Reproduce “Domain-Adaptive Pretraining Enhances Water Treatment Semantic Representation for Large-Scale Structured Literature Mining” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Mudi Zhai, Ruihong Qiu, Qingyun Zeng, T. David Waite, Bing-Jie Ni, Haoran Duan
WaterBERT adapts SciBERT to water-treatment literature, then extracts entities and relations to build a searchable knowledge graph. It was evaluated on screening, extraction, and retrieval tasks. On 100 pollutant-removal queries, graph-plus-text retrieval scored 77.7, versus 64.5 for the best text-based baseline. On 300 abstracts, extraction F1 was 69.3%, below GPT-5.6 Sol at 80.4%.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.