{"url":"/dataset/robust04","name":"Robust04","full_name":null,"description_markdown":"The goal of the Robust track is to improve the consistency of retrieval technology by focusing on poorly performing topics. In addition, the track brings back a classic, ad hoc retrieval task in TREC that provides a natural home for new participants. An ad hoc task in TREC investigates the performance of systems that search a static set of documents using previously-unseen topics. For each topic, participants create a query and submit a ranking of the top 1000 documents for that topic.","description_withheld":null,"homepage":"https://trec.nist.gov/data/robust.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Zero-shot Text Search","url":"/task/zero-shot-text-search","datasets_with_task":"/datasets/task/zero-shot-text-search"},{"name":"Ad-Hoc Information Retrieval","url":"/task/ad-hoc-information-retrieval","datasets_with_task":"/datasets/task/ad-hoc-information-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TREC Robust04","Robust04"],"data_loaders":[],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/ad-hoc-information-retrieval-on-trec-robust04","task":"Ad-Hoc Information Retrieval","dataset_variant":"TREC Robust04","rows":21,"metrics":["nDCG@20","MAP","P@20"],"first_row_in_archive_order":{"model":"monoT5-3B (zero-shot)","paper":"/paper/document-ranking-with-a-pretrained-sequence","metrics":{"MAP":"0.3876","P@20":"0.5165","nDCG@20":"0.6091"},"code_links":[{"title":"castorini/pygaggle","url":"https://github.com/castorini/pygaggle"},{"title":"neuralmind-ai/coliee","url":"https://github.com/neuralmind-ai/coliee"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/parade-passage-representation-aggregation-for","title":"PARADE: Passage Representation Aggregation for Document Reranking","date":"2020-08-20","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/document-ranking-with-a-pretrained-sequence","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","date":"2020-03-14","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deeper-text-understanding-for-ir-with","title":"Deeper Text Understanding for IR with Contextual Neural Language Modeling","date":"2019-05-22","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/190407094","title":"CEDR: Contextualized Embeddings for Document Ranking","date":"2019-04-15","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/simple-applications-of-bert-for-ad-hoc","title":"Simple Applications of BERT for Ad Hoc Document Retrieval","date":"2019-03-26","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/the-neural-hype-and-comparisons-against-weak","title":"The Neural Hype and Comparisons Against Weak Baselines","date":"2018-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nprf-a-neural-pseudo-relevance-feedback","title":"NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval","date":"2018-10-30","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/from-neural-re-ranking-to-neural-ranking","title":"From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing","date":"2018-10-22","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/deep-relevance-ranking-using-enhanced","title":"Deep Relevance Ranking Using Enhanced Document-Query Interactions","date":"2018-09-05","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-deep-relevance-matching-model-for-ad-hoc","title":"A Deep Relevance Matching Model for Ad-hoc Retrieval","date":"2017-11-23","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/neural-ranking-models-with-weak-supervision","title":"Neural Ranking Models with Weak Supervision","date":"2017-04-28","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":23,"samples_ran":4,"samples_unverified":19,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":2,"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."}