{"id":"W6893565298","doi":"10.5281/zenodo.3997149","title":"News Corpus for RUSSE'2020 task","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Task (project management); Corpus linguistics; Key (lock); Headline","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003422713,0.0001144647,0.0001284362,0.0000595765,0.001212334,0.0009647197,0.001759847,0.00005303933,0.0008053836],"category_scores_gemma":[0.0007656399,0.0001196505,0.0000626074,0.0005947437,0.00007535651,0.0004485194,0.0008759959,0.0001551382,0.003728333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006652005,"about_ca_system_score_gemma":0.000006442218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007920408,"about_ca_topic_score_gemma":2.543292e-7,"domain_scores_codex":[0.9985132,0.000164118,0.0002355749,0.0005343292,0.0002637391,0.0002890227],"domain_scores_gemma":[0.9987331,0.00004317797,0.0000928933,0.0005321759,0.0003545264,0.0002441231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007455149,0.0001334114,0.000007673281,0.0001041629,0.00002841401,0.000006786834,0.003724004,0.0001075021,0.01608267,0.09151959,0.3151725,0.5730388],"study_design_scores_gemma":[0.0003386367,0.0002684603,0.0003404691,0.000005215979,0.000004952821,0.00002459809,0.00008232515,0.009813981,0.0008254721,0.001181506,0.9869713,0.0001431027],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004935573,0.00007540947,0.9501357,0.02214768,0.0001408248,0.0008621454,0.000148485,0.001732075,0.01982213],"genre_scores_gemma":[0.9851235,0.00006023689,0.01013315,0.002240867,0.0003707844,1.996074e-7,0.0008786668,0.0007789093,0.000413675],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.980188,"threshold_uncertainty_score":0.9970474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04795015764437081,"score_gpt":0.2435366356435991,"score_spread":0.1955864779992283,"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."}}