{"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/funsd","name":"FUNSD","full_name":"Form Understanding in Noisy Scanned Documents","description_markdown":"Form Understanding in Noisy Scanned Documents (FUNSD) comprises 199 real, fully annotated, scanned forms. The documents are noisy and vary widely in appearance, making form understanding (FoUn) a challenging task. The proposed dataset can be used for various tasks, including text detection, optical character recognition, spatial layout analysis, and entity labeling/linking.\r\n\r\nSource: [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](/paper/190513538)\r\n\r\nImage source: [https://guillaumejaume.github.io/FUNSD/](https://guillaumejaume.github.io/FUNSD/)","description_withheld":null,"homepage":"https://guillaumejaume.github.io/FUNSD/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/190513538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","first_author":"Guillaume Jaume","url":null},"license":{"name":"Custom","url":"https://guillaumejaume.github.io/FUNSD/work/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Table Detection","url":"/task/table-detection","datasets_with_task":"/datasets/task/table-detection"},{"name":"Semantic entity labeling","url":"/task/semantic-entity-labeling","datasets_with_task":"/datasets/task/semantic-entity-labeling"}],"languages":[],"variants":["FUNSD"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/nielsr/FUNSD_layoutlmv2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/mindee/doctr","url":"https://mindee.github.io/doctr/latest/datasets.html#doctr.datasets.FUNSD","frameworks":["tf","pytorch"]}],"num_papers_in_archive":179,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-entity-labeling-on-funsd","task":"Semantic entity labeling","dataset_variant":"FUNSD","rows":15,"metrics":["F1"],"first_row_in_archive_order":{"model":"LayoutMask (large)","paper":"/paper/layoutmask-enhance-text-layout-interaction-in","metrics":{"F1":"93.20"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/relation-extraction-on-funsd","task":"Relation Extraction","dataset_variant":"FUNSD","rows":9,"metrics":["F1"],"first_row_in_archive_order":{"model":"LayoutLMv3 large EM + BBO + RSF","paper":"/paper/a-layoutlmv3-based-model-for-enhanced","metrics":{"F1":"90.81"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/entity-linking-on-funsd","task":"Entity Linking","dataset_variant":"FUNSD","rows":7,"metrics":["F1"],"first_row_in_archive_order":{"model":"GeoLayoutLM","paper":"/paper/geolayoutlm-geometric-pre-training-for-visual","metrics":{"F1":"89.45"},"code_links":[{"title":"alibabaresearch/advancedliteratemachinery","url":"https://github.com/alibabaresearch/advancedliteratemachinery"}]},"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":17,"of":17,"counts":{"papers_with_a_benchmark_row":17,"with_a_code_link":12,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":17,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"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/modeling-layout-reading-order-as-ordering","slug":"modeling-layout-reading-order-as-ordering","title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","date":"2024-09-29","arxiv_id":"2409.19672","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/a-layoutlmv3-based-model-for-enhanced","slug":"a-layoutlmv3-based-model-for-enhanced","title":"A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents","date":"2024-04-16","arxiv_id":"2404.10848","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/reading-order-matters-information-extraction","slug":"reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/doctr-document-transformer-for-structured","slug":"doctr-document-transformer-for-structured","title":"DocTr: Document Transformer for Structured Information Extraction in Documents","date":"2023-07-16","arxiv_id":"2307.07929","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/layoutmask-enhance-text-layout-interaction-in","slug":"layoutmask-enhance-text-layout-interaction-in","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","date":"2023-05-30","arxiv_id":"2305.18721","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/geolayoutlm-geometric-pre-training-for-visual","slug":"geolayoutlm-geometric-pre-training-for-visual","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","date":"2023-04-21","arxiv_id":"2304.10759","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/structextv2-masked-visual-textual-prediction","slug":"structextv2-masked-visual-textual-prediction","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","date":"2023-03-01","arxiv_id":"2303.00289","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/dgcn-based-solution-for-entity-linking-on","slug":"dgcn-based-solution-for-entity-linking-on","title":"DGCN Based Solution for Entity Linking on Visual Rich Document","date":"2022-11-16","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ernie-layout-layout-knowledge-enhanced-pre","slug":"ernie-layout-layout-knowledge-enhanced-pre","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","date":"2022-10-12","arxiv_id":"2210.06155","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-layout-layout-knowledge-enhanced-pre#ran","syntology_url":"https://syntology.ai/paper/2210.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06155"}}}},{"paper":"/paper/xdoc-unified-pre-training-for-cross-format","slug":"xdoc-unified-pre-training-for-cross-format","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","date":"2022-10-06","arxiv_id":"2210.02849","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/doc2graph-a-task-agnostic-document","slug":"doc2graph-a-task-agnostic-document","title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","date":"2022-08-23","arxiv_id":"2208.11168","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/layoutlmv3-pre-training-for-document-ai-with","slug":"layoutlmv3-pre-training-for-document-ai-with","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","date":"2022-04-18","arxiv_id":"2204.08387","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/lilt-a-simple-yet-effective-language","slug":"lilt-a-simple-yet-effective-language","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","date":"2022-02-28","arxiv_id":"2202.13669","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["jpwang/lilt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lilt-a-simple-yet-effective-language#ran","syntology_url":"https://syntology.ai/paper/2202.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13669"}}}},{"paper":"/paper/entity-relation-extraction-as-dependency","slug":"entity-relation-extraction-as-dependency","title":"Entity Relation Extraction as Dependency Parsing in Visually Rich Documents","date":"2021-10-19","arxiv_id":"2110.09915","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bros-a-layout-aware-pre-trained-language","slug":"bros-a-layout-aware-pre-trained-language","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","date":"2021-08-10","arxiv_id":"2108.04539","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["clovaai/bros"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bros-a-layout-aware-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2108.04539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04539"}}}},{"paper":"/paper/layoutlmv2-multi-modal-pre-training-for","slug":"layoutlmv2-multi-modal-pre-training-for","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","date":"2020-12-29","arxiv_id":"2012.14740","rows_on_this_dataset":3,"code_links":9,"syntology":null},{"paper":"/paper/layoutlm-pre-training-of-text-and-layout-for","slug":"layoutlm-pre-training-of-text-and-layout-for","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","date":"2019-12-31","arxiv_id":"1912.13318","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/layoutlm-pre-training-of-text-and-layout-for#ran","syntology_url":"https://syntology.ai/paper/1912.13318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.13318"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/modeling-layout-reading-order-as-ordering","slug":"modeling-layout-reading-order-as-ordering","title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","date":"2024-09-29","arxiv_id":"2409.19672","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/a-layoutlmv3-based-model-for-enhanced","slug":"a-layoutlmv3-based-model-for-enhanced","title":"A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents","date":"2024-04-16","arxiv_id":"2404.10848","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/reading-order-matters-information-extraction","slug":"reading-order-matters-information-extraction","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","date":"2023-10-17","arxiv_id":"2310.11016","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/doctr-document-transformer-for-structured","slug":"doctr-document-transformer-for-structured","title":"DocTr: Document Transformer for Structured Information Extraction in Documents","date":"2023-07-16","arxiv_id":"2307.07929","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/layoutmask-enhance-text-layout-interaction-in","slug":"layoutmask-enhance-text-layout-interaction-in","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","date":"2023-05-30","arxiv_id":"2305.18721","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/geolayoutlm-geometric-pre-training-for-visual","slug":"geolayoutlm-geometric-pre-training-for-visual","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","date":"2023-04-21","arxiv_id":"2304.10759","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/structextv2-masked-visual-textual-prediction","slug":"structextv2-masked-visual-textual-prediction","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","date":"2023-03-01","arxiv_id":"2303.00289","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/dgcn-based-solution-for-entity-linking-on","slug":"dgcn-based-solution-for-entity-linking-on","title":"DGCN Based Solution for Entity Linking on Visual Rich Document","date":"2022-11-16","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ernie-layout-layout-knowledge-enhanced-pre","slug":"ernie-layout-layout-knowledge-enhanced-pre","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","date":"2022-10-12","arxiv_id":"2210.06155","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ernie-layout-layout-knowledge-enhanced-pre#ran","syntology_url":"https://syntology.ai/paper/2210.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06155"}}}},{"paper":"/paper/xdoc-unified-pre-training-for-cross-format","slug":"xdoc-unified-pre-training-for-cross-format","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","date":"2022-10-06","arxiv_id":"2210.02849","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/doc2graph-a-task-agnostic-document","slug":"doc2graph-a-task-agnostic-document","title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","date":"2022-08-23","arxiv_id":"2208.11168","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/layoutlmv3-pre-training-for-document-ai-with","slug":"layoutlmv3-pre-training-for-document-ai-with","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","date":"2022-04-18","arxiv_id":"2204.08387","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/lilt-a-simple-yet-effective-language","slug":"lilt-a-simple-yet-effective-language","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","date":"2022-02-28","arxiv_id":"2202.13669","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["jpwang/lilt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lilt-a-simple-yet-effective-language#ran","syntology_url":"https://syntology.ai/paper/2202.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13669"}}}},{"paper":"/paper/entity-relation-extraction-as-dependency","slug":"entity-relation-extraction-as-dependency","title":"Entity Relation Extraction as Dependency Parsing in Visually Rich Documents","date":"2021-10-19","arxiv_id":"2110.09915","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bros-a-layout-aware-pre-trained-language","slug":"bros-a-layout-aware-pre-trained-language","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","date":"2021-08-10","arxiv_id":"2108.04539","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["clovaai/bros"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bros-a-layout-aware-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2108.04539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04539"}}}},{"paper":"/paper/layoutlmv2-multi-modal-pre-training-for","slug":"layoutlmv2-multi-modal-pre-training-for","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","date":"2020-12-29","arxiv_id":"2012.14740","rows_on_this_dataset":3,"code_links":9,"syntology":null},{"paper":"/paper/layoutlm-pre-training-of-text-and-layout-for","slug":"layoutlm-pre-training-of-text-and-layout-for","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","date":"2019-12-31","arxiv_id":"1912.13318","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/layoutlm-pre-training-of-text-and-layout-for#ran","syntology_url":"https://syntology.ai/paper/1912.13318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.13318"}}}}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/funsd/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/funsd/papers/ran/1","json":"/dataset/funsd/papers/ran/1.json","rows":4}],"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":26,"samples_ran":25,"samples_constructed":0,"samples_ran_checked":19,"samples_ran_instrument_failed":6,"samples_unverified":1,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":3,"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/semantic-entity-labeling-on-funsd","since_archive":"/sota/semantic-entity-labeling-on-funsd#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/relation-extraction-on-funsd","since_archive":"/sota/relation-extraction-on-funsd#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":"b2c3c8f5d5a56a50c7aace8f842549b6bf80c19cbdca87854a196646eef6aaa1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}