{"id":"W4293797358","doi":"10.48550/arxiv.2208.12924","title":"Quantifying French Document Complexity","year":2022,"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":"","keywords":"Computer science; Contrast (vision); Task (project management); Natural language processing; Range (aeronautics); Linguistic sequence complexity; Measure (data warehouse); Artificial intelligence; Information retrieval; Linguistics; Data mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0004754916,0.0002568368,0.0002903471,0.0001944243,0.0003959594,0.0001915915,0.002627956,0.0001565775,0.0003546221],"category_scores_gemma":[0.00002835507,0.0003172552,0.0002173694,0.000561317,0.0001299168,0.000376407,0.003871997,0.000729159,0.00008986478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004963443,"about_ca_system_score_gemma":0.0002184019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001050177,"about_ca_topic_score_gemma":0.0001480943,"domain_scores_codex":[0.9977171,0.0002890218,0.0002365439,0.001275827,0.0001578498,0.0003235965],"domain_scores_gemma":[0.9974341,0.0001190932,0.0002534823,0.001960821,0.00009424497,0.0001382038],"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":[0.000007805931,0.0001449412,0.006267187,0.00009264826,0.00005335443,0.00008576948,0.0005844794,0.06947617,0.00003594806,0.9214063,0.000415513,0.001429908],"study_design_scores_gemma":[0.0004826821,0.00009193001,0.04027439,0.00004779858,0.00006507084,0.000007866683,0.0001969885,0.4142307,0.0001938649,0.5324771,0.01092496,0.001006601],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2784652,0.00005642548,0.7155898,0.0003846307,0.0008291082,0.0003598784,0.0000226865,0.0004049051,0.003887339],"genre_scores_gemma":[0.9942505,0.00005029094,0.004626418,0.00008941416,0.00003613368,0.000002721051,0.00005215114,0.000009858536,0.000882491],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7157853,"threshold_uncertainty_score":0.9999279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2211808650180716,"score_gpt":0.2390983731331629,"score_spread":0.01791750811509135,"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."}}