{"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/rvl-cdip","name":"RVL-CDIP","full_name":"RVL-CDIP","description_markdown":"The **RVL-CDIP** dataset consists of scanned document images belonging to 16 classes such as letter, form, email, resume, memo, etc. The dataset has 320,000 training, 40,000 validation and 40,000 test images. The images are characterized by low quality, noise, and low resolution, typically 100 dpi.\r\n\r\nSource: [Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning](https://arxiv.org/abs/2009.14457)\r\nImage Source: [https://www.cs.cmu.edu/~aharley/rvl-cdip/](https://www.cs.cmu.edu/~aharley/rvl-cdip/)","description_withheld":null,"homepage":"https://www.cs.cmu.edu/~aharley/rvl-cdip/","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/evaluation-of-deep-convolutional-nets-for","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","first_author":"Adam W. Harley","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Document Image Classification","url":"/task/document-image-classification","datasets_with_task":"/datasets/task/document-image-classification"},{"name":"Document Layout Analysis","url":"/task/document-layout-analysis","datasets_with_task":"/datasets/task/document-layout-analysis"},{"name":"Multi-Modal Document Classification","url":"/task/multi-modal-document-classification","datasets_with_task":"/datasets/task/multi-modal-document-classification"}],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"}],"variants":["RVL-CDIP","rvl_cdip"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/rvl_cdip","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jordyvl/rvl-cdip_easyOCR","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/aharley/rvl_cdip","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jordyvl/rvl_cdip_easyocr","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/dvgodoy/rvl_cdip_mini","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":107,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/document-image-classification-on-rvl-cdip","task":"Document Image Classification","dataset_variant":"RVL-CDIP","rows":31,"metrics":["Accuracy","Parameters"],"first_row_in_archive_order":{"model":"EAML","paper":"/paper/eaml-ensemble-self-attention-based-mutual","metrics":{"Accuracy":"97.70%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-layout-analysis-on-rvl-cdip","task":"Document Layout Analysis","dataset_variant":"RVL-CDIP","rows":1,"metrics":["FAR","WAR"],"first_row_in_archive_order":{"model":"VisualWordGrid","paper":"/paper/visualwordgrid-information-extraction-from-1","metrics":{"FAR":"28.7","WAR":"18.7"},"code_links":[]},"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":25,"of":25,"counts":{"papers_with_a_benchmark_row":25,"with_a_code_link":18,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":25,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/dopta-improving-document-layout-analysis","slug":"dopta-improving-document-layout-analysis","title":"DoPTA: Improving Document Layout Analysis using Patch-Text Alignment","date":"2024-12-17","arxiv_id":"2412.12902","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/transferdoc-a-self-supervised-transferable","slug":"transferdoc-a-self-supervised-transferable","title":"GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification","date":"2023-09-11","arxiv_id":"2309.05756","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/eaml-ensemble-self-attention-based-mutual","slug":"eaml-ensemble-self-attention-based-mutual","title":"EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification","date":"2023-05-11","arxiv_id":"2305.06923","rows_on_this_dataset":1,"code_links":0,"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/multimodal-side-tuning-for-document","slug":"multimodal-side-tuning-for-document","title":"Multimodal Side-Tuning for Document Classification","date":"2023-01-16","arxiv_id":"2301.07502","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vlcdoc-vision-language-contrastive-pre","slug":"vlcdoc-vision-language-contrastive-pre","title":"VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification","date":"2022-05-24","arxiv_id":"2205.12029","rows_on_this_dataset":1,"code_links":0,"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/docxclassifier-high-performance-explainable","slug":"docxclassifier-high-performance-explainable","title":"DocXClassifier: High Performance Explainable Deep Network for Document Image Classification","date":"2022-03-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dit-self-supervised-pre-training-for-document","slug":"dit-self-supervised-pre-training-for-document","title":"DiT: Self-supervised Pre-training for Document Image Transformer","date":"2022-03-04","arxiv_id":"2203.02378","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"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/dit-self-supervised-pre-training-for-document#ran","syntology_url":"https://syntology.ai/paper/2203.02378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02378"}}}},{"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/donut-document-understanding-transformer","slug":"donut-document-understanding-transformer","title":"OCR-free Document Understanding Transformer","date":"2021-11-30","arxiv_id":"2111.15664","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["clovaai/donut"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/donut-document-understanding-transformer#ran","syntology_url":"https://syntology.ai/paper/2111.15664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15664"}}}},{"paper":"/paper/docformer-end-to-end-transformer-for-document","slug":"docformer-end-to-end-transformer-for-document","title":"DocFormer: End-to-End Transformer for Document Understanding","date":"2021-06-22","arxiv_id":"2106.11539","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/docformer-end-to-end-transformer-for-document#ran","syntology_url":"https://syntology.ai/paper/2106.11539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11539"}}}},{"paper":"/paper/beit-bert-pre-training-of-image-transformers","slug":"beit-bert-pre-training-of-image-transformers","title":"BEiT: BERT Pre-Training of Image Transformers","date":"2021-06-15","arxiv_id":"2106.08254","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/beit-bert-pre-training-of-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08254"}}}},{"paper":"/paper/layoutxlm-multimodal-pre-training-for","slug":"layoutxlm-multimodal-pre-training-for","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","date":"2021-04-18","arxiv_id":"2104.08836","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/going-full-tilt-boogie-on-document","slug":"going-full-tilt-boogie-on-document","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","date":"2021-02-18","arxiv_id":"2102.09550","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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":2,"code_links":9,"syntology":null},{"paper":"/paper/training-data-efficient-image-transformers","slug":"training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","arxiv_id":"2012.12877","rows_on_this_dataset":1,"code_links":40,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":12,"samples_constructed":1,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":3,"official":{"repos":["facebookresearch/deit"],"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/training-data-efficient-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2012.12877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.12877"}}}},{"paper":"/paper/visualwordgrid-information-extraction-from-1","slug":"visualwordgrid-information-extraction-from-1","title":"VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach","date":"2020-10-05","arxiv_id":"2010.02358","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-accuracy-and-speeding-up-document","slug":"improving-accuracy-and-speeding-up-document","title":"Improving accuracy and speeding up Document Image Classification through parallel systems","date":"2020-06-16","arxiv_id":"2006.09141","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-and-textual-deep-feature-fusion-for","slug":"visual-and-textual-deep-feature-fusion-for","title":"Visual and Textual Deep Feature Fusion for Document Image Classification","date":"2020-06-16","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"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"}}}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"official":{"repos":["pytorch/fairseq"],"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/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/paper/document-image-classification-with-intra","slug":"document-image-classification-with-intra","title":"Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks","date":"2018-01-29","arxiv_id":"1801.09321","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/document-image-classification-with-intra#ran","syntology_url":"https://syntology.ai/paper/1801.09321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.09321"}}}},{"paper":"/paper/analysis-of-convolutional-neural-networks-for","slug":"analysis-of-convolutional-neural-networks-for","title":"Analysis of Convolutional Neural Networks for Document Image Classification","date":"2017-08-10","arxiv_id":"1708.03273","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cutting-the-error-by-half-investigation-of","slug":"cutting-the-error-by-half-investigation-of","title":"Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification","date":"2017-04-11","arxiv_id":"1704.03557","rows_on_this_dataset":1,"code_links":5,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/dopta-improving-document-layout-analysis","slug":"dopta-improving-document-layout-analysis","title":"DoPTA: Improving Document Layout Analysis using Patch-Text Alignment","date":"2024-12-17","arxiv_id":"2412.12902","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/transferdoc-a-self-supervised-transferable","slug":"transferdoc-a-self-supervised-transferable","title":"GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification","date":"2023-09-11","arxiv_id":"2309.05756","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/eaml-ensemble-self-attention-based-mutual","slug":"eaml-ensemble-self-attention-based-mutual","title":"EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification","date":"2023-05-11","arxiv_id":"2305.06923","rows_on_this_dataset":1,"code_links":0,"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/multimodal-side-tuning-for-document","slug":"multimodal-side-tuning-for-document","title":"Multimodal Side-Tuning for Document Classification","date":"2023-01-16","arxiv_id":"2301.07502","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vlcdoc-vision-language-contrastive-pre","slug":"vlcdoc-vision-language-contrastive-pre","title":"VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification","date":"2022-05-24","arxiv_id":"2205.12029","rows_on_this_dataset":1,"code_links":0,"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/docxclassifier-high-performance-explainable","slug":"docxclassifier-high-performance-explainable","title":"DocXClassifier: High Performance Explainable Deep Network for Document Image Classification","date":"2022-03-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dit-self-supervised-pre-training-for-document","slug":"dit-self-supervised-pre-training-for-document","title":"DiT: Self-supervised Pre-training for Document Image Transformer","date":"2022-03-04","arxiv_id":"2203.02378","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"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/dit-self-supervised-pre-training-for-document#ran","syntology_url":"https://syntology.ai/paper/2203.02378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02378"}}}},{"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/donut-document-understanding-transformer","slug":"donut-document-understanding-transformer","title":"OCR-free Document Understanding Transformer","date":"2021-11-30","arxiv_id":"2111.15664","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["clovaai/donut"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/donut-document-understanding-transformer#ran","syntology_url":"https://syntology.ai/paper/2111.15664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15664"}}}},{"paper":"/paper/docformer-end-to-end-transformer-for-document","slug":"docformer-end-to-end-transformer-for-document","title":"DocFormer: End-to-End Transformer for Document Understanding","date":"2021-06-22","arxiv_id":"2106.11539","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/docformer-end-to-end-transformer-for-document#ran","syntology_url":"https://syntology.ai/paper/2106.11539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11539"}}}},{"paper":"/paper/beit-bert-pre-training-of-image-transformers","slug":"beit-bert-pre-training-of-image-transformers","title":"BEiT: BERT Pre-Training of Image Transformers","date":"2021-06-15","arxiv_id":"2106.08254","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/beit-bert-pre-training-of-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08254"}}}},{"paper":"/paper/layoutxlm-multimodal-pre-training-for","slug":"layoutxlm-multimodal-pre-training-for","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","date":"2021-04-18","arxiv_id":"2104.08836","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/going-full-tilt-boogie-on-document","slug":"going-full-tilt-boogie-on-document","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","date":"2021-02-18","arxiv_id":"2102.09550","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"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":2,"code_links":9,"syntology":null},{"paper":"/paper/training-data-efficient-image-transformers","slug":"training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","arxiv_id":"2012.12877","rows_on_this_dataset":1,"code_links":40,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":12,"samples_constructed":1,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":3,"official":{"repos":["facebookresearch/deit"],"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/training-data-efficient-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2012.12877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.12877"}}}},{"paper":"/paper/visualwordgrid-information-extraction-from-1","slug":"visualwordgrid-information-extraction-from-1","title":"VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach","date":"2020-10-05","arxiv_id":"2010.02358","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-accuracy-and-speeding-up-document","slug":"improving-accuracy-and-speeding-up-document","title":"Improving accuracy and speeding up Document Image Classification through parallel systems","date":"2020-06-16","arxiv_id":"2006.09141","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-and-textual-deep-feature-fusion-for","slug":"visual-and-textual-deep-feature-fusion-for","title":"Visual and Textual Deep Feature Fusion for Document Image Classification","date":"2020-06-16","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"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"}}}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"official":{"repos":["pytorch/fairseq"],"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/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/paper/document-image-classification-with-intra","slug":"document-image-classification-with-intra","title":"Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks","date":"2018-01-29","arxiv_id":"1801.09321","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/document-image-classification-with-intra#ran","syntology_url":"https://syntology.ai/paper/1801.09321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.09321"}}}},{"paper":"/paper/analysis-of-convolutional-neural-networks-for","slug":"analysis-of-convolutional-neural-networks-for","title":"Analysis of Convolutional Neural Networks for Document Image Classification","date":"2017-08-10","arxiv_id":"1708.03273","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cutting-the-error-by-half-investigation-of","slug":"cutting-the-error-by-half-investigation-of","title":"Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification","date":"2017-04-11","arxiv_id":"1704.03557","rows_on_this_dataset":1,"code_links":5,"syntology":null}],"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/dataset/rvl-cdip/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/rvl-cdip/papers/ran/1","json":"/dataset/rvl-cdip/papers/ran/1.json","rows":9}],"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":9,"samples_harvested":115,"samples_ran":80,"samples_constructed":19,"samples_ran_checked":70,"samples_ran_instrument_failed":10,"samples_unverified":35,"pointer_only_for_licence":29,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":9,"papers_with_a_run_with_no_instrument_failure":7,"papers_where_every_run_was_an_instrument_failure":2,"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":"4f299f0871098bbc41eaedb39c3e6dad6edc896b7a28f72beffcfc7477ec5790","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}