* chore(release): unify package versions * fix(release): harden version synchronization
* test(bench): probe optional backend evidence * fix(bench): accept native stext pages
* test(bench): compare OpenDataLoader builds * docs(bench): keep reference comparisons generic * fix(bench): keep regression gates complete * fix(bench): clarify missing reference gates * fix(bench): validate nonnegative limits * fix(bench): isolate prediction runs * chore(bench): refresh review