{"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/knowledgehub-an-end-to-end-tool-for-assisted","title":"KnowledgeHub: An end-to-end Tool for Assisted Scientific Discovery","arxiv_id":"2406.00008","date":"2024-05-16","proceeding":null,"authors":["Shinnosuke Tanaka","James Barry","Vishnudev Kuruvanthodi","Movina Moses","Maxwell J. Giammona","Nathan Herr","Mohab Elkaref","Geeth de Mel"],"abstract":"This paper describes the KnowledgeHub tool, a scientific literature Information Extraction (IE) and Question Answering (QA) pipeline. This is achieved by supporting the ingestion of PDF documents that are converted to text and structured representations. An ontology can then be constructed where a user defines the types of entities and relationships they want to capture. A browser-based annotation tool enables annotating the contents of the PDF documents according to the ontology. Named Entity Recognition (NER) and Relation Classification (RC) models can be trained on the resulting annotations and can be used to annotate the unannotated portion of the documents. A knowledge graph is constructed from these entity and relation triples which can be queried to obtain insights from the data. Furthermore, we integrate a suite of Large Language Models (LLMs) that can be used for QA and summarisation that is grounded in the included documents via a retrieval component. KnowledgeHub is a unique tool that supports annotation, IE and QA, which gives the user full insight into the knowledge discovery pipeline.","url_abs":"https://arxiv.org/abs/2406.00008v2","url_pdf":"https://arxiv.org/pdf/2406.00008v2.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":[],"tasks":[{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"},{"task_slug":"scientific-discovery","task_name":"scientific discovery"}],"methods":[{"method_slug":"ontology","method_name":"Ontology"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.00008","atlas_url":"https://app.syntology.ai/?focus=2406.00008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00008"}},"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":"deterministic:regex_extraction","url":"https://github.com/kermitt2/grobid","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/pallets/flask","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran":8,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":11,"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":0,"samples":[{"code_sha256_prefix":"f1c2d2ed704ee037","entry":"extract_notes_from_file","repo":"kermitt2/grobid","repo_kind":"found_in_text","path":"grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/analyze_notes.py","file_url":"https://github.com/kermitt2/grobid/blob/HEAD/grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/analyze_notes.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f1c2d2ed704ee037"}},{"code_sha256_prefix":"aad2dd9c73594608","entry":"extract_notes_with_context","repo":"kermitt2/grobid","repo_kind":"found_in_text","path":"grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/detailed_analysis.py","file_url":"https://github.com/kermitt2/grobid/blob/HEAD/grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/detailed_analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aad2dd9c73594608"}},{"code_sha256_prefix":"778ca7dac99a1b9a","entry":"find_meaningful_matches","repo":"kermitt2/grobid","repo_kind":"found_in_text","path":"grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/detailed_analysis.py","file_url":"https://github.com/kermitt2/grobid/blob/HEAD/grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/detailed_analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"778ca7dac99a1b9a"}},{"code_sha256_prefix":"e0266593a34937b3","entry":"find_similar_content","repo":"kermitt2/grobid","repo_kind":"found_in_text","path":"grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/analyze_notes.py","file_url":"https://github.com/kermitt2/grobid/blob/HEAD/grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/analyze_notes.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e0266593a34937b3"}},{"code_sha256_prefix":"fd6e58cb31c7aaac","entry":"get_load_dotenv","repo":"pallets/flask","repo_kind":"found_in_text","path":"src/flask/helpers.py","file_url":"https://github.com/pallets/flask/blob/HEAD/src/flask/helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fd6e58cb31c7aaac"}},{"code_sha256_prefix":"350bacaad3c6d13f","entry":"has_level_handler","repo":"pallets/flask","repo_kind":"found_in_text","path":"src/flask/logging.py","file_url":"https://github.com/pallets/flask/blob/HEAD/src/flask/logging.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"350bacaad3c6d13f"}},{"code_sha256_prefix":"354d9000bf5db282","entry":"normalize_text","repo":"kermitt2/grobid","repo_kind":"found_in_text","path":"grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/analyze_notes.py","file_url":"https://github.com/kermitt2/grobid/blob/HEAD/grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/analyze_notes.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"354d9000bf5db282"}},{"code_sha256_prefix":"b906150b79481c79","entry":"normalize_text","repo":"kermitt2/grobid","repo_kind":"found_in_text","path":"grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/detailed_analysis.py","file_url":"https://github.com/kermitt2/grobid/blob/HEAD/grobid-trainer/resources/dataset/segmentation/article/light/corpus/tei/detailed_analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b906150b79481c79"}},{"code_sha256_prefix":"49bdf356790b18d9","entry":"copy_current_request_context","repo":"pallets/flask","repo_kind":"found_in_text","path":"src/flask/ctx.py","file_url":"https://github.com/pallets/flask/blob/HEAD/src/flask/ctx.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"49bdf356790b18d9"}},{"code_sha256_prefix":"fe553530b7388d89","entry":"stream_with_context","repo":"pallets/flask","repo_kind":"found_in_text","path":"src/flask/helpers.py","file_url":"https://github.com/pallets/flask/blob/HEAD/src/flask/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"fe553530b7388d89"}},{"code_sha256_prefix":"dfd355bdaa47bdad","entry":"url_for","repo":"pallets/flask","repo_kind":"found_in_text","path":"src/flask/helpers.py","file_url":"https://github.com/pallets/flask/blob/HEAD/src/flask/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dfd355bdaa47bdad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}