{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002707243,0.0004609191,0.000634154,0.0002010445,0.0005258135,0.0002808687,0.001107599,0.0003403113,0.00007828546],"category_scores_gemma":[0.00003425636,0.0005207051,0.0004953953,0.0003695874,0.0002452318,0.0007416827,0.001266302,0.0003882877,0.000002914956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002113012,"about_ca_system_score_gemma":0.0002442408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005546458,"about_ca_topic_score_gemma":0.00007034117,"domain_scores_codex":[0.997472,0.0003920663,0.0003736737,0.0012297,0.0001481027,0.0003844043],"domain_scores_gemma":[0.9979016,0.0001848214,0.0005134833,0.0006934785,0.0005737922,0.0001328192],"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":[0.00004934695,0.0001114228,0.000222922,0.00005227682,0.0002409221,0.00003150789,0.0004649316,0.9798313,0.01278395,0.005582599,0.0002218659,0.0004069042],"study_design_scores_gemma":[0.0006993212,0.0001097035,0.0004115759,0.0001482734,0.0001804722,0.000005101023,0.0005491922,0.9906691,0.003083212,0.003602311,0.00002315526,0.0005185594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1654745,0.0001238043,0.8326862,0.00008073449,0.0007854343,0.0004868319,0.00008867903,0.00006488064,0.0002089119],"genre_scores_gemma":[0.957475,0.00009951246,0.0412837,0.00007470191,0.0005013279,0.000003235106,0.0002614466,0.00002573697,0.0002753278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7920005,"threshold_uncertainty_score":0.9997244,"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."}}