{"id":"W4366068401","doi":"10.2139/ssrn.4419855","title":"Maskrenderer: 3d-Infused Multi-Mask Realistic Face Reenactment","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Face (sociological concept); Computer science; Computer graphics (images); Computer vision; Artificial intelligence; Sociology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002453192,0.0005267888,0.0006374582,0.0006134408,0.0003554846,0.0006388808,0.002203377,0.0003464217,0.00004317816],"category_scores_gemma":[0.000165706,0.0004830678,0.0006061574,0.0005662858,0.00005160203,0.0002484092,0.001090686,0.005443748,0.0006212179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002141177,"about_ca_system_score_gemma":0.003984809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003114268,"about_ca_topic_score_gemma":0.001541383,"domain_scores_codex":[0.9939975,0.0003339123,0.0007792834,0.0009457993,0.0008580342,0.003085496],"domain_scores_gemma":[0.9976974,0.0001214878,0.000648912,0.001026972,0.000212886,0.0002923018],"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":[0.0001065712,0.00164536,0.0008603972,0.0004247546,0.010086,0.0006828118,0.004207962,0.06611646,0.0005847907,0.1935133,0.007936091,0.7138355],"study_design_scores_gemma":[0.00284086,0.0004201308,0.0004658357,0.0005248179,0.0005925071,0.0007117702,0.002137013,0.4974194,0.0001608783,0.4876835,0.00490206,0.002141214],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001125455,0.002012283,0.9897889,0.004867065,0.001053474,0.0002725939,0.00002829427,0.0005046483,0.0003472771],"genre_scores_gemma":[0.836142,0.07650542,0.04209638,0.0009484024,0.001219738,0.0001477085,0.0002867013,0.0002626224,0.042391],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9476925,"threshold_uncertainty_score":0.9997621,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04179961296173216,"score_gpt":0.2876117978307977,"score_spread":0.2458121848690655,"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."}}