{"id":"W2224819922","doi":"","title":"Segmentation des corpus chronologiques : 143 ans de discours gouvernemental au Québec","year":2010,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","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":[0.004317048,0.0003685982,0.0002759759,0.0001682782,0.0009151248,0.0008641504,0.002007351,0.0003239091,0.0002181497],"category_scores_gemma":[0.001347018,0.0003911018,0.0001582774,0.0005885205,0.001240659,0.001262756,0.0008696334,0.000855687,0.00005203018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00103411,"about_ca_system_score_gemma":0.001874026,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1356877,"about_ca_topic_score_gemma":0.3943147,"domain_scores_codex":[0.9947549,0.002854045,0.0004828748,0.0007536925,0.0004235582,0.0007309639],"domain_scores_gemma":[0.9956473,0.0008958425,0.0004560614,0.001431993,0.001276213,0.0002925701],"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":[0.000008911165,0.0006280078,0.01501043,0.0001403113,0.00004461203,0.00001994047,0.04092682,0.000003266015,0.1087226,0.2551647,0.0008409897,0.5784895],"study_design_scores_gemma":[0.0006709307,0.000004765875,0.008225542,0.001412701,0.00006836779,0.0001792792,0.0007903793,0.01838768,0.9270744,0.02912552,0.01327461,0.000785781],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2833827,0.007315664,0.6659457,0.03388838,0.0005736677,0.0003708088,0.00003397759,0.0007348135,0.007754302],"genre_scores_gemma":[0.5387283,0.00030483,0.4516334,0.000162601,0.00004811475,0.00003859851,0.00004530472,0.0000290513,0.009009802],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8183519,"threshold_uncertainty_score":0.9998541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01085560157810038,"score_gpt":0.2507190383187914,"score_spread":0.239863436740691,"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."}}