{"id":"W4294300070","doi":"10.21428/594757db.8b7cd94b","title":"Quantifying French Document Complexity","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Contrast (vision); Task (project management); Natural language processing; Range (aeronautics); Linguistic sequence complexity; Artificial intelligence; Measure (data warehouse); Information retrieval; Linguistics; Data mining","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.0006487063,0.0001851765,0.0002329575,0.000095374,0.0002390968,0.0003878309,0.002116781,0.0001004433,0.00123949],"category_scores_gemma":[0.00002882905,0.0001796222,0.0001362246,0.0001819149,0.00005267245,0.0001795238,0.004578454,0.0005959143,0.00007596552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002222135,"about_ca_system_score_gemma":0.0001761785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001636433,"about_ca_topic_score_gemma":0.0002297001,"domain_scores_codex":[0.9979788,0.0001773716,0.0003468821,0.0008053049,0.0004619423,0.000229717],"domain_scores_gemma":[0.9977891,0.0000926682,0.0001562763,0.001827599,0.00005775957,0.00007655302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001150169,0.0001187715,0.001765229,0.0001142807,0.0000256712,0.000004394446,0.0011419,0.001118364,0.00005641644,0.965619,0.002865421,0.02716945],"study_design_scores_gemma":[0.0002304667,0.00007788025,0.1023854,0.00003534553,0.00001759159,0.00001197751,0.0001375882,0.07842498,0.0006457153,0.7239015,0.09311888,0.001012783],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01850465,0.0001379797,0.957716,0.004304319,0.001463164,0.0004612418,0.00001208964,0.0006192958,0.01678128],"genre_scores_gemma":[0.833555,0.0000176333,0.1649104,0.0003147272,0.00005081671,0.0001196205,0.00007471076,0.000007540347,0.0009495021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8150504,"threshold_uncertainty_score":0.9996735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1522546582994682,"score_gpt":0.346716417992687,"score_spread":0.1944617596932187,"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."}}