{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001389415,0.0008769291,0.000861116,0.001148935,0.0004013109,0.001084824,0.002096006,0.00117844,0.00459027],"category_scores_gemma":[0.004100219,0.0002631254,0.0008257484,0.0009892597,0.000431854,0.002031514,0.0006649715,0.001721001,0.001787259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001199594,"about_ca_system_score_gemma":0.0007493818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009666596,"about_ca_topic_score_gemma":0.01701599,"domain_scores_codex":[0.9992393,0.0002485646,0.00003581818,0.0002637057,0.0001335692,0.00007904753],"domain_scores_gemma":[0.9987699,0.0005539143,0.0001364482,0.0001275097,0.0003443849,0.00006778973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005439019,0.0008502347,0.007554788,0.0002678937,0.0003659432,0.0002404308,0.0002063572,0.3344356,0.008521521,0.01723447,0.01762055,0.6121583],"study_design_scores_gemma":[0.00001088416,0.0001011675,0.001430457,0.00001103529,0.0000316744,0.00004964683,0.00001519336,0.988936,0.001020528,0.007582322,0.000790693,0.00002044246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1765979,0.002134186,0.7933308,0.001598343,0.0005208164,0.0002671095,0.003146762,0.005080453,0.01732363],"genre_scores_gemma":[0.8746648,0.0003820382,0.1010566,0.0003812902,0.0002414665,0.0003092831,0.002777453,0.0001909334,0.01999609],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009666596,"threshold_uncertainty_score":0.01922065,"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."}}