{"id":"W4285337687","doi":"10.14778/3494124.3494125","title":"Enabling SQL-based training data debugging for federated learning","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Debugging; Computer science; SQL; SQL injection; Protocol (science); Machine learning; Federated learning; Database; Software engineering; Artificial intelligence; Data mining; Query by Example; Programming language; World Wide Web; Search engine","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":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00110705,0.0001959196,0.0002634108,0.0001067809,0.0004542379,0.0004174115,0.0206002,0.00008537467,0.000006092266],"category_scores_gemma":[0.02836267,0.0001608545,0.00008561833,0.0007435816,0.00007095413,0.0008041558,0.05270107,0.0003298236,0.000001786669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009729202,"about_ca_system_score_gemma":0.0002194234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001310525,"about_ca_topic_score_gemma":0.000003382676,"domain_scores_codex":[0.9978906,0.00001657143,0.0003814528,0.0007777176,0.0004383473,0.0004952914],"domain_scores_gemma":[0.9965925,0.0002801063,0.0003437763,0.002380635,0.0003491864,0.00005378732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007772609,0.0004111237,0.004491067,0.001093315,0.0004570191,0.00001458454,0.001619061,0.0008420416,0.5571414,0.02071317,0.1184382,0.2947013],"study_design_scores_gemma":[0.0007098358,0.00005146172,0.00006678497,0.0003091116,0.00003136669,0.00001771517,0.0005501723,0.5071014,0.4548428,0.02649586,0.009583449,0.0002401113],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09235863,0.002023754,0.7468655,0.145719,0.001797428,0.002230336,0.0001189942,0.003920073,0.004966279],"genre_scores_gemma":[0.6459005,0.00002364062,0.3536055,0.0002585499,0.00004667462,0.00005452234,0.00002154778,0.00002094414,0.00006811181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5535419,"threshold_uncertainty_score":0.9846988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09386716120745424,"score_gpt":0.2972390531859824,"score_spread":0.2033718919785282,"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."}}