Papers/2609.01673
🧪 Test?View on arXiv

CliffRank: A Dual-Branch Framework for Activity-Cliff Ranking Prediction

Not provided in the content

rankingactivity predictionmachine learningbiological data
2609.01673
Builder Relevance
70%
2h ago

Abstract

CliffRank combines absolute-activity regression with ranking-consistency learning to improve activity-cliff ranking predictions.

Reality Card

Core Claim

CliffRank achieved the highest mean Spearman correlation of 0.6890 on small-molecule datasets using PNA with activated Pairwise Preference Consistency after 120 epochs.

Method / Result

Mean Spearman correlation of 0.6890 on small-molecule datasets.

Limitations

High-quality data that resolve underlying mechanisms remain limited, affecting reproducibility.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers