{"id":"W2963489463","doi":"","title":"GibbsNet: Iterative Adversarial Inference for Deep Graphical Models","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Latent variable; Inference; Computer science; Joint probability distribution; Sampling (signal processing); Latent class model; Graphical model; Conditional probability distribution; Algorithm; Variable (mathematics); Artificial intelligence; Gibbs sampling; Flexibility (engineering); Theoretical computer science; Mathematical optimization; Machine learning; Mathematics; 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":["sts","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.000489208,0.0002217384,0.0002686877,0.0001681477,0.001588335,0.003635694,0.001492577,0.0001467594,0.000001590099],"category_scores_gemma":[0.0005706658,0.0001962794,0.00008162225,0.0001450655,0.0001020188,0.01814506,0.0002881218,0.0002811168,0.00001337005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005840618,"about_ca_system_score_gemma":0.0001184658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006148822,"about_ca_topic_score_gemma":0.000004367796,"domain_scores_codex":[0.9983003,0.00006771316,0.0005778532,0.0002645314,0.0004370774,0.000352503],"domain_scores_gemma":[0.9977466,0.0001304712,0.0009087403,0.0006044315,0.000504803,0.0001049086],"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":[0.00007043748,0.0000207314,0.0004538966,0.0004022947,0.00002304964,0.000002544778,0.008128894,0.6655683,0.00003913425,0.2001323,0.0001950133,0.1249634],"study_design_scores_gemma":[0.0007464266,0.00006153451,0.0002404575,0.00008892479,0.000007328802,0.00001292711,0.0001302315,0.9938375,0.00002674154,0.003147695,0.001463769,0.0002365142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002046394,0.00004591181,0.992254,0.0005887202,0.001695769,0.0005287598,0.000005509724,0.0002616438,0.002573356],"genre_scores_gemma":[0.9844751,0.000001822263,0.01484977,0.0001892532,0.0002771752,0.000115311,0.00001889153,0.000009813356,0.00006285181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9824287,"threshold_uncertainty_score":0.9997115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03247017259697883,"score_gpt":0.3099848913903102,"score_spread":0.2775147187933314,"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."}}