{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001905119,0.0005308595,0.000663974,0.001177898,0.001004786,0.001059633,0.000732466,0.0002408644,0.000004244474],"category_scores_gemma":[0.002217568,0.0005175546,0.0002896803,0.01125957,0.0004322067,0.002035699,0.0005888543,0.0004080203,0.0001885259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001959174,"about_ca_system_score_gemma":0.0002438101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003899508,"about_ca_topic_score_gemma":0.00006210234,"domain_scores_codex":[0.9961233,0.0001698327,0.0008303126,0.001117929,0.0006148654,0.001143733],"domain_scores_gemma":[0.9958295,0.001618216,0.000549452,0.0006359878,0.001098778,0.0002680713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003827489,0.0007760703,0.07552622,0.004557101,0.002572463,0.0003623149,0.3308521,0.001688525,0.0004197644,0.06984183,0.01654378,0.4964771],"study_design_scores_gemma":[0.006007878,0.002411449,0.03131134,0.002450712,0.00001284361,0.0004835826,0.5941926,0.06132016,0.005166243,0.06433651,0.2278499,0.004456824],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3697467,0.01775166,0.5920789,0.01182052,0.004582336,0.00159883,0.0004316454,0.001028173,0.0009612758],"genre_scores_gemma":[0.9841831,0.002141993,0.0004169647,0.0001649935,0.0004128799,0.0003208283,0.0001965324,0.00006880142,0.01209392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6144364,"threshold_uncertainty_score":0.9999774,"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."}}