{"id":"W4403444399","doi":"10.48550/arxiv.2410.08674","title":"Guidelines for Fine-grained Sentence-level Arabic Readability Annotation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Zayed University; York University; New York University Abu Dhabi","keywords":"Readability; Annotation; Arabic; Sentence; Natural language processing; Computer science; Linguistics; Artificial intelligence; Programming language; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02291179,0.002016073,0.001194646,0.0103911,0.002837778,0.003847693,0.00290016,0.001948977,0.0183381],"category_scores_gemma":[0.08934203,0.0009857364,0.0008958226,0.004350496,0.001801578,0.004347072,0.005951524,0.003219631,0.01968916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001960084,"about_ca_system_score_gemma":0.004561285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005658363,"about_ca_topic_score_gemma":0.00958447,"domain_scores_codex":[0.9804516,0.009191046,0.004061545,0.002396491,0.003333382,0.0005658366],"domain_scores_gemma":[0.8610803,0.03554004,0.00458583,0.01343907,0.08330847,0.002046201],"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":[0.0006374126,0.0004914178,0.01265015,0.006452464,0.0001275297,0.001035337,0.02727277,0.00481016,0.1078139,0.02284101,0.3089619,0.5069058],"study_design_scores_gemma":[0.0002067277,0.0003208572,0.03742879,0.003681046,0.0001783675,0.001296997,0.008799078,0.03256203,0.0849557,0.03214762,0.7978855,0.0005372596],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06681377,0.002529868,0.7312791,0.004772116,0.001801487,0.009730067,0.05147569,0.03592562,0.09567232],"genre_scores_gemma":[0.1037214,0.0008352846,0.7649255,0.001163172,0.00043749,0.01728217,0.08458918,0.00986349,0.01718226],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02291179,"threshold_uncertainty_score":0.1211706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3015222385074146,"score_gpt":0.2694105302271697,"score_spread":0.0321117082802449,"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."}}