“Clutch or Cry” Team at TRACS @ WASP2025: A Hybrid Stacking Ensemble for Astrophysical Document Classification
Bibliographic record
Abstract
Automatically identifying telescopes and their roles within astrophysical literature is crucial for large-scale scientific analysis and tracking instrument usage patterns.This paper describes the system developed by the "Clutch or Cry" team for the Telescope Reference and Astronomy Categorization Shared task (TRACS) at WASP 2025 (Grezes et al., 2025).The task involved multi-class telescope identification (Task 1) and multi-label role classification (Task 2) within scientific papers.For Task 1, we employed a feature-engineering approach centered on document identifiers (Id suffix) combined with metadata and textual features, utilizing a tuned Random Forest classifier to achieve high accuracy.For the more complex Task 2, we utilized a carefully designed two-level stacking ensemble.Level-0 combines a rule-based keyword classifier with the domain-adapted astroBERT transformer, effectively fusing symbolic and semantic information.Level-1 uses four independent XGBoost meta-learners for targeted per-role optimization.These architectures address the primary challenges: handling long documents and managing severe class imbalance in Task 2 (notably 1:91 for instrumentation).Systematic optimization focused on mitigating imbalance significantly improved Task 2 performance for minority classes.This work validates the effectiveness of tailored approaches for distinct subtasks and targeted optimization for imbalanced classification in specialized scientific domains.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.007 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".