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.
CKM-Lite’s broader distribution (11.2% below 3, 5.8% above
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.