{"id":"W2987414108","doi":"10.1145/3391403.3399541","title":"Multi-Item Mechanisms without Item-Independence: Learnability via Robustness","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Defense Sciences Office, DARPA; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Heising-Simons Foundation; Innovative Research Group Project of the National Natural Science Foundation of China; Fonds de recherche du Québec – Nature et technologies; Alfred P. Sloan Foundation; U.S. Department of Energy; National Science Foundation","keywords":"Learnability; Markov blanket; Robustness (evolution); Graphical model; Mathematics; Bayesian network; Random variable; Computer science; Markov chain; Independence (probability theory); Bounded function; Bayesian probability; Theoretical computer science; Mathematical optimization; Artificial intelligence; Machine learning; Markov model; Variable-order Markov model; Statistics","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004829508,0.0004886489,0.000830588,0.0002230669,0.0004679222,0.0005923394,0.002829601,0.0007316731,0.006240714],"category_scores_gemma":[0.004019698,0.0003729591,0.0004568146,0.0008070403,0.0002756097,0.0002986178,0.002224452,0.001589218,0.002401462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001149321,"about_ca_system_score_gemma":0.0003284957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008605065,"about_ca_topic_score_gemma":0.00007710068,"domain_scores_codex":[0.9930561,0.000734802,0.001378317,0.002223398,0.00221917,0.0003882056],"domain_scores_gemma":[0.994083,0.0013477,0.0008282246,0.002417338,0.0009042771,0.0004194269],"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":[0.0007719705,0.00305722,0.0224985,0.0004760777,0.0006582509,0.00008187962,0.005754397,0.2627091,0.02930668,0.4640303,0.02176851,0.1888871],"study_design_scores_gemma":[0.0003697505,0.00003720371,0.00343156,0.00002690383,0.00005082137,0.00002196944,0.001725835,0.2842035,0.004676762,0.7005799,0.004153928,0.0007218915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01694075,0.00002876544,0.9729419,0.003862203,0.001080755,0.001019352,0.00005862164,0.0004598872,0.003607803],"genre_scores_gemma":[0.916787,0.000007436759,0.06321528,0.0004849948,0.0002252099,0.0002633151,0.00002782104,0.00003922355,0.01894967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9097266,"threshold_uncertainty_score":0.9998722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1672390636790978,"score_gpt":0.4112897747592437,"score_spread":0.2440507110801459,"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."}}