{"id":"W2134862753","doi":"10.1007/978-3-540-87536-9_99","title":"Analysis-by-Synthesis by Learning to Invert Generative Black Boxes","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Face recognition and analysis","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Computer science; Generative model; Artificial neural network; Set (abstract data type); Artificial intelligence; Black box; Graphics; Generative Design; Machine learning; Computer graphics (images); Compatibility (geochemistry); Programming language","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":[0.0006042456,0.0006305847,0.000927808,0.001838053,0.0004597889,0.0006816445,0.002674261,0.0003035864,0.0001509711],"category_scores_gemma":[0.0001876787,0.0005836805,0.0004046106,0.002492203,0.0006061679,0.0005111566,0.0009101898,0.0007858895,0.0003292873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002906066,"about_ca_system_score_gemma":0.0002703532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006560119,"about_ca_topic_score_gemma":0.0001155274,"domain_scores_codex":[0.9953352,0.00011018,0.0005794333,0.00201625,0.001242629,0.0007162677],"domain_scores_gemma":[0.9974604,0.000554355,0.0002955788,0.0009749752,0.0003259853,0.0003886726],"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":[0.000006045513,0.00007474894,0.000260879,0.00001972196,0.0004240152,0.0000772179,0.002907581,0.2232686,0.001470635,0.0002704478,0.006485856,0.7647343],"study_design_scores_gemma":[0.0001311112,0.0001210519,0.00003531558,0.0001108799,0.0001262401,0.00001325618,0.000001033868,0.9698281,0.01079961,0.00167149,0.01604412,0.001117826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002776553,0.0004268433,0.9944002,0.002079834,0.000239409,0.0002020154,0.00002097665,0.0001686768,0.002184385],"genre_scores_gemma":[0.3696863,0.001789248,0.5947721,0.01861604,0.0007467992,0.00007852588,0.0001290252,0.0001476422,0.0140343],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7636164,"threshold_uncertainty_score":0.9996614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01524933951670038,"score_gpt":0.2336942533400051,"score_spread":0.2184449138233047,"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."}}