{"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/oie2016","name":"OIE2016","full_name":null,"description_markdown":"OIE2016 is the first large-scale OpenIE benchmark. It is created by automatic conversion from QA-SRL [He et al., 2015], a semantic role labeling dataset. The sentences are from news (e.g., WSJ) and encyclopedia (e.g., WIKI) domains. Since there are no restrictions on the elements of OpenIE extractions, partial-matching criteria instead of exact-matching is typically used. Hence, the evaluation script can tolerate the extractions that are slightly different from the gold annotation. \r\n\r\nSource: https://arxiv.org/pdf/2205.11725.pdf (section 3.1)","description_withheld":null,"homepage":"","introduced_date":"2016-11-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/creating-a-large-benchmark-for-open","title":"Creating a Large Benchmark for Open Information Extraction","first_author":"Gabriel Stanovsky","url":null},"license":null,"modalities":[],"tasks":[{"name":"Open Information Extraction","url":"/task/open-information-extraction","datasets_with_task":"/datasets/task/open-information-extraction"}],"languages":[],"variants":["OIE2016"],"data_loaders":[],"num_papers_in_archive":31,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/open-information-extraction-on-oie2016","task":"Open Information Extraction","dataset_variant":"OIE2016","rows":12,"metrics":["F1","AUC"],"first_row_in_archive_order":{"model":"DeepEx (zero-shot)","paper":"/paper/zero-shot-information-extraction-as-a-unified","metrics":{"AUC":"58.6","F1":"72.6"},"code_links":[{"title":"cgraywang/deepex","url":"https://github.com/cgraywang/deepex"}]},"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":5,"of":5,"counts":{"papers_with_a_benchmark_row":5,"with_a_code_link":3,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/improving-open-information-extraction-with","slug":"improving-open-information-extraction-with","title":"Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty","date":"2023-09-07","arxiv_id":"2309.03433","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/a-survey-on-neural-open-information","slug":"a-survey-on-neural-open-information","title":"A Survey on Neural Open Information Extraction: Current Status and Future Directions","date":"2022-05-24","arxiv_id":"2205.11725","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/deepstruct-pretraining-of-language-models-for-1","slug":"deepstruct-pretraining-of-language-models-for-1","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","date":"2022-05-21","arxiv_id":"2205.10475","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["cgraywang/deepstruct"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deepstruct-pretraining-of-language-models-for-1#ran","syntology_url":"https://syntology.ai/paper/2205.10475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10475"}}}},{"paper":"/paper/zero-shot-information-extraction-as-a-unified","slug":"zero-shot-information-extraction-as-a-unified","title":"Zero-Shot Information Extraction as a Unified Text-to-Triple Translation","date":"2021-09-23","arxiv_id":"2109.11171","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/span-based-open-information-extraction","slug":"span-based-open-information-extraction","title":"Span Model for Open Information Extraction on Accurate Corpus","date":"2019-01-30","arxiv_id":"1901.10879","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["zhanjunlang/Span_OIE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/span-based-open-information-extraction#ran","syntology_url":"https://syntology.ai/paper/1901.10879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10879"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/improving-open-information-extraction-with","slug":"improving-open-information-extraction-with","title":"Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty","date":"2023-09-07","arxiv_id":"2309.03433","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/a-survey-on-neural-open-information","slug":"a-survey-on-neural-open-information","title":"A Survey on Neural Open Information Extraction: Current Status and Future Directions","date":"2022-05-24","arxiv_id":"2205.11725","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/deepstruct-pretraining-of-language-models-for-1","slug":"deepstruct-pretraining-of-language-models-for-1","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","date":"2022-05-21","arxiv_id":"2205.10475","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["cgraywang/deepstruct"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deepstruct-pretraining-of-language-models-for-1#ran","syntology_url":"https://syntology.ai/paper/2205.10475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10475"}}}},{"paper":"/paper/zero-shot-information-extraction-as-a-unified","slug":"zero-shot-information-extraction-as-a-unified","title":"Zero-Shot Information Extraction as a Unified Text-to-Triple Translation","date":"2021-09-23","arxiv_id":"2109.11171","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/span-based-open-information-extraction","slug":"span-based-open-information-extraction","title":"Span Model for Open Information Extraction on Accurate Corpus","date":"2019-01-30","arxiv_id":"1901.10879","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["zhanjunlang/Span_OIE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/span-based-open-information-extraction#ran","syntology_url":"https://syntology.ai/paper/1901.10879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10879"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/oie2016/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/oie2016/papers/ran/1","json":"/dataset/oie2016/papers/ran/1.json","rows":2}],"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":2,"samples_harvested":17,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":7,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"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":"2fbc49a7804e7b3ee2560dd48beab9c341d573d1aed2a717f34ef101f6f7b817","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}