{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001605409,0.00005674826,0.00007487773,0.000005120852,0.00005727679,0.00000873708,0.00008799396,0.00007781696,0.00001041951],"category_scores_gemma":[0.000027497,0.00003053591,0.00003707426,0.00003832922,0.0001573035,4.951623e-7,0.0001008012,0.00004657708,4.086785e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001554988,"about_ca_system_score_gemma":0.00001046477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006354276,"about_ca_topic_score_gemma":0.00005109794,"domain_scores_codex":[0.9995829,0.00004854096,0.0001075081,0.0001388532,0.00003009282,0.00009213971],"domain_scores_gemma":[0.9998053,0.00002529699,0.00002095838,0.0001225631,0.000009417938,0.00001651982],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005783501,0.00006178309,0.01756065,0.00003153753,0.00007610801,5.906073e-7,0.00002730389,0.000006096862,0.7958629,0.1783119,0.001322173,0.006681058],"study_design_scores_gemma":[0.0005171577,0.0002638671,0.02688635,0.0000309901,0.00002995135,0.000006594171,0.0001819069,0.0002162264,0.6101766,0.00442692,0.3570542,0.00020932],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9118623,0.0004868956,0.001892222,0.001227311,0.00005886738,0.00008191354,0.000003534586,0.000009598279,0.08437737],"genre_scores_gemma":[0.9951257,0.000009192258,0.0001697452,0.004246505,0.0000427603,0.000001265463,0.000002532842,0.00000193952,0.0004003435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.355732,"threshold_uncertainty_score":0.1245218,"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."}}