{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0305349,0.0004851091,0.0008497552,0.01079229,0.008220082,0.01705281,0.002524227,0.001516408,0.003623035],"category_scores_gemma":[0.06900091,0.0006797522,0.000409911,0.01872737,0.02519173,0.01459337,0.00748403,0.003258521,0.0006821401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009643812,"about_ca_system_score_gemma":0.01076526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02637169,"about_ca_topic_score_gemma":0.06029793,"domain_scores_codex":[0.9721552,0.02038111,0.001336823,0.002495441,0.002853852,0.0007776323],"domain_scores_gemma":[0.913328,0.05855126,0.005870966,0.01186674,0.008788533,0.001594476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001008201,0.00005876357,0.0155934,0.00102366,0.00006148322,0.001914673,0.6509972,0.0008073663,0.005734363,0.2228236,0.007671666,0.09321314],"study_design_scores_gemma":[0.0000125474,0.0000446954,0.01603125,0.00278891,0.00004621544,0.0007234684,0.550573,0.001474226,0.002781784,0.08142738,0.3439938,0.0001027598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4649866,0.01028039,0.2399205,0.04821584,0.00214458,0.001655468,0.004356107,0.0005088557,0.2279317],"genre_scores_gemma":[0.9060296,0.002464931,0.0839754,0.0009752479,0.0002540404,0.0006956959,0.001343764,0.0004104103,0.003850963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0305349,"threshold_uncertainty_score":0.1614859,"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."}}