{"id":"W4402755500","doi":"","title":"McCATMuS : retours sur la production d'un méta-dataset multilingue et multiséculaire","year":2024,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00524358,0.004674617,0.002362089,0.005987784,0.002488598,0.004807215,0.005101916,0.003664224,0.01619678],"category_scores_gemma":[0.02464406,0.001813713,0.004359287,0.004840345,0.001056281,0.006123109,0.00483677,0.004222078,0.01435748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002299032,"about_ca_system_score_gemma":0.004442494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06311946,"about_ca_topic_score_gemma":0.1066936,"domain_scores_codex":[0.9935861,0.001667377,0.0005448071,0.001915228,0.001863104,0.00042326],"domain_scores_gemma":[0.9863786,0.005428326,0.0002645739,0.00380963,0.003256227,0.0008626995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00126774,0.0006745278,0.004764152,0.003149554,0.001418779,0.001248186,0.0007851599,0.01123628,0.0293225,0.005608634,0.754946,0.1855785],"study_design_scores_gemma":[0.00110337,0.0006297768,0.01893293,0.0009594337,0.001049811,0.001741557,0.002274112,0.2401387,0.05655596,0.01849181,0.6577501,0.0003723881],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.07476357,0.005103599,0.1826821,0.006362784,0.004485414,0.001377658,0.5249481,0.1854473,0.01482954],"genre_scores_gemma":[0.05156534,0.001030005,0.2438457,0.001036834,0.000244212,0.001098494,0.6793941,0.01370158,0.008083807],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.06311946,"threshold_uncertainty_score":0.1255041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01629570940677649,"score_gpt":0.2701629951961025,"score_spread":0.253867285789326,"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."}}