{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003241785,0.0001646715,0.0003456415,0.000073412,0.0008005104,0.0001260796,0.005163155,0.0001480588,0.0008987744],"category_scores_gemma":[0.001016338,0.0001439956,0.00003606437,0.0007022875,0.000865375,0.0006636558,0.00108116,0.0008213353,0.000003110717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006536024,"about_ca_system_score_gemma":0.0004746158,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0132602,"about_ca_topic_score_gemma":0.2247555,"domain_scores_codex":[0.9971957,0.0004535776,0.0003769756,0.0006556762,0.0008940676,0.0004239894],"domain_scores_gemma":[0.9969139,0.0005180343,0.000155151,0.002260941,0.0001036196,0.00004833183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001498004,0.002067298,0.1946857,0.000283432,0.00005934034,0.00007778931,0.2868724,0.00001696987,0.0003048503,0.5012386,0.002012078,0.01223171],"study_design_scores_gemma":[0.002003365,0.0004166552,0.1332491,0.00009451153,0.0001250593,0.000004190881,0.5685512,0.0007558689,0.00001810379,0.165569,0.1283344,0.0008784534],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9205568,0.001268134,0.00006738422,0.04075881,0.0005447345,0.0008636408,0.01028751,0.00008723592,0.02556577],"genre_scores_gemma":[0.9970044,0.001810577,0.00008841886,0.0004076207,0.00006900926,0.00004387632,0.0004811593,0.00001044207,0.00008450963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3356696,"threshold_uncertainty_score":0.9933106,"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."}}