges in cross-linguistic corpus-assisted discourse studies","year":2013,"lang":"en","type":"article","venue":"Corpora","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Corpus linguistics; Linguistics; Focus (optics); Population; Contrastive linguistics; Sociology; Applied linguistics; Computer science; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002251501,0.000245854,0.0004615175,0.0001799203,0.0002522221,0.0002220934,0.0002581875,0.0000355537,0.00140269],"category_scores_gemma":[0.0003338585,0.0001884954,0.0001165321,0.00006416628,0.001090706,0.0002632877,0.0001509522,0.0001568134,0.000650552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000565032,"about_ca_system_score_gemma":0.00002354874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003805762,"about_ca_topic_score_gemma":0.007979228,"domain_scores_codex":[0.9985762,0.00006013302,0.0003992026,0.0003687674,0.0002423386,0.0003533808],"domain_scores_gemma":[0.9988181,0.0001593648,0.000190622,0.0004167148,0.000357811,0.00005738325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002585826,0.0005823436,0.01693403,0.000287393,0.0009300514,0.000290093,0.2125735,0.00002750118,0.0000398951,0.663621,0.009843783,0.0948446],"study_design_scores_gemma":[0.002366269,0.0003627235,0.1413468,0.0009097179,0.0005280799,0.00002059908,0.6324573,0.0002793915,0.00007503039,0.1143115,0.1052758,0.002066715],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.574764,0.05125159,0.000002966958,0.001828314,0.001638457,0.0003835262,0.00001754946,0.0001816742,0.3699319],"genre_scores_gemma":[0.9868029,0.001517536,0.00005357976,0.0001411968,0.0007719068,0.0001383589,0.00001116954,0.000029104,0.0105343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5493095,"threshold_uncertainty_score":0.9995102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.16594680154034,"score_gpt":0.363258996867498,"score_spread":0.1973121953271579,"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."}}