{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000808752,0.0003604905,0.0003703654,0.0002617034,0.000178577,0.0002235648,0.0015161,0.0003467198,0.00001005631],"category_scores_gemma":[0.0006496498,0.0003774247,0.0003732934,0.0006991789,0.0001298134,0.0003448372,0.001236735,0.0004455317,0.00007547957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004150484,"about_ca_system_score_gemma":0.0005423431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002957505,"about_ca_topic_score_gemma":0.0002661718,"domain_scores_codex":[0.9971839,0.0001303224,0.0004782385,0.001712911,0.0001402071,0.0003544902],"domain_scores_gemma":[0.9962796,0.0002990191,0.0002654689,0.001725078,0.001287868,0.0001429442],"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":[0.0001378496,0.0002589684,0.001271753,0.001402128,0.0002031664,0.00006273577,0.001025034,0.1420271,0.00054531,0.8060789,0.01224076,0.03474634],"study_design_scores_gemma":[0.0001526279,0.00004280461,0.001290299,0.00008746966,0.00005892078,0.00000282168,0.00006095688,0.6047421,0.0002774883,0.3915014,0.001441318,0.0003418079],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1547759,0.00008157733,0.8390756,0.003211653,0.0009624332,0.0008515595,0.0001707102,0.0004949123,0.0003757277],"genre_scores_gemma":[0.9745617,0.00003700714,0.02204135,0.0001643096,0.0001732111,0.00001311752,0.0001395878,0.00002011625,0.002849601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8197858,"threshold_uncertainty_score":0.9998678,"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."}}