{"id":"W6967989515","doi":"10.5281/zenodo.11077480","title":"FR.POL.GEN: A repository for textual analysis of all 'general policy speeches' from the Fifth French Republic.","year":2024,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Scripting language; Annotation; Natural language; Knowledge base; Natural (archaeology); Digital humanities","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":[0.001109718,0.001397358,0.0007073969,0.007259231,0.0007064123,0.001703477,0.000905868,0.0009187427,0.08227085],"category_scores_gemma":[0.005948847,0.0007418395,0.0005724658,0.006182855,0.0004534612,0.001816337,0.001258231,0.0008198044,0.05841601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001256278,"about_ca_system_score_gemma":0.00232754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01923889,"about_ca_topic_score_gemma":0.02093063,"domain_scores_codex":[0.9989649,0.0002966,0.0001436014,0.0002105497,0.0003060341,0.00007829277],"domain_scores_gemma":[0.9962373,0.001843272,0.0003341185,0.0006627544,0.0007897229,0.0001327809],"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":[0.0004759248,0.00006686983,0.004444511,0.003559198,0.00009830016,0.0007207671,0.002585867,0.001240758,0.00933357,0.005144328,0.8044886,0.1678413],"study_design_scores_gemma":[0.00005496494,0.00003104394,0.0092524,0.000280864,0.00003081158,0.0003875291,0.0006507824,0.001169529,0.004208166,0.00157347,0.9822991,0.00006129414],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.004254749,0.0005802884,0.01128655,0.0002443678,0.0001016719,0.0001142093,0.9486945,0.02194173,0.01278196],"genre_scores_gemma":[0.01124706,0.0004541994,0.01388958,0.00008169232,0.00004541238,0.0003843289,0.9600573,0.005061626,0.008778787],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.08227085,"threshold_uncertainty_score":0.2752234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07004695761329054,"score_gpt":0.3470227756223349,"score_spread":0.2769758180090444,"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."}}