{"id":"W3215741750","doi":"10.3917/lang.224.0025","title":"Élaboration du corpus DEMOCRAT : procédures d’annotation et d’évaluation","year":2021,"lang":"fr","type":"article","venue":"Langages","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Agence Nationale de la Recherche","keywords":"Humanities; Philosophy; Annotation; Computer science; Artificial intelligence","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":[0.03203797,0.001899926,0.001440478,0.010458,0.006172984,0.008993933,0.002215652,0.002283897,0.02729891],"category_scores_gemma":[0.08235225,0.001933368,0.001256074,0.007714185,0.003763674,0.005811506,0.00825168,0.004703881,0.01555153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004062313,"about_ca_system_score_gemma":0.01315415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01667792,"about_ca_topic_score_gemma":0.02403975,"domain_scores_codex":[0.9559922,0.02321688,0.004082518,0.005889989,0.009945325,0.0008730611],"domain_scores_gemma":[0.9128745,0.03566615,0.002430482,0.01932777,0.02857809,0.001123136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00136134,0.0004113937,0.007186355,0.003973367,0.000303774,0.0007902183,0.03655285,0.004234856,0.09164131,0.1274306,0.1651489,0.560965],"study_design_scores_gemma":[0.0001965456,0.0001455868,0.01109114,0.0008787201,0.0001187208,0.0006392843,0.00612578,0.01408828,0.06318909,0.02730692,0.8758903,0.0003297063],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04634366,0.001686388,0.765842,0.004209538,0.00207663,0.006326694,0.03270872,0.01898105,0.1218253],"genre_scores_gemma":[0.08026762,0.0006273214,0.8221726,0.0006648197,0.0003293065,0.01616612,0.03131067,0.01173199,0.03672959],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03203797,"threshold_uncertainty_score":0.169435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04037754227829086,"score_gpt":0.2941102141943758,"score_spread":0.253732671916085,"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."}}