{"id":"W4411113401","doi":"10.18653/v1/2025.cmcl-1.11","title":"Unzipping the Causality of Zipf’s Law and Other Lexical Trade-offs","year":2025,"lang":"en","type":"article","venue":"","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Zipf's law; Causality (physics); Computer science; Artificial intelligence; Mathematics; Statistics","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":[0.01653881,0.0007777954,0.001222236,0.004177159,0.001979011,0.003383695,0.001228031,0.001122719,0.008434357],"category_scores_gemma":[0.1130122,0.0008342639,0.001617943,0.004023758,0.006323673,0.009296617,0.003288136,0.003220932,0.0005424967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001859353,"about_ca_system_score_gemma":0.001549111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003981527,"about_ca_topic_score_gemma":0.002951684,"domain_scores_codex":[0.9934662,0.003039277,0.0004124074,0.001762397,0.0009958037,0.0003240081],"domain_scores_gemma":[0.851687,0.1261962,0.008634389,0.009635095,0.003030557,0.0008167932],"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":[0.0006073811,0.0001759542,0.1592174,0.0008135404,0.0007936394,0.001244256,0.002146238,0.02874402,0.003550905,0.6090764,0.005342617,0.1882877],"study_design_scores_gemma":[0.00007963178,0.00006804548,0.02150536,0.00005874284,0.0001429885,0.0003924716,0.0003451549,0.09363612,0.001915966,0.8775343,0.004246338,0.00007493752],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2807299,0.002573666,0.6971003,0.00544848,0.0002652411,0.0002721442,0.00131947,0.001022343,0.01126853],"genre_scores_gemma":[0.9286494,0.0007001624,0.06710467,0.0008242231,0.0002009967,0.0002476889,0.0004871943,0.0001880747,0.001597576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01653881,"threshold_uncertainty_score":0.08746666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01874921092364341,"score_gpt":0.2815976880776964,"score_spread":0.262848477154053,"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."}}