{"id":"W2134653808","doi":"","title":"Modeling image patches with a directed hierarchy of Markov random fields","year":2007,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Inference; Markov random field; Hierarchy; Generative model; Markov chain; Generative grammar; Artificial intelligence; Hidden Markov model; Markov process; Layer (electronics); Image (mathematics); Variable-order Markov model; Markov model; Algorithm; Pattern recognition (psychology); Machine learning; Mathematics; Image segmentation; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004509052,0.0001111583,0.0001931447,0.00007333476,0.00006334714,0.00005092672,0.000316412,0.00004272399,0.00003615962],"category_scores_gemma":[0.00004088905,0.00007574898,0.00005790167,0.0003008149,0.0000416511,0.0003239934,0.00009061368,0.00008045561,0.000002686248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009140957,"about_ca_system_score_gemma":0.00003253908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002531636,"about_ca_topic_score_gemma":0.0001763459,"domain_scores_codex":[0.9990836,0.00004970876,0.0002135045,0.0002336351,0.0001844684,0.0002351221],"domain_scores_gemma":[0.9992665,0.0001700259,0.00004492174,0.0003034304,0.0001484755,0.00006663392],"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":[0.001957571,0.0006267833,0.002099147,0.0001088258,0.0005287409,0.0002036627,0.006411778,0.1122857,0.06374425,0.006346107,0.003760577,0.8019269],"study_design_scores_gemma":[0.0008134255,0.00007603104,0.0001918068,0.00001893591,0.000008063794,0.000003543381,0.0000562888,0.9548652,0.04331066,0.0004560188,0.00006353197,0.0001364521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02834703,0.0000544639,0.9621847,0.0002700705,0.00006965538,0.0001087753,5.41443e-7,0.00009673963,0.008868055],"genre_scores_gemma":[0.6608891,0.0000084241,0.3387712,0.00008599002,0.00003923459,0.00000202158,5.438086e-7,0.000004280196,0.0001992023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8425795,"threshold_uncertainty_score":0.3088953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009046311200374649,"score_gpt":0.2160018947225266,"score_spread":0.206955583522152,"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."}}