{"url":"/dataset/fake","name":"fake","full_name":"Real / Fake Job Posting Prediction","description_markdown":"[Real or Fake] : Fake Job Description Prediction\r\nThis dataset contains 18K job descriptions out of which about 800 are fake. The data consists of both textual information and meta-information about the jobs. The dataset can be used to create classification models which can learn the job descriptions which are fraudulent.","description_withheld":null,"homepage":"https://www.kaggle.com/datasets/shivamb/real-or-fake-fake-jobposting-prediction","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"CC0: Public Domain","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Binary Classification","url":"/task/binary-classification","datasets_with_task":"/datasets/task/binary-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["fake"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/binary-classification-on-fake","task":"Binary Classification","dataset_variant":"fake","rows":8,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"Trompt + OpenAI embedding","paper":"/paper/pytorch-frame-a-modular-framework-for-multi","metrics":{"AUROC":"0.979"},"code_links":[{"title":"pyg-team/pytorch-frame","url":"https://github.com/pyg-team/pytorch-frame"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/pytorch-frame-a-modular-framework-for-multi","title":"PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learning","date":"2024-03-31","rows_on_this_dataset":8,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}