{"id":"W4308627439","doi":"10.1145/3549037.3570195","title":"Data quality and model under-specification issues (keynote)","year":2022,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Pipeline (software); Process (computing); Quality (philosophy); Data quality; Data modeling; Data science; Root cause; Software engineering; Artificial intelligence; Machine learning; Engineering; Reliability engineering; Programming language; Operations management","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07504271,0.001340115,0.001873705,0.003357465,0.002040793,0.008717909,0.005361346,0.003104646,0.008250373],"category_scores_gemma":[0.3455327,0.001717784,0.002348064,0.004443671,0.005624774,0.01371933,0.008858597,0.01052292,0.002628621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003701815,"about_ca_system_score_gemma":0.004712436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004285733,"about_ca_topic_score_gemma":0.002848395,"domain_scores_codex":[0.9163935,0.03226447,0.008106238,0.01097213,0.02982488,0.002438772],"domain_scores_gemma":[0.5475173,0.2755395,0.02024315,0.1150108,0.03911385,0.002575463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001349265,0.0003039416,0.03078489,0.001836724,0.0006904826,0.001649027,0.003694701,0.03929163,0.01043759,0.226563,0.06973614,0.6136626],"study_design_scores_gemma":[0.0001949825,0.0004833238,0.00794734,0.002084927,0.0003417455,0.002940098,0.001872563,0.2539209,0.07065006,0.4926087,0.1665793,0.0003761352],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.01269611,0.002658248,0.9529222,0.02242389,0.001622279,0.0002235804,0.0009513987,0.00385014,0.002652261],"genre_scores_gemma":[0.3655902,0.003505925,0.603319,0.01071383,0.002646591,0.0006076731,0.00384295,0.002879784,0.006894075],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.07504271,"threshold_uncertainty_score":0.3968685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2185267427719628,"score_gpt":0.3905440558722597,"score_spread":0.1720173131002969,"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."}}