{"id":"W4405077419","doi":"10.1075/scl.118.09mil","title":"Modeling fine-grained sociolinguistic variation","year":2024,"lang":"en","type":"book-chapter","venue":"Studies in corpus linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Variation (astronomy); Computer science; Linguistics; Astrophysics; Physics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005430107,0.0005846664,0.0007333011,0.0004793088,0.0001656362,0.0001701434,0.00108469,0.0004495172,0.000004626012],"category_scores_gemma":[0.007214483,0.0005577249,0.0001648448,0.000164498,0.0001700509,0.00003373784,0.001191597,0.001206819,0.00006477448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005516561,"about_ca_system_score_gemma":0.0002211767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003064601,"about_ca_topic_score_gemma":0.00007600863,"domain_scores_codex":[0.9973099,0.00001958779,0.0008055975,0.0009245004,0.000520368,0.0004200984],"domain_scores_gemma":[0.997212,0.0004099994,0.000249416,0.0007691456,0.001296475,0.00006296708],"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":[0.000004432369,0.000008669983,7.377049e-7,0.0004953811,0.000112988,0.0005061615,0.00189718,0.0003319981,0.000002921736,0.9939799,0.0006573526,0.002002319],"study_design_scores_gemma":[0.00009453337,0.00004521785,7.093905e-8,0.001536756,0.00008629936,0.00001028563,0.000009869757,0.135044,0.000008369087,0.8464957,0.01615477,0.0005141268],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002604674,0.181076,0.4077255,0.0002970482,0.0192116,0.0007152049,0.0000697275,0.00284456,0.3880578],"genre_scores_gemma":[0.05706815,0.004320861,0.7210215,0.0004128872,0.008390671,0.0000741137,0.00006396321,0.0002838105,0.2083641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.313296,"threshold_uncertainty_score":0.9996874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05598935463493161,"score_gpt":0.3361349588186589,"score_spread":0.2801456041837273,"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."}}