{"id":"W2548122763","doi":"10.14778/2994509.2994514","title":"ActiveClean","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":244,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"MNIST database; Computer science; Context (archaeology); Support vector machine; Data mining; Convergence (economics); Process (computing); Class (philosophy); Iterative and incremental development; Machine learning; Artificial intelligence; Deep learning","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":[0.0002455014,0.00006172685,0.00006522557,0.00003417992,0.00006358518,0.00003427575,0.0009108183,0.00001755708,0.00001058924],"category_scores_gemma":[0.0001236381,0.00002905918,0.0000414636,0.0001489794,0.00003619854,0.0003022806,0.0003272137,0.00004717764,0.00002646544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003386122,"about_ca_system_score_gemma":0.00001160415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009090244,"about_ca_topic_score_gemma":2.792583e-7,"domain_scores_codex":[0.999399,0.000006654332,0.0001172592,0.0001828491,0.0001766334,0.0001175978],"domain_scores_gemma":[0.9995267,0.00003516491,0.0001479358,0.0001874553,0.00007123804,0.00003150084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005092331,0.00004358792,0.005162852,0.00001270583,0.00001072455,3.301596e-8,0.0002485394,2.972087e-7,0.3499639,0.3406787,0.002692454,0.3011811],"study_design_scores_gemma":[0.0006386968,0.0001065241,0.07652286,0.0001276876,0.00001114911,0.0000107853,0.00007034253,0.0008733721,0.8030983,0.02366083,0.09468397,0.0001954392],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3562582,0.0002442886,0.2771933,0.1524427,0.001813846,0.001391986,0.00001480555,0.0009568534,0.2096839],"genre_scores_gemma":[0.9882314,0.0000155887,0.01057301,0.00009126191,0.00002797692,0.00001227271,9.592381e-8,0.000003741714,0.001044702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6319731,"threshold_uncertainty_score":0.1692542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009115700324434017,"score_gpt":0.2121947867126384,"score_spread":0.2030790863882044,"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."}}