{"id":"W3162708316","doi":"10.31234/osf.io/d2h5c","title":"Why is scaling up models of language evolution hard?","year":2021,"lang":"en","type":"article","venue":"","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Koninklijke Nederlandse Akademie van Wetenschappen; Lorentz Center; Netherlands Institute for Advanced Study in the Humanities and Social Sciences","keywords":"Artifact (error); Computer science; Scaling; Computational model; Face (sociological concept); Scale (ratio); Artificial intelligence; Resource (disambiguation); Computational complexity theory; Theoretical computer science; Algorithm; Mathematics; Sociology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.005126934,0.0009164041,0.002139601,0.001060351,0.001844183,0.004281082,0.002903464,0.003527261,0.007939263],"category_scores_gemma":[0.04853579,0.001214106,0.001653612,0.001119792,0.004219663,0.01400384,0.003505267,0.005621451,0.001209368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001742938,"about_ca_system_score_gemma":0.001135934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003772826,"about_ca_topic_score_gemma":0.002010903,"domain_scores_codex":[0.9976459,0.001078555,0.0001377955,0.0005336261,0.0003718604,0.0002321388],"domain_scores_gemma":[0.9751673,0.01646462,0.001387837,0.004653858,0.001218591,0.00110778],"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":[0.0001036089,0.0001339462,0.004275416,0.0003736861,0.0002348297,0.0004057914,0.0008961482,0.2621561,0.000871772,0.6926252,0.01144121,0.02648237],"study_design_scores_gemma":[0.00003520008,0.00001688701,0.0003439754,0.00002669863,0.00001599232,0.00005603486,0.0001013991,0.1643318,0.00009036607,0.8327193,0.002245681,0.00001672441],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3638387,0.004506247,0.4506375,0.09220318,0.001110577,0.0002811773,0.001119286,0.002496847,0.08380656],"genre_scores_gemma":[0.9242657,0.001834397,0.06246005,0.003153662,0.0006007595,0.0006128756,0.0005322876,0.000567199,0.005972981],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007939263,"threshold_uncertainty_score":0.02711415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0274771200073386,"score_gpt":0.2972865535372728,"score_spread":0.2698094335299342,"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."}}