{"id":"W6910578118","doi":"10.48448/nqav-4054","title":"A Neural Pairwise Ranking Model for Readability Assessment","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Toronto","funders":"","keywords":"Readability; Pairwise comparison; Ranking (information retrieval); Task (project management); Benchmark (surveying); Reading (process); Artificial neural network","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00421375,0.0005516206,0.0006032531,0.001093962,0.0007654808,0.0002375576,0.002015736,0.0001675031,0.00294542],"category_scores_gemma":[0.0004233319,0.0005209944,0.0002056223,0.001485847,0.0009669221,0.0003238274,0.0008551707,0.0006359851,0.0001088121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002030524,"about_ca_system_score_gemma":0.002717604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002513427,"about_ca_topic_score_gemma":0.0009573181,"domain_scores_codex":[0.9943117,0.0001472241,0.000543486,0.001743006,0.002138879,0.001115662],"domain_scores_gemma":[0.9972093,0.0001558491,0.0005706331,0.001574843,0.0002123043,0.000277139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000155036,0.001482213,0.002339391,0.0005001159,0.0001347147,0.00002599638,0.000707794,0.09600295,0.004193514,0.01917133,0.8406503,0.03463669],"study_design_scores_gemma":[0.0005043158,0.0001099873,0.00004843689,0.00003308857,0.00006734639,0.000005446373,0.0001571884,0.9255094,0.00001128049,0.002594155,0.07038167,0.0005776873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.002400139,0.0006694024,0.2093564,0.002922523,0.00378564,0.01282718,0.007439845,0.005999622,0.7545992],"genre_scores_gemma":[0.2406102,0.00001221312,0.2911443,0.00112414,0.0008683481,0.001628808,0.001083993,0.003211667,0.4603163],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8295065,"threshold_uncertainty_score":0.9997241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05689957135663417,"score_gpt":0.3652027872376594,"score_spread":0.3083032158810253,"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."}}