{"id":"W2766046864","doi":"10.48550/arxiv.1710.08874","title":"Synthetic Data for Social Good","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact","funders":"","keywords":"Data science; Computer science","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":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0006398772,0.0003442643,0.0004135625,0.0002101877,0.0006089949,0.0004708773,0.1518975,0.0005716185,0.00001259194],"category_scores_gemma":[0.008529247,0.0004130054,0.0001662489,0.0001902081,0.0003266534,0.001173057,0.4646835,0.0006924979,0.00006545413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001861841,"about_ca_system_score_gemma":0.0002991378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008845276,"about_ca_topic_score_gemma":0.00003710464,"domain_scores_codex":[0.9967631,0.00008034796,0.0001917711,0.002324321,0.0001172768,0.0005232059],"domain_scores_gemma":[0.9597071,0.0002210242,0.0004545957,0.03938978,0.000144168,0.00008333754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005444505,0.0002660098,0.0005841608,0.0004533703,0.0004658644,0.0004187583,0.00008174961,0.0006494396,0.0000400155,0.4009732,0.5769855,0.01902758],"study_design_scores_gemma":[0.0002417924,0.00001704109,0.0001140314,0.00005382752,0.00005676252,0.000002387596,0.00001043697,0.4834031,0.00005205599,0.5077083,0.00799951,0.0003407454],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004272684,0.00007269219,0.9812232,0.006506089,0.001275429,0.0005505054,0.001056427,0.001177193,0.00386583],"genre_scores_gemma":[0.936789,0.0001408122,0.06185998,0.00005539579,0.0001677261,0.00000330467,0.0002778385,0.0000310412,0.0006748716],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9325163,"threshold_uncertainty_score":0.9998322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.220244900746353,"score_gpt":0.2578539553684698,"score_spread":0.03760905462211681,"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."}}