Termination:Unlearning stops when the current model’s perplexity on the original (unshuffled) forget set reaches or exceedsPPL target
· 2000
· arXiv 6314.3711
1 Pith paper cite this work. Polarity classification is still indexing.
Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.