{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002420207,0.0005081706,0.0004743959,0.001880524,0.001212531,0.00400865,0.000467019,0.0006890437,0.01338013],"category_scores_gemma":[0.02420524,0.0003375814,0.0005194135,0.002404186,0.002002414,0.006975264,0.004294997,0.001118591,0.0009007286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007200519,"about_ca_system_score_gemma":0.0004126468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002906518,"about_ca_topic_score_gemma":0.003523169,"domain_scores_codex":[0.9973854,0.001268097,0.0001900163,0.0006002805,0.0002243815,0.0003318238],"domain_scores_gemma":[0.9862127,0.006931038,0.002134049,0.003596912,0.000657066,0.0004681486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001070304,0.0002614328,0.4152344,0.0006338989,0.0008294757,0.0009405969,0.02970107,0.02700936,0.01404026,0.241716,0.008277794,0.2602854],"study_design_scores_gemma":[0.0001170476,0.0005061375,0.2924188,0.0005584423,0.0005956396,0.001785957,0.03369395,0.0667417,0.009463291,0.5344805,0.05941068,0.0002277886],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9346654,0.0004927738,0.03767307,0.002233279,0.0000542475,0.00002500419,0.001378608,0.000246747,0.02323092],"genre_scores_gemma":[0.9942263,0.0001081219,0.00406949,0.0001136412,0.00001449205,0.00001150918,0.0006308952,0.00004233015,0.0007832512],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01338013,"threshold_uncertainty_score":0.044761,"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."}}