{"id":"W4392913259","doi":"10.1111/cogs.13424","title":"Recursive Numeral Systems Optimize the Trade‐off Between Lexicon Size and Average Morphosyntactic Complexity","year":2022,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Seventh Framework Programme; Azrieli Foundation; Tel Aviv University; École Normale Supérieure","keywords":"Lexicon; Numeral system; Computer science; Semantics (computer science); Natural language processing; Linguistics; Artificial intelligence; Domain (mathematical analysis); Simple (philosophy); Variation (astronomy); Principle of compositionality; Mathematics; Programming language","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":[0.001640305,0.0001981969,0.000232533,0.000126972,0.001930815,0.0007083821,0.002075678,0.00003265045,0.00002583538],"category_scores_gemma":[0.0007449058,0.0001511184,0.00004701755,0.001390781,0.001323587,0.001138918,0.001482198,0.0005831131,0.000005162508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001757774,"about_ca_system_score_gemma":0.0003000845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008464534,"about_ca_topic_score_gemma":0.000001371655,"domain_scores_codex":[0.9973556,0.0003290914,0.0002298071,0.0007645362,0.0008348865,0.0004861094],"domain_scores_gemma":[0.9980516,0.001021248,0.0002120103,0.0004009401,0.0001676917,0.000146463],"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":[0.0002265352,0.0005108884,0.007126121,0.0002325615,0.0001926639,0.0007021806,0.03725831,0.000306611,0.02587104,0.6341496,0.002090559,0.291333],"study_design_scores_gemma":[0.005575586,0.003624185,0.07156169,0.00108126,0.0003299185,0.003638101,0.01348325,0.2158123,0.1137053,0.5598167,0.005596167,0.005775656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2150837,0.0123382,0.7462078,0.01646207,0.001889005,0.002989058,0.0002681811,0.001492967,0.003268952],"genre_scores_gemma":[0.9738066,0.00001509039,0.02519732,0.0007339722,0.00005766413,0.00008301237,0.00000293506,0.00000948244,0.00009397927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7587228,"threshold_uncertainty_score":0.9993685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03155150480088137,"score_gpt":0.2884835817107361,"score_spread":0.2569320769098547,"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."}}