Incremental sliding-window processing of evolving literature via CKM-Lite outperforms batch methods on predictive hit rate, hypothesis yield, and alignment while cutting token costs by 92%, with change-aware analysis revealing quality-coverage trade-offs.
human attention patterns
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Literature-grounded LLM synthesis of theories from 13.7k papers yields 2.9k theories that better match evidence and predict future results from 4.6k subsequent papers than parametric baselines.
citing papers explorer
-
Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature
Incremental sliding-window processing of evolving literature via CKM-Lite outperforms batch methods on predictive hit rate, hypothesis yield, and alignment while cutting token costs by 92%, with change-aware analysis revealing quality-coverage trade-offs.
-
Generating Literature-Driven Scientific Theories at Scale
Literature-grounded LLM synthesis of theories from 13.7k papers yields 2.9k theories that better match evidence and predict future results from 4.6k subsequent papers than parametric baselines.