data-obfuscator reverse (run2 key) - report. PRIVATE: the restored dataset holds real data again. ====================================================================== Input : master_masked.csv Key : out2/l3/keymap2.txt (program 0.0.0.23, level 3) Steps : scaling, dates, recoding Restored file : back2/full/restored.csv Restored SHA-256: 39469eba26a8b32b52610d91d6466e17bb2bd4a62dae1bf3fac477abacb8c253 Columns of the dataset ID identifier (subject) via --map restored 264 value(s) USUBJID identifier (subject) restored 264 value(s) DATE date found by its values restored 264 value(s) EVID unchanged AMT unchanged DV scaled (AVAL) via --map restored 240 value(s) DVID unchanged WT scaled (WEIGHTBL) via --map restored 264 value(s) ARM identifier (treatment) restored 264 value(s) Cannot be restored (removed when masking) adsl.csv: COMMENT - free text redacted (.) Note: columns of the key that are not in the master dataset (nothing to restore, or they were renamed - use --map): STUDYID (study codes), SUBJID (subject codes), SITEID (site codes), INVNAM (user codes), TRT01P (treatment codes), TRT01PN (treatment codes), SEX (sex codes), RACE (race codes), TRTSDT (dates), TRTEDT (dates), BRTHDT (dates), EXSTDTC (dates), ADTM (dates), ADT (dates), AGE (scaled) What this cannot do: values the LLM derived or transformed (a log of DV, a unit conversion, a re-coded SEX) are not recognised and stay as they are; free text and dropped columns were removed when masking; a master column that mixes several scaled source columns needs --map COMBINED=SOURCE:WHENCOL=VALUE rules to be restored.