{"id":"W4283167130","doi":"10.1145/3531146.3534637","title":"Data Governance in the Age of Large-Scale Data-Driven Language Technology","year":2022,"lang":"en","type":"article","venue":"2022 ACM Conference on Fairness, Accountability, and Transparency","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Corporate governance; Data governance; Work (physics); Knowledge management; Computer science; Data science; Data management; Scale (ratio); Public relations; Political science; Business; Database; Data quality; Engineering; Marketing","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":[0.09051332,0.0004617216,0.001082289,0.00300719,0.004359432,0.01889553,0.00349155,0.004512988,0.002206832],"category_scores_gemma":[0.1049389,0.0009499345,0.0007613037,0.00447407,0.02083683,0.03673578,0.01772404,0.009119137,0.0008899851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005561952,"about_ca_system_score_gemma":0.00933232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003895778,"about_ca_topic_score_gemma":0.002444423,"domain_scores_codex":[0.9527237,0.02765098,0.002708553,0.007306039,0.007847951,0.001762881],"domain_scores_gemma":[0.8333529,0.09261414,0.009655314,0.04667885,0.01167593,0.006022851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004607753,0.00005134127,0.002961436,0.0001074913,0.00003513594,0.0001322342,0.006114466,0.003713337,0.0007511843,0.9399692,0.005807211,0.04031079],"study_design_scores_gemma":[0.0000265605,0.00003141293,0.0007450936,0.0001460382,0.00001211797,0.00009557256,0.002047581,0.007678626,0.0006982579,0.9093406,0.07913738,0.00004066899],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06703626,0.004358048,0.7113709,0.1683724,0.0007669042,0.0004269336,0.0005213504,0.00142104,0.04572612],"genre_scores_gemma":[0.7513699,0.003181679,0.2200696,0.0124764,0.001556209,0.0008047663,0.0007859556,0.0006441314,0.009111483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.09051332,"threshold_uncertainty_score":0.4786859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1154822459186154,"score_gpt":0.3960952844375087,"score_spread":0.2806130385188934,"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."}}