{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":11,"of":11,"counts":{"papers_with_a_benchmark_row":11,"with_a_code_link":11,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/parade-passage-representation-aggregation-for","slug":"parade-passage-representation-aggregation-for","title":"PARADE: Passage Representation Aggregation for Document Reranking","date":"2020-08-20","arxiv_id":"2008.09093","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["canjiali/PARADE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/parade-passage-representation-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2008.09093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.09093"}}}},{"paper":"/paper/document-ranking-with-a-pretrained-sequence","slug":"document-ranking-with-a-pretrained-sequence","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","date":"2020-03-14","arxiv_id":"2003.06713","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deeper-text-understanding-for-ir-with","slug":"deeper-text-understanding-for-ir-with","title":"Deeper Text Understanding for IR with Contextual Neural Language Modeling","date":"2019-05-22","arxiv_id":"1905.09217","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["AdeDZY/SIGIR19-BERT-IR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deeper-text-understanding-for-ir-with#ran","syntology_url":"https://syntology.ai/paper/1905.09217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09217"}}}},{"paper":"/paper/190407094","slug":"190407094","title":"CEDR: Contextualized Embeddings for Document Ranking","date":"2019-04-15","arxiv_id":"1904.07094","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["Georgetown-IR-Lab/cedr","Georgetown-IR-Lab/contextualized-reps-for-ranking"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190407094#ran","syntology_url":"https://syntology.ai/paper/1904.07094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07094"}}}},{"paper":"/paper/simple-applications-of-bert-for-ad-hoc","slug":"simple-applications-of-bert-for-ad-hoc","title":"Simple Applications of BERT for Ad Hoc Document Retrieval","date":"2019-03-26","arxiv_id":"1903.10972","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/the-neural-hype-and-comparisons-against-weak","slug":"the-neural-hype-and-comparisons-against-weak","title":"The Neural Hype and Comparisons Against Weak Baselines","date":"2018-12-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nprf-a-neural-pseudo-relevance-feedback","slug":"nprf-a-neural-pseudo-relevance-feedback","title":"NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval","date":"2018-10-30","arxiv_id":"1810.12936","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["ucasir/NPRF"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/nprf-a-neural-pseudo-relevance-feedback#ran","syntology_url":"https://syntology.ai/paper/1810.12936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12936"}}}},{"paper":"/paper/from-neural-re-ranking-to-neural-ranking","slug":"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","arxiv_id":null,"rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/deep-relevance-ranking-using-enhanced","slug":"deep-relevance-ranking-using-enhanced","title":"Deep Relevance Ranking Using Enhanced Document-Query Interactions","date":"2018-09-05","arxiv_id":"1809.01682","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-deep-relevance-matching-model-for-ad-hoc","slug":"a-deep-relevance-matching-model-for-ad-hoc","title":"A Deep Relevance Matching Model for Ad-hoc Retrieval","date":"2017-11-23","arxiv_id":"1711.08611","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/neural-ranking-models-with-weak-supervision","slug":"neural-ranking-models-with-weak-supervision","title":"Neural Ranking Models with Weak Supervision","date":"2017-04-28","arxiv_id":"1704.08803","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/parade-passage-representation-aggregation-for","slug":"parade-passage-representation-aggregation-for","title":"PARADE: Passage Representation Aggregation for Document Reranking","date":"2020-08-20","arxiv_id":"2008.09093","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["canjiali/PARADE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/parade-passage-representation-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2008.09093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.09093"}}}},{"paper":"/paper/document-ranking-with-a-pretrained-sequence","slug":"document-ranking-with-a-pretrained-sequence","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","date":"2020-03-14","arxiv_id":"2003.06713","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deeper-text-understanding-for-ir-with","slug":"deeper-text-understanding-for-ir-with","title":"Deeper Text Understanding for IR with Contextual Neural Language Modeling","date":"2019-05-22","arxiv_id":"1905.09217","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":2,"official":{"repos":["AdeDZY/SIGIR19-BERT-IR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deeper-text-understanding-for-ir-with#ran","syntology_url":"https://syntology.ai/paper/1905.09217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09217"}}}},{"paper":"/paper/190407094","slug":"190407094","title":"CEDR: Contextualized Embeddings for Document Ranking","date":"2019-04-15","arxiv_id":"1904.07094","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["Georgetown-IR-Lab/cedr","Georgetown-IR-Lab/contextualized-reps-for-ranking"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190407094#ran","syntology_url":"https://syntology.ai/paper/1904.07094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07094"}}}},{"paper":"/paper/simple-applications-of-bert-for-ad-hoc","slug":"simple-applications-of-bert-for-ad-hoc","title":"Simple Applications of BERT for Ad Hoc Document Retrieval","date":"2019-03-26","arxiv_id":"1903.10972","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/the-neural-hype-and-comparisons-against-weak","slug":"the-neural-hype-and-comparisons-against-weak","title":"The Neural Hype and Comparisons Against Weak Baselines","date":"2018-12-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/nprf-a-neural-pseudo-relevance-feedback","slug":"nprf-a-neural-pseudo-relevance-feedback","title":"NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval","date":"2018-10-30","arxiv_id":"1810.12936","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["ucasir/NPRF"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/nprf-a-neural-pseudo-relevance-feedback#ran","syntology_url":"https://syntology.ai/paper/1810.12936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12936"}}}},{"paper":"/paper/from-neural-re-ranking-to-neural-ranking","slug":"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","arxiv_id":null,"rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/deep-relevance-ranking-using-enhanced","slug":"deep-relevance-ranking-using-enhanced","title":"Deep Relevance Ranking Using Enhanced Document-Query Interactions","date":"2018-09-05","arxiv_id":"1809.01682","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-deep-relevance-matching-model-for-ad-hoc","slug":"a-deep-relevance-matching-model-for-ad-hoc","title":"A Deep Relevance Matching Model for Ad-hoc Retrieval","date":"2017-11-23","arxiv_id":"1711.08611","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/neural-ranking-models-with-weak-supervision","slug":"neural-ranking-models-with-weak-supervision","title":"Neural Ranking Models with Weak Supervision","date":"2017-04-28","arxiv_id":"1704.08803","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/robust04/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/robust04/papers/ran/1","json":"/dataset/robust04/papers/ran/1.json","rows":3}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":4,"samples_harvested":23,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":4,"samples_unverified":11,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/ad-hoc-information-retrieval-on-trec-robust04","since_archive":"/sota/ad-hoc-information-retrieval-on-trec-robust04#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"24192c7eaa194c7c4a661f75d756c1d7937c68e5ec16b06a7b4dd8135e4e0043","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}