The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale
Not on the map. Why?
Abstract (arXiv)
Scientific contributions rarely develop in isolation, but instead build upon prior discoveries. We formulate the task of automated technological roadmapping as extracting scientific contributions from scholarly articles and linking them to their prerequisites. We present the Scientific Contribution Graph, a large-scale resource containing 6 million detailed scientific contributions extracted from 655k open-access papers spanning computer science, medicine, biology, physics, chemistry, and other sciences, and connected by 36 million prerequisite edges. We further introduce scientific prerequisite prediction, a scientific discovery task in which models predict which existing technologies can enable future discoveries, and show that contemporary models are rapidly improving on this task, reaching 0.48 MAP when evaluated using temporally-filtered backtesting. We anticipate technological roadmapping resources such as this will support scientific impact assessment and automated scientific discovery.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 68 references that are in the map. First posted on arXiv 14 May 2026.
Builds on
28 of 68 references.
References · 28
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
- 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
- 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
- 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 363
- 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 322
- 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 210
- 2021Explaining Answers with Entailment Treescited by 152
- 2018Construction of the Literature Graph in Semantic Scholarcited by 118
- 2020SciREX: A Challenge Dataset for Document-Level Information Extractioncited by 113
16 more
- 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 97
- 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 93
- 2025CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentationcited by 57
- 2021End-to-End NLP Knowledge Graph Constructioncited by 21
- 2022CORWA: A Citation-Oriented Related Work Annotation Datasetcited by 17
- 2024Related Work and Citation Text Generation: A Surveycited by 17
- 2021SemEval-2021 Task 11: NLPContributionGraph -- Structuring Scholarly NLP Contributions for a Research Knowledge Graphcited by 16
- 2023GSAP-NER: A Novel Task, Corpus, and Baseline for Scholarly Entity Extraction Focused on Machine Learning Models and Datasetscited by 12
- 2024Large Language Models for Scientific Information Extraction: An Empirical Study for Virologycited by 12
- 2024The Nature of NLP: Analyzing Contributions in NLP Paperscited by 12
- 2025Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedbackcited by 12
- 2021Extracting Fine-Grained Knowledge Graphs of Scientific Claims: Dataset and Transformer-Based Resultscited by 10
- 2025HypER: Literature-grounded Hypothesis Generation and Distillation with Provenancecited by 10
- 2025Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Sciencecited by 9
- 2026GIANTS: Generative Insight Anticipation from Scientific Literaturecited by 8
- 2024Mitigating Consequences of Prestige in Citations of Publicationscited by 1
Built on by
Not cited yet.