{"id":"W4394842830","doi":"10.1515/cllt-2023-0028","title":"The distributional properties of long nominal compounds in scientific articles: an investigation based on the uniform information density hypothesis","year":2024,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Constant (computer programming); Scientific literature; Information transmission; Econometrics; Data science; Information retrieval; Mathematics; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.002158883,0.0001337207,0.0001322209,0.0001701995,0.0004678295,0.0006274836,0.0004570065,0.00004361197,0.000001191429],"category_scores_gemma":[0.008099127,0.0000808144,0.00004421234,0.0004756323,0.0006852428,0.00008789635,0.000101356,0.0001908807,0.000003847036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008680188,"about_ca_system_score_gemma":0.0002282792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003218299,"about_ca_topic_score_gemma":0.0000587313,"domain_scores_codex":[0.9987395,0.0001508708,0.0003918876,0.0002233322,0.0003086326,0.0001857777],"domain_scores_gemma":[0.9974768,0.001384372,0.0001353088,0.0004767134,0.0004670336,0.0000598082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003008232,0.00002660479,0.0007765244,0.00004893717,0.000008640644,0.000005562481,0.001000569,0.000219572,0.0002943409,0.9877283,0.00001583083,0.009845027],"study_design_scores_gemma":[0.00008966772,0.0000768133,0.003094169,0.0002685451,0.00002756149,0.000003387,0.0001108546,0.5625045,0.01044495,0.4221849,0.001045912,0.0001486952],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.488733,0.0004324335,0.5076927,0.0003275823,0.001136571,0.0004140519,0.00002729543,0.0002355636,0.0010008],"genre_scores_gemma":[0.9964358,0.00000678408,0.003307343,0.00007980612,0.0001133892,0.00001494786,0.00001165532,0.000006215166,0.00002405128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5655434,"threshold_uncertainty_score":0.9695996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02148689408851192,"score_gpt":0.2315409293294229,"score_spread":0.210054035240911,"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."}}