{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001518402,0.00004301501,0.00007775168,0.00001616779,0.0001445402,0.00002305605,0.00007292585,0.00006277349,0.001617019],"category_scores_gemma":[0.00006388341,0.00003530307,0.00006429926,0.0002278477,0.00005035786,0.0002853868,0.00002224176,0.00004180263,0.00002655291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006161466,"about_ca_system_score_gemma":0.00008210442,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01218603,"about_ca_topic_score_gemma":0.003070756,"domain_scores_codex":[0.9993279,0.00006829217,0.0001041361,0.0001169759,0.0002413755,0.0001413513],"domain_scores_gemma":[0.9996597,0.00001468727,0.00003419569,0.00009654996,0.0001507017,0.0000441264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002161934,0.0001350494,0.000818464,0.00005934574,0.00007217321,0.00002473399,0.3898143,0.0003269224,0.08387339,0.3693655,0.1260885,0.02939997],"study_design_scores_gemma":[0.001188992,0.00004156142,0.00243553,0.0002713458,0.0001290347,0.000009176365,0.7623359,0.011293,0.1161989,0.04735437,0.0579596,0.0007826132],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7827361,0.00509028,0.02057246,0.004871148,0.0005079271,0.0001568566,0.0000155767,0.0001614039,0.1858882],"genre_scores_gemma":[0.9825155,0.00007282547,0.0007456249,0.0008715105,0.0001266159,0.000001922223,0.000007651201,0.000003132075,0.01565528],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3725216,"threshold_uncertainty_score":0.9992957,"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."}}