{"id":"W4392056957","doi":"10.21203/rs.3.rs-3970681/v1","title":"Emotion-Aware Face De-identification with Generative Adversarial Networks","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Face recognition and analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Calgary","keywords":"Adversarial system; Generative grammar; Identification (biology); Face (sociological concept); Computer science; Artificial intelligence; Cognitive science; Psychology; Linguistics; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009909038,0.0009992165,0.0009039871,0.0004101408,0.0003360058,0.0007161782,0.00128522,0.00126649,0.002933529],"category_scores_gemma":[0.002595688,0.000572567,0.0008804645,0.0003528172,0.0006264676,0.001028686,0.001942995,0.002263521,0.001856544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004614331,"about_ca_system_score_gemma":0.0004290379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001678645,"about_ca_topic_score_gemma":0.002753799,"domain_scores_codex":[0.9994049,0.0001853975,0.00001742834,0.0001675507,0.0001388222,0.00008598679],"domain_scores_gemma":[0.9990771,0.0005059617,0.00006577562,0.0001987142,0.0001174171,0.00003501802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003574317,0.0001542579,0.00100724,0.0001004875,0.0001478066,0.0001396011,0.00008886407,0.6081345,0.02970421,0.01357063,0.006356914,0.340238],"study_design_scores_gemma":[0.000002497703,0.00001205914,0.0001355034,0.000004401412,0.000007087979,0.00003582186,0.000004774718,0.9933321,0.00292627,0.003222202,0.0003124869,0.000004664899],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01307489,0.0002948752,0.9834759,0.0002732171,0.00008853828,0.00003394629,0.00008993658,0.0007629543,0.001905764],"genre_scores_gemma":[0.6944032,0.0005904343,0.2847911,0.000701632,0.0002101181,0.000156691,0.000780048,0.0003918559,0.01797504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002933529,"threshold_uncertainty_score":0.009813666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04827290496959803,"score_gpt":0.3655764144425613,"score_spread":0.3173035094729633,"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."}}