%0 Conference Paper %1 frbe2021copycat %A Fröbe, Maik %A Bevendorff, Janek %A Gienapp, Lukas %A Völske, Michael %A Stein, Benno %A Potthast, Martin %A Hagen, Matthias %B Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval %D 2021 %I ACM %K common copycat crawl detection duplicate web %R 10.1145/3404835.3463246 %T CopyCat: Near-Duplicates Within and Between the ClueWeb and the Common Crawl %U https://doi.org/10.1145%2F3404835.3463246

@inproceedings{frbe2021copycat, added-at = {2023-02-09T13:15:43.000+0100}, author = {Fröbe, Maik and Bevendorff, Janek and Gienapp, Lukas and Völske, Michael and Stein, Benno and Potthast, Martin and Hagen, Matthias}, biburl = {https://www.bibsonomy.org/bibtex/21a2787ae4b526cda4263033ec4b95c51/jaeschke}, booktitle = {Proceedings of the 44th International {ACM} {SIGIR} Conference on Research and Development in Information Retrieval}, description = {CopyCat: Near-Duplicates Within and Between the ClueWeb and the Common Crawl | Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval}, doi = {10.1145/3404835.3463246}, interhash = {201e409a0b834af85bbeb20bc32388ba}, intrahash = {1a2787ae4b526cda4263033ec4b95c51}, keywords = {common copycat crawl detection duplicate web}, month = jul, publisher = {{ACM}}, timestamp = {2023-02-09T13:15:43.000+0100}, title = {{CopyCat}: Near-Duplicates Within and Between the {ClueWeb} and the Common Crawl}, url = {https://doi.org/10.1145%2F3404835.3463246}, year = 2021 }