{"id":"W3134020311","doi":"10.48550/arxiv.2103.06331","title":"Face Images as Jigsaw Puzzles: Compositional Perception of Human Faces for Machines Using Generative Adversarial Networks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Jigsaw; Face (sociological concept); Perception; Generative grammar; Artificial intelligence; Adversarial system; Computer science; Computer vision; Facial recognition system; Machine learning; Pattern recognition (psychology); Psychology; Sociology; Social psychology","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":[0.0005742312,0.0005256244,0.0003213063,0.0002478453,0.0002347893,0.0006223571,0.000639625,0.0008244397,0.002446525],"category_scores_gemma":[0.0018775,0.0004012654,0.0004960768,0.0001702569,0.001203062,0.000886815,0.001412908,0.001447615,0.0003667771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005357969,"about_ca_system_score_gemma":0.000242411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000993529,"about_ca_topic_score_gemma":0.00100136,"domain_scores_codex":[0.9997936,0.00009317419,0.000004542717,0.0000439231,0.00004678016,0.00001793068],"domain_scores_gemma":[0.9995664,0.0002801837,0.00003983905,0.00006334505,0.00002610637,0.00002418955],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007635733,0.00002291151,0.0004363165,0.00004679326,0.00003846356,0.0001231403,0.0001412853,0.8997524,0.01133669,0.05723216,0.001648264,0.02914505],"study_design_scores_gemma":[0.000003598656,0.00001273538,0.00008269516,0.000005879047,0.000003177696,0.00002722852,0.000008155517,0.9734743,0.001040168,0.02472924,0.0006084254,0.000004330017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0215644,0.0001890316,0.974149,0.0004841579,0.00004436104,0.00002669119,0.00004312169,0.0002011381,0.003298017],"genre_scores_gemma":[0.8649592,0.0004336719,0.1262132,0.0003717258,0.00007023783,0.0001011951,0.0001259085,0.0001455389,0.007579258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002446525,"threshold_uncertainty_score":0.008184493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0661748536992891,"score_gpt":0.2308505866861828,"score_spread":0.1646757329868937,"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."}}