{"id":"W6968313569","doi":"10.5281/zenodo.14301374","title":"Vers une classification automatique de didascalies en français avec des grands modèles de langue","year":2024,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Domain (mathematical analysis); Context (archaeology); Field (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001692243,0.0002015934,0.000166485,0.0002558756,0.001611246,0.002505395,0.001306039,0.0001976455,0.00250635],"category_scores_gemma":[0.0007170236,0.0002221012,0.0001006706,0.001222531,0.0005013969,0.0009594873,0.0005499418,0.0004430512,0.005360479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006917481,"about_ca_system_score_gemma":0.00004277602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000814933,"about_ca_topic_score_gemma":0.00001755644,"domain_scores_codex":[0.997173,0.0009881163,0.000335579,0.0005940559,0.0003633848,0.0005459164],"domain_scores_gemma":[0.9985188,0.0001556194,0.00006808119,0.000627693,0.0003790469,0.0002507218],"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":[0.00002210972,0.0001726183,0.0000286578,0.0005769337,0.00006433651,0.00003388692,0.05916611,0.0004321389,0.008999671,0.2364332,0.03602703,0.6580433],"study_design_scores_gemma":[0.0001866794,0.0001361494,0.02773166,0.0002039558,0.00003043111,0.0002608501,0.000624704,0.1950549,0.0009475801,0.007869064,0.7667183,0.0002356899],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05619945,0.001861346,0.8689271,0.01721032,0.0003709908,0.0005044448,0.0002508568,0.002642414,0.05203307],"genre_scores_gemma":[0.9902802,0.0005109363,0.005288608,0.0001164999,0.0002177495,2.547378e-7,0.0004450756,0.0005859245,0.002554737],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9340808,"threshold_uncertainty_score":0.9996885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04214523564787754,"score_gpt":0.2657347261294624,"score_spread":0.2235894904815848,"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."}}