{"id":"W4324107265","doi":"10.16995/dscn.9665","title":"Zesting Up Stylometry with MapLemon: A Corpus for Stylometric Demographic Identification","year":2023,"lang":"fr","type":"article","venue":"Digital Studies / Le champ numérique","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Humanities; Corpus linguistics; Style (visual arts); Art; Linguistics; History; Literature; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003399469,0.0006549644,0.0005520544,0.01004299,0.002523077,0.002607096,0.001121632,0.0007442932,0.01660049],"category_scores_gemma":[0.01756575,0.0004592153,0.0003322354,0.009228521,0.001595057,0.00248338,0.004319855,0.001058802,0.006062399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001691521,"about_ca_system_score_gemma":0.003020323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01228241,"about_ca_topic_score_gemma":0.02529176,"domain_scores_codex":[0.9965527,0.001266786,0.0004723113,0.0007551527,0.0008198164,0.0001332025],"domain_scores_gemma":[0.9864,0.006045994,0.0007048527,0.002794146,0.003645445,0.0004095378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003803326,0.0001987855,0.02222007,0.003481266,0.00007835354,0.001114781,0.06624687,0.001661415,0.02410161,0.05029464,0.3235091,0.5067129],"study_design_scores_gemma":[0.00004893674,0.00004233886,0.05450741,0.0004900317,0.00002716357,0.0005769441,0.009626678,0.003094567,0.006719312,0.006378362,0.9183888,0.00009934336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2922014,0.003200113,0.1783111,0.002531253,0.001675176,0.00585723,0.3558317,0.006929582,0.1534625],"genre_scores_gemma":[0.3237216,0.001339105,0.3353523,0.0005882874,0.0003738245,0.01402913,0.2751502,0.003242171,0.04620337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01660049,"threshold_uncertainty_score":0.05553418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1062625220570823,"score_gpt":0.3247444777505745,"score_spread":0.2184819556934922,"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."}}