A bad archive can preserve misinformation just as efficiently as it preserves files.
That is what makes this page from A Columbine Site worth reading carefully.
Visit the Eric Harris webpages archive page
A Columbine Site describes itself as a long-running research archive dedicated to the injured, the survivors and those who died in the April 20, 1999 Columbine High School shooting. Its Eric Harris webpage section deals with material that existed online before the attack and what happened to that material afterward.
The important part is not the killer’s writing. It is the site’s unusually explicit discussion of provenance.
The page says Harris had used several online services and maintained webpages, but that his actual pages were removed before their addresses became widely public. The site’s author says some directory material and files were preserved, while the original HTML for the webpages was already gone.
That created a problem.
A reconstruction escaped its label
The archivist explains that in 1999 they displayed surviving graphics and links in a layout intended to help readers imagine how some of the missing pages may have looked. Other websites later copied those displays and presented them as mirrors of Harris’s original webpages.
According to A Columbine Site, they were not.
The page now goes out of its way to distinguish actual preserved directories from later reconstruction pages and says there are no surviving copies of Harris’s original websites. Whether a reader is researching Columbine specifically or digital history generally, that distinction is valuable.
Once a screenshot, mirror or copied page loses its chain of custody, repetition can turn a reconstruction into supposed evidence. Search engines then index the copies. New writers cite the search results. Eventually the false provenance becomes easier to find than the correction.
This site is also a reminder that disturbing historical material needs context. A Columbine Site’s homepage frames its collection around victims, survivors, official documents, reporting and the consequences of the attack. That is a far more useful archival purpose than turning the perpetrators into Internet folklore.
For researchers in 2026, the lesson extends well beyond this event: “I found it online” is not provenance. A mirror may be genuine, partial, reconstructed, mislabeled or copied from another reconstruction. The URL alone cannot tell you which.
In this case, the surviving archive does something responsible and surprisingly rare.
It tells you exactly where its evidence stops.