{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/mineru-an-open-source-solution-for-precise","title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","arxiv_id":"2409.18839","date":"2024-09-27","proceeding":null,"authors":["Bin Wang","Chao Xu","Xiaomeng Zhao","Linke Ouyang","Fan Wu","Zhiyuan Zhao","Rui Xu","Kaiwen Liu","Yuan Qu","FuKai Shang","Bo Zhang","Liqun Wei","Zhihao Sui","Wei Li","Botian Shi","Yu Qiao","Dahua Lin","Conghui He"],"abstract":"Document content analysis has been a crucial research area in computer vision. Despite significant advancements in methods such as OCR, layout detection, and formula recognition, existing open-source solutions struggle to consistently deliver high-quality content extraction due to the diversity in document types and content. To address these challenges, we present MinerU, an open-source solution for high-precision document content extraction. MinerU leverages the sophisticated PDF-Extract-Kit models to extract content from diverse documents effectively and employs finely-tuned preprocessing and postprocessing rules to ensure the accuracy of the final results. Experimental results demonstrate that MinerU consistently achieves high performance across various document types, significantly enhancing the quality and consistency of content extraction. The MinerU open-source project is available at https://github.com/opendatalab/MinerU.","url_abs":"https://arxiv.org/abs/2409.18839v1","url_pdf":"https://arxiv.org/pdf/2409.18839v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mineru-an-open-source-solution-for-precise","repo_url":"https://github.com/opendatalab/mineru","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"mineru-an-open-source-solution-for-precise","repo_url":"https://github.com/opendatalab/PDF-Extract-Kit","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.18839","atlas_url":"https://app.syntology.ai/?focus=2409.18839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18839"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendatalab/PDF-Extract-Kit","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendatalab/mineru","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":8},"by_repo_kind":{"official":{"samples":8,"ran":8,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":8,"samples":[{"code_sha256_prefix":"b79b7d17cc70c726","entry":"colormap","repo":"opendatalab/PDF-Extract-Kit","repo_kind":"official","path":"pdf_extract_kit/utils/visualization.py","file_url":"https://github.com/opendatalab/PDF-Extract-Kit/blob/HEAD/pdf_extract_kit/utils/visualization.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b79b7d17cc70c726"}},{"code_sha256_prefix":"a18384902cc7a2ee","entry":"fix_text_block","repo":"opendatalab/PDF-Extract-Kit","repo_kind":"official","path":"pdf_extract_kit/utils/merge_blocks_and_spans.py","file_url":"https://github.com/opendatalab/PDF-Extract-Kit/blob/HEAD/pdf_extract_kit/utils/merge_blocks_and_spans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a18384902cc7a2ee"}},{"code_sha256_prefix":"e64b9a96e01e32e8","entry":"line_sort_spans_by_left_to_right","repo":"opendatalab/PDF-Extract-Kit","repo_kind":"official","path":"pdf_extract_kit/utils/merge_blocks_and_spans.py","file_url":"https://github.com/opendatalab/PDF-Extract-Kit/blob/HEAD/pdf_extract_kit/utils/merge_blocks_and_spans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e64b9a96e01e32e8"}},{"code_sha256_prefix":"1fa7fe0dde747633","entry":"load_config","repo":"opendatalab/PDF-Extract-Kit","repo_kind":"official","path":"pdf_extract_kit/utils/config_loader.py","file_url":"https://github.com/opendatalab/PDF-Extract-Kit/blob/HEAD/pdf_extract_kit/utils/config_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1fa7fe0dde747633"}},{"code_sha256_prefix":"43054df240bda638","entry":"locator_for_block","repo":"opendatalab/mineru","repo_kind":"official","path":"mineru/doclib/locators.py","file_url":"https://github.com/opendatalab/mineru/blob/HEAD/mineru/doclib/locators.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"43054df240bda638"}},{"code_sha256_prefix":"d756e662074a98d6","entry":"merge_spans_to_line","repo":"opendatalab/PDF-Extract-Kit","repo_kind":"official","path":"pdf_extract_kit/utils/merge_blocks_and_spans.py","file_url":"https://github.com/opendatalab/PDF-Extract-Kit/blob/HEAD/pdf_extract_kit/utils/merge_blocks_and_spans.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d756e662074a98d6"}},{"code_sha256_prefix":"5dc0a361cb211d20","entry":"read_endpoint_file","repo":"opendatalab/mineru","repo_kind":"official","path":"mineru/doclib/endpoint.py","file_url":"https://github.com/opendatalab/mineru/blob/HEAD/mineru/doclib/endpoint.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5dc0a361cb211d20"}},{"code_sha256_prefix":"b680afa6f11bd5cd","entry":"visualize_bbox","repo":"opendatalab/PDF-Extract-Kit","repo_kind":"official","path":"pdf_extract_kit/utils/visualization.py","file_url":"https://github.com/opendatalab/PDF-Extract-Kit/blob/HEAD/pdf_extract_kit/utils/visualization.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b680afa6f11bd5cd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}