@article{keyhere,
  abstract = {We have developed an efficient way to determine the syntactic similarity of files and have applied it to every document on the World Wide Web. Using this mechanism, we built a clustering of all the documents that are syntactically similar. Possible applications include a "Lost and Found" service, filtering the results of Web searches, updating widely distributed web-pages, and identifying violations of intellectual property rights.},
  author = {Broder, Andrei Z. and Glassman, Steven C. and Manasse, Mark S. and Zweig, Geoffrey},
  booktitle = {Papers from the Sixth International World Wide Web Conference},
  interhash = {424cdc36335873e4d8c0bed6e07e872e},
  intrahash = {93a3440b81c13ec81c17481a97719c71},
  journal = {Computer Networks and ISDN Systems},
  month = {#sep#},
  number = {8-13},
  pages = {1157--1166},
  title = {Syntactic clustering of the Web},
  url = {http://www.sciencedirect.com/science/article/B6TYT-3SP60S4-11/2/38f44c816ec8d69b406317de1629e56d},
  volume = 29,
  year = 1997
}