{"id":"W1515378164","doi":"10.1111/lnc3.12103","title":"What Kind of Data is it? Situating Sociolinguistic Corpora in Context","year":2014,"lang":"en","type":"article","venue":"Language and Linguistics Compass","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorization; Context (archaeology); Computer science; Linguistics; Coding (social sciences); Data collection; Sociology; Data science; History; Artificial intelligence; Social science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001407429,0.000117476,0.000314962,0.00008606611,0.0001643012,0.00009425207,0.0003863009,0.0001231752,0.000200575],"category_scores_gemma":[0.01574052,0.0001218655,0.00002609955,0.0001337814,0.0002621627,0.00003940077,0.0001594721,0.0001771785,0.00001532247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002553254,"about_ca_system_score_gemma":0.0001199891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004886393,"about_ca_topic_score_gemma":0.00571761,"domain_scores_codex":[0.9985626,0.0002269962,0.000395608,0.0003064222,0.0002385449,0.0002697833],"domain_scores_gemma":[0.9981015,0.0009047716,0.0002391493,0.0003912433,0.0002573554,0.0001059559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003182878,0.0001446996,0.008686256,0.0001044874,0.00004092508,0.00007337304,0.3099644,0.000009547762,0.00008635301,0.6629177,0.003783947,0.01415648],"study_design_scores_gemma":[0.002770892,0.0001374241,0.00343782,0.0005431122,0.0001559614,0.000004863054,0.1955158,0.02302557,0.0001646876,0.02169821,0.7517572,0.0007884371],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5523235,0.005258395,0.01434612,0.009039818,0.0193055,0.001594374,0.0004377875,0.0003114375,0.3973831],"genre_scores_gemma":[0.9940333,0.0001106591,0.002223012,0.001536488,0.001581253,0.000002261304,0.00006904859,0.00001160096,0.0004324271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7479733,"threshold_uncertainty_score":0.9925503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07580123310037273,"score_gpt":0.3738781810605298,"score_spread":0.2980769479601571,"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."}}