{"id":"W2101806650","doi":"","title":"{PAC-Bayesian Theory for Transductive Learning}","year":2014,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Université de Moncton","funders":"","keywords":"Artificial intelligence; Bayesian probability; Generalization; Computer science; Generalization error; Machine learning; Probably approximately correct learning; Inductive bias; Multi-task learning; Stability (learning theory); Mathematics","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":[0.000617075,0.0001467646,0.0001417228,0.0001081206,0.0001896795,0.0002985329,0.000457824,0.00005124329,0.0001193674],"category_scores_gemma":[0.0007932961,0.0001351171,0.00003784299,0.00007547474,0.0001191391,0.0001347493,0.00004254268,0.0002209067,0.00004625225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001691594,"about_ca_system_score_gemma":0.00003975243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001639027,"about_ca_topic_score_gemma":0.00001785917,"domain_scores_codex":[0.998777,0.0001600314,0.0002548973,0.0003678689,0.0002413151,0.0001989135],"domain_scores_gemma":[0.9985589,0.0008491662,0.00009717409,0.0001475663,0.0002614926,0.00008569567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003533668,0.00002580536,0.000007580096,0.000003034935,0.00001078901,0.000001139403,0.0005358086,0.0003307824,0.00008619828,0.605359,0.00004716298,0.3935573],"study_design_scores_gemma":[0.00002617952,0.000252527,0.000027432,0.0000114442,0.000003485837,0.000003550845,0.0001670625,0.5146558,0.0006064668,0.4822201,0.001918014,0.0001079888],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002253569,0.000006458156,0.9900933,0.002041268,0.0006096329,0.0001096832,0.00003809278,0.00007461647,0.006801603],"genre_scores_gemma":[0.8662564,0.00002685993,0.1321829,0.0003449728,0.000220177,0.0000145693,0.00002727015,0.000009764636,0.0009170908],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.866031,"threshold_uncertainty_score":0.5509917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05392569779190722,"score_gpt":0.3345362810595931,"score_spread":0.2806105832676859,"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."}}