{"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/icdar-2021-competition-on-scientific","title":"ICDAR 2021 Competition on Scientific Literature Parsing","arxiv_id":"2106.14616","date":"2021-06-08","proceeding":null,"authors":["Antonio Jimeno Yepes","Xu Zhong","Douglas Burdick"],"abstract":"Scientific literature contain important information related to cutting-edge innovations in diverse domains. Advances in natural language processing have been driving the fast development in automated information extraction from scientific literature. However, scientific literature is often available in unstructured PDF format. While PDF is great for preserving basic visual elements, such as characters, lines, shapes, etc., on a canvas for presentation to humans, automatic processing of the PDF format by machines presents many challenges. With over 2.5 trillion PDF documents in existence, these issues are prevalent in many other important application domains as well. Our ICDAR 2021 Scientific Literature Parsing Competition (ICDAR2021-SLP) aims to drive the advances specifically in document understanding. ICDAR2021-SLP leverages the PubLayNet and PubTabNet datasets, which provide hundreds of thousands of training and evaluation examples. In Task A, Document Layout Recognition, submissions with the highest performance combine object detection and specialised solutions for the different categories. In Task B, Table Recognition, top submissions rely on methods to identify table components and post-processing methods to generate the table structure and content. Results from both tasks show an impressive performance and opens the possibility for high performance practical applications.","url_abs":"https://arxiv.org/abs/2106.14616v1","url_pdf":"https://arxiv.org/pdf/2106.14616v1.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":"icdar-2021-competition-on-scientific","repo_url":"https://github.com/ibm-aur-nlp/PubLayNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"icdar-2021-competition-on-scientific","repo_url":"https://github.com/ibm-aur-nlp/PubTabNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"icdar-2021-competition-on-scientific","repo_url":"https://github.com/wenwenyu/MASTER-pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"table-recognition","task_name":"Table Recognition"},{"task_slug":"document-understanding","task_name":"document understanding"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.14616","atlas_url":"https://app.syntology.ai/?focus=2106.14616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14616"}},"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/ibm-aur-nlp/PubLayNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wenwenyu/MASTER-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibm-aur-nlp/PubTabNet","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"repositories":1}},"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":1,"samples":[{"code_sha256_prefix":"158bf4c3a5f11f04","entry":"conv1x1","repo":"wenwenyu/MASTER-pytorch","repo_kind":"official","path":"model/backbone.py","file_url":"https://github.com/wenwenyu/MASTER-pytorch/blob/HEAD/model/backbone.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"158bf4c3a5f11f04"}},{"code_sha256_prefix":"ec20f22a185cd708","entry":"conv3x3","repo":"wenwenyu/MASTER-pytorch","repo_kind":"official","path":"model/backbone.py","file_url":"https://github.com/wenwenyu/MASTER-pytorch/blob/HEAD/model/backbone.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec20f22a185cd708"}},{"code_sha256_prefix":"ef1e85717438b077","entry":"convert_PubLayNet_blob_to_target_blob","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ef1e85717438b077"}},{"code_sha256_prefix":"919b57fa5b33755b","entry":"clones","repo":"wenwenyu/MASTER-pytorch","repo_kind":"official","path":"model/transformer.py","file_url":"https://github.com/wenwenyu/MASTER-pytorch/blob/HEAD/model/transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"919b57fa5b33755b"}},{"code_sha256_prefix":"040902e0434e025a","entry":"pad_image_with_specific_base","repo":"wenwenyu/MASTER-pytorch","repo_kind":"official","path":"utils/GeometryUtils.py","file_url":"https://github.com/wenwenyu/MASTER-pytorch/blob/HEAD/utils/GeometryUtils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"040902e0434e025a"}},{"code_sha256_prefix":"353e3f0c62275e10","entry":"predict","repo":"wenwenyu/MASTER-pytorch","repo_kind":"official","path":"model/master.py","file_url":"https://github.com/wenwenyu/MASTER-pytorch/blob/HEAD/model/master.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"353e3f0c62275e10"}},{"code_sha256_prefix":"570d335fcbf53e29","entry":"resize_with_height","repo":"wenwenyu/MASTER-pytorch","repo_kind":"official","path":"utils/GeometryUtils.py","file_url":"https://github.com/wenwenyu/MASTER-pytorch/blob/HEAD/utils/GeometryUtils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"570d335fcbf53e29"}},{"code_sha256_prefix":"834af6288569bec9","entry":"subsequent_mask","repo":"wenwenyu/MASTER-pytorch","repo_kind":"official","path":"model/transformer.py","file_url":"https://github.com/wenwenyu/MASTER-pytorch/blob/HEAD/model/transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"834af6288569bec9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}