AI4EIC Hackathon: PID with the ePIC dRICH
Bibliographic record
Abstract
The inaugural AI4EIC Hackathon unfolded as a high-point satellite event during the second AI4EIC Workshop at William & Mary. The workshop itself boasted over two hundred participants in a hybrid format and delved into the myriad applications of Artificial Intelligence and Machine Learning (AI/ML) for the Electron-Ion Collider (EIC). This workshop aimed to catalyze advancements in AI/ML with applications ranging from advancements in accelerator and detector technologies—highlighted by the ongoing work on the ePIC detector and potential development of a second detector for the EIC—to data analytics, reconstruction, and particle identification, as well as the synergies between theoretical and experimental research. Complementing the technical agenda was an enriched educational outreach program that featured tutorials from leading AI/ML experts representing academia, national laboratories, and industry. The hackathon, held on the final day, showcased international participation with ten teams from around the globe. Each team, comprising up to four members, focused on the dual-radiator Ring Imaging Cherenkov (dRICH) detector, an integral part of the particle identification (PID) system in ePIC. The data for the hackathon were generated using the ePIC software suite. While the hackathon presented questions of increasing complexity, its challenges were designed with deliberate simplifications to serve as a preliminary step toward the integration of machine learning and deep learning techniques in PID with the dRICH detector. This article encapsulates the key findings and insights gained from this unique experience.
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 | 0.007 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.007 | 0.005 |
| Open science | 0.002 | 0.009 |
| Research integrity | 0.003 | 0.006 |
| Insufficient payload (model declined to judge) | 0.130 | 0.050 |
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".