Efficient Context-Limited Telescope Bibliography Classification for the WASP-2025 Shared Task Using SciBERT

Author1, Author2, Author3, Author4, Author5

classificationSciBERTastronomytext processing

2609.01647

Builder Relevance

80%

2h ago

Abstract

This paper presents an efficient SciBERT-based approach for automatic classification of scientific papers related to telescopes, achieving a high macro F1 score.

Reality Card

Core Claim

The proposed SciBERT-based approach achieved a macro F1 score of 0.89, ranking at the top of the WASP-2025 leaderboard despite context-length constraints.

Method / Result

Achieved a macro F1 score of 0.89.

Limitations

The method faces limitations due to strict context-length constraints and the challenge of truncation affecting sample sizes.

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