{"id":"W4280645526","doi":"10.18653/v1/2022.findings-acl.164","title":"Richer Countries and Richer Representations","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Embedding; Space (punctuation); Vocabulary; Inequality; Computer science; Word lists by frequency; Word (group theory); Power (physics); Work (physics); Natural language processing; Artificial intelligence; Econometrics; Linguistics; Economics; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.000891786,0.00005997214,0.00009939229,0.00004533152,0.001554275,0.00005126692,0.000190222,0.00004146007,0.0002188199],"category_scores_gemma":[0.005064636,0.00005518659,0.00008133471,0.0002791864,0.00006393354,0.00004638763,0.0001153783,0.0001151013,0.000004157664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004429157,"about_ca_system_score_gemma":0.0001470305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003757215,"about_ca_topic_score_gemma":0.00007615402,"domain_scores_codex":[0.9987159,0.0001462653,0.0002043089,0.000137215,0.0006481102,0.0001481818],"domain_scores_gemma":[0.9983123,0.000684189,0.000310003,0.00006214724,0.0006032173,0.00002813005],"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":[0.00003792645,0.00008415717,0.1274022,0.00002385105,0.0001395494,4.087957e-7,0.01961311,0.01488893,0.00003665841,0.7263254,0.1113366,0.0001112754],"study_design_scores_gemma":[0.0007846461,0.00005572439,0.09726987,0.00001011489,0.0001374572,7.194755e-7,0.007958835,0.002779752,0.00003930155,0.1198013,0.7709326,0.0002296521],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7775388,0.002167087,0.002963116,0.04112996,0.01424376,0.004831013,0.004846826,0.0004462878,0.1518331],"genre_scores_gemma":[0.9815366,0.000008716802,0.0007078441,0.000421672,0.0003707726,0.00004840012,0.0001168099,0.000008200016,0.01678093],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.659596,"threshold_uncertainty_score":0.9997455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01130151103574686,"score_gpt":0.2913571103954506,"score_spread":0.2800555993597038,"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."}}