{"id":"W2602562802","doi":"10.1145/3051088","title":"Guilt-free data reuse","year":2017,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Stanford Bio-X; Simons Institute for the Theory of Computing, University of California Berkeley; University of Toronto; University of Pennsylvania; Microsoft Research; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Computer science; Reuse; Inference; Process (computing); Set (abstract data type); Data mining; Data set; Statistical inference; Simple (philosophy); Machine learning; Data validation; Artificial intelligence; Database","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch","open_science"],"domain":"reproducibility","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.1367217,0.002328967,0.004596208,0.004128348,0.005463113,0.01041023,0.01714825,0.007396481,0.007156057],"category_scores_gemma":[0.4541235,0.002848975,0.006348056,0.004551127,0.02195424,0.03022001,0.03284819,0.01376204,0.003502843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003654794,"about_ca_system_score_gemma":0.01077122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001922274,"about_ca_topic_score_gemma":0.001542017,"domain_scores_codex":[0.7983206,0.1092783,0.01314596,0.02894512,0.04528154,0.005028552],"domain_scores_gemma":[0.345869,0.2055373,0.01643339,0.4098668,0.01839493,0.003898518],"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":[0.0009871159,0.0003230117,0.00678565,0.0007850328,0.0007556559,0.0009523628,0.004838679,0.02031986,0.003689176,0.7041544,0.01037301,0.246036],"study_design_scores_gemma":[0.0001524946,0.0001864997,0.0006779141,0.0003059871,0.0001717095,0.0007333475,0.0003807562,0.0552733,0.006253976,0.9183808,0.01738422,0.00009898747],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007494125,0.0005282303,0.9813406,0.003353789,0.0001484242,0.000480834,0.0002254819,0.001230217,0.005198284],"genre_scores_gemma":[0.3680386,0.0007332934,0.6151727,0.004320119,0.0007274918,0.001956295,0.0009849042,0.001130374,0.006936279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9828517,"threshold_uncertainty_score":0.7230623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2370552844700501,"score_gpt":0.3837375646579778,"score_spread":0.1466822801879276,"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."}}