{"id":"W3085364681","doi":"10.14778/3415478.3415562","title":"Data collection and quality challenges for deep learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Feature engineering; Deep learning; Data collection; Big data; Data science; Software; Data mining","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":[0.0002457347,0.00005433211,0.00008237451,0.00001586779,0.0001602956,0.00003964957,0.0005892426,0.00002226572,9.328311e-7],"category_scores_gemma":[0.00009299544,0.00004134062,0.00002502368,0.0001489436,0.00002322384,0.0001835234,0.0005234082,0.0000624755,4.671265e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001281825,"about_ca_system_score_gemma":0.000006592554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008911918,"about_ca_topic_score_gemma":0.000001719747,"domain_scores_codex":[0.999429,0.000004350586,0.0001365836,0.0002497307,0.0001021425,0.00007821957],"domain_scores_gemma":[0.9996014,0.00003064546,0.000139619,0.0001184174,0.00007515113,0.0000347991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004798514,0.0001197802,0.001822355,0.0005275249,0.00006703479,2.937659e-8,0.004295507,0.00001438758,0.07864595,0.6292531,0.002535056,0.2826712],"study_design_scores_gemma":[0.001327588,0.0009906711,0.01302388,0.00007684271,0.00006673175,0.00001298656,0.002236707,0.2485432,0.4241993,0.03144207,0.2775256,0.0005544057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03894528,0.001535561,0.8831534,0.06631579,0.0001273695,0.002198731,0.0000148469,0.0006774585,0.007031583],"genre_scores_gemma":[0.9614473,0.0004223336,0.03774157,0.0001573281,0.00003922248,0.0001076324,6.897483e-7,0.000004764426,0.00007916247],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.922502,"threshold_uncertainty_score":0.1685822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1284582489283515,"score_gpt":0.3110977474383105,"score_spread":0.182639498509959,"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."}}