{"url":"/sota/key-value-pair-extraction-on-sibr","task":{"name":"Key-value Pair Extraction","url":"/task/key-value-pair-extraction","note":null},"dataset":{"name":"SIBR","url":"/dataset/sibr"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"Extract key-value pairs from a form-like document. \r\n\r\nA prediction is considered TP if the predicted key and value contents match the ground truths. Key-value pair F1-score is employed as the metric.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["key-value pair F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"key-value pair F1":"higher"}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PEneo\n(LayoutLMv3_base_chinese)","metrics":{"key-value pair F1":"82.52"},"uses_additional_data":false,"paper_date":"2024-01-07","paper":"/paper/peneo-unifying-line-extraction-line-grouping","paper_url":"https://arxiv.org/abs/2401.03472v3","paper_title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","code":"https://github.com/ZeningLin/PEneo","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"PEneo\n(LiLT[InfoXLM]_base)","metrics":{"key-value pair F1":"82.36"},"uses_additional_data":false,"paper_date":"2024-01-07","paper":"/paper/peneo-unifying-line-extraction-line-grouping","paper_url":"https://arxiv.org/abs/2401.03472v3","paper_title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","code":"https://github.com/ZeningLin/PEneo","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"PEneo\n(LayoutXLM_base)","metrics":{"key-value pair F1":"82.23"},"uses_additional_data":false,"paper_date":"2024-01-07","paper":"/paper/peneo-unifying-line-extraction-line-grouping","paper_url":"https://arxiv.org/abs/2401.03472v3","paper_title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","code":"https://github.com/ZeningLin/PEneo","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"LayoutLMv3_base_chinese","metrics":{"key-value pair F1":"73.51"},"uses_additional_data":false,"paper_date":"2022-04-18","paper":"/paper/layoutlmv3-pre-training-for-document-ai-with","paper_url":"https://arxiv.org/abs/2204.08387v3","paper_title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","code":"https://github.com/huggingface/transformers","n_code_links":4,"syntology":null},{"rank_in_archive_order":5,"model":"LiLT\n([InfoXLM]_base)","metrics":{"key-value pair F1":"72.76"},"uses_additional_data":false,"paper_date":"2022-02-28","paper":"/paper/lilt-a-simple-yet-effective-language","paper_url":"https://arxiv.org/abs/2202.13669v1","paper_title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","code":"https://github.com/huggingface/transformers","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"LayoutXLM","metrics":{"key-value pair F1":"70.45"},"uses_additional_data":false,"paper_date":"2021-04-18","paper":"/paper/layoutxlm-multimodal-pre-training-for","paper_url":"https://arxiv.org/abs/2104.08836v3","paper_title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","code":"https://github.com/huggingface/transformers","n_code_links":6,"syntology":null},{"rank_in_archive_order":7,"model":"Donut","metrics":{"key-value pair F1":"17.26"},"uses_additional_data":false,"paper_date":"2021-11-30","paper":"/paper/donut-document-understanding-transformer","paper_url":"https://arxiv.org/abs/2111.15664v5","paper_title":"OCR-free Document Understanding Transformer","code":"https://github.com/clovaai/donut","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}