{"id":"W2903958360","doi":"10.1609/aaai.v33i01.33017975","title":"Lifted Hinge-Loss Markov Random Fields","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"U.S. Army Corps of Engineers; Institut de Valorisation des Données; Canada First Research Excellence Fund; National Science Foundation","keywords":"Inference; Approximate inference; Graphical model; Markov chain; Hinge loss; Random field; Markov random field; Computer science; Mathematical optimization; Optimization problem; Convex optimization; Algorithm; Maximum a posteriori estimation; Theoretical computer science; Mathematics; Artificial intelligence; Regular polygon; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006744041,0.0002848656,0.0003753715,0.000131242,0.0001621423,0.000355638,0.002893705,0.0001707103,0.0001864376],"category_scores_gemma":[0.0002805903,0.0002105778,0.0001829312,0.0006674787,0.0001791072,0.00051097,0.00049923,0.0005098294,0.0003907026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003601533,"about_ca_system_score_gemma":0.0001296858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004618229,"about_ca_topic_score_gemma":0.000005703624,"domain_scores_codex":[0.9976606,0.00002926476,0.0006107899,0.000643446,0.0005992617,0.0004565907],"domain_scores_gemma":[0.9981948,0.0001564786,0.0003570882,0.0005292254,0.0006396845,0.0001227858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001345151,0.0001203263,0.0005933773,0.0000553556,0.00002213177,8.931121e-7,0.001094813,0.0001308651,0.01540131,0.9156723,0.0003247342,0.06644939],"study_design_scores_gemma":[0.0001512473,0.000357402,0.0002508427,0.00048223,0.00001838865,0.00001333191,0.0002694565,0.3124245,0.3370976,0.3481667,0.0002348846,0.0005333609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6130919,0.00007288432,0.3088647,0.0122281,0.002067933,0.00105422,0.000007397337,0.0003943582,0.06221852],"genre_scores_gemma":[0.9945647,0.00004403213,0.003773508,0.0005588728,0.00006846021,0.00002081973,4.428961e-7,0.0000140285,0.0009551384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5675056,"threshold_uncertainty_score":0.8587112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04339664534832468,"score_gpt":0.2723407101887145,"score_spread":0.2289440648403898,"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."}}