{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0006796418,0.00006940887,0.000099474,0.00003696942,0.0008073205,0.0001850312,0.9961025,0.00005213898,0.000002396468],"category_scores_gemma":[0.9834828,0.00005294835,0.00003196406,0.000133877,0.0006775819,0.001026635,0.9995713,0.0002432043,0.00002261999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001905802,"about_ca_system_score_gemma":0.00005686426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000143835,"about_ca_topic_score_gemma":0.00008736785,"domain_scores_codex":[0.9991809,0.00009074721,0.0001875184,0.0002390647,0.0001733556,0.0001283889],"domain_scores_gemma":[0.08847716,0.0003268369,0.0003046054,0.9107986,0.0000746956,0.0000181068],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[3.653538e-7,0.00002836596,0.001021606,0.000002553645,0.00001009636,9.118173e-8,0.00001958458,1.976385e-7,0.0001862254,0.008927578,0.9889661,0.0008372196],"study_design_scores_gemma":[0.00009670857,0.000004048994,0.006489985,0.00003060067,0.000005756123,0.000002323872,0.000005467532,0.008557901,0.0009605169,0.9609535,0.0228349,0.00005823289],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.001129896,0.0004838362,0.000408948,0.9929394,0.0001720427,0.0001077202,0.00008449482,0.0001836757,0.004490059],"genre_scores_gemma":[0.02285854,0.0003878367,0.9765785,0.0001152743,0.000008220468,0.000007776966,0.00001173138,0.000005363346,0.00002677414],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.9928241,"threshold_uncertainty_score":0.6209338,"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."}}