%0 Journal Article %1 ident3 %A Spinellis, Diomidis %D 2005 %J Information Retrieval %K identifier %N 1 %P 5- %T Index-Based Persistent Document Identifiers %U http://www.dmst.aueb.gr/dds/pubs/jrnl/2005-IR-PDI/html/Spi04b.pdf %V 8 %X The infrastructure of a typical search engine can be used to calculate and resolve persistent document identifiers: a string that can uniquely identify and locate a document on the Internet without reference to its original location (URL). Bookmarking a document using such an identifier allows its retrieval even if the document's URL, and, in many cases, its contents change. Web client applications can offer facilities for users to bookmark a page by reference to a search engine and the persistent identifier instead of the original URL. The identifiers are calculated using a global Internet term index; a document's unique identifier consists of a word or word combination that occurs uniquely in the specific document. We use a genetic algorithm to locate a minimal unique document identifier: the shortest word or word combination that will locate the document. We tested our approach by implementing tools for indexing a document collection, calculating the persistent identifiers, performing queries, and distributing the computation and storage load among many computers.

@article{ident3, abstract = {The infrastructure of a typical search engine can be used to calculate and resolve persistent document identifiers: a string that can uniquely identify and locate a document on the Internet without reference to its original location (URL). Bookmarking a document using such an identifier allows its retrieval even if the document's URL, and, in many cases, its contents change. Web client applications can offer facilities for users to bookmark a page by reference to a search engine and the persistent identifier instead of the original URL. The identifiers are calculated using a global Internet term index; a document's unique identifier consists of a word or word combination that occurs uniquely in the specific document. We use a genetic algorithm to locate a minimal unique document identifier: the shortest word or word combination that will locate the document. We tested our approach by implementing tools for indexing a document collection, calculating the persistent identifiers, performing queries, and distributing the computation and storage load among many computers.}, added-at = {2006-11-01T16:14:41.000+0100}, author = {Spinellis, Diomidis}, biburl = {https://www.bibsonomy.org/bibtex/28bc72e653cd017032ec94df68caabc8f/nichtich}, interhash = {fec953b2a09662fc41929618bbf86937}, intrahash = {8bc72e653cd017032ec94df68caabc8f}, journal = {Information Retrieval}, keywords = {identifier}, number = 1, pages = {5-}, timestamp = {2017-04-02T20:21:46.000+0200}, title = {Index-Based Persistent Document Identifiers}, url = {http://www.dmst.aueb.gr/dds/pubs/jrnl/2005-IR-PDI/html/Spi04b.pdf}, volume = 8, year = 2005 }