DS@GT ARC

FAQ

This FAQ answers common questions about ARC’s competitions, team roles, participation expectations, and how DS@GT ARC operates. If you are new to ARC, start with the Join page.

ARC’s annual cycle centers on CLEF, but we also participate in venues such as TREC, MediaEval, and NTCIR. Most questions below use CLEF as the primary example because it drives our publication schedule.

1. What is CLEF?

CLEF (Conference and Labs of the Evaluation Forum) is an annual independent peer-reviewed conference focused on information access systems in multilingual and multimodal contexts. It provides infrastructure for testing, tuning, and evaluating these systems, and for creating reusable test collections through community-based evaluation labs.

2. What CLEF lab/task should I pursue?

Each lab and task addresses a problem in a particular domain. Are you more interested in natural language processing? Computer vision? Biodiversity conservation? Medical applications? Multi-modality? You may find a summary of each lab in the last question of this FAQ. Review the task overview papers in the most recent CLEF working notes: Working Notes of CLEF 2025 (CEUR-WS Vol-4038).

3. How many tasks can I participate in CLEF?

There is no limit to tasks that someone can participate in. We strongly recommend first-time members not doing more than one task.

4. What’s the difference between a Lab Lead and a Lab member?

A Lab Lead is the main person responsible for delivering the task, including:

A Lab member is responsible for the following:

Lab Leads and members are expected to commit time, have strong programming skills, and be legitimately curious about the lab and task.

5. How do I become a Lab Lead for a task?

Lab Lead selection typically happens before the spring competition cycle begins. If you are interested in leading a future task, monitor the Join page and use the Contact page to reach the current ARC leadership team.

6. What is the time commitment required to participate?

The time commitment varies depending on your role and the effort you want to put in. However, to make a meaningful contribution, you should expect to dedicate around 100–150 hours throughout the project. Think of it as the equivalent of a 2–3 unit course, requiring consistent effort. Lab Leads require additional time to manage their tasks and coordinate with team members. This is the type of experience where you get out what you put in. Ultimately, your level of involvement is up to you, but consistent effort is key to gaining valuable experience and making an impact.

7. Can two teams participate in the same task?

No. A person can be part of one or more teams. But a team can only do one task.

8. Why can’t I edit the meeting documents?

Meeting documents and collaboration resources are typically shared with active participants after team formation. If you think you should already have access, ask in the DS@GT Slack or use the Contact page.

9. Is this opportunity only available for current students, or can alumni participate as well?

We welcome both current students and GT alumni to join our group. However, alumni must enroll in at least a 1-credit course (such as 8903) or a standard 3-credit course to gain access to the PACE cluster.

Also, all participants must be members of the Data Science @ Georgia Tech (DS@GT) club and have paid their membership dues. To join:

10. How can I earn academic credit through ARC?

The ARC academic pathway is one credit in Fall and three credits in Spring. Course registration, eligibility, and coursework details are still being finalized and will be shared when confirmed. Submit the Fall 2026 Interest Form for updates.

11. What kinds of labs are available through CLEF?

The table below summarizes the labs in the current CLEF 2026 program. Lab lineups shift year to year, so visit the CLEF 2026 labs page for each lab’s current tasks, call for participation, and official lab pages.

Lab Focus
BioASQ Large-scale biomedical semantic indexing and question answering
CheckThat! Claim verification and combating disinformation
ELOQUENT Evaluation of generative language model quality
eRisk Early risk detection on the internet (health and safety)
EXIST Sexism identification in social networks
FinMMEval Multilingual and multimodal evaluation for financial AI
HIPE Person–place relation extraction from multilingual historical texts
ImageCLEF Multimodal data annotation, indexing, and retrieval
JOKER Humor detection, search, and translation
LifeCLEF Biodiversity monitoring with AI-powered tools
LongEval Longitudinal evaluation of information retrieval model performance
PAN Stylometry and digital text forensics
qCLEF Quantum computing for information retrieval and recommender systems
SimpleText Scientific text simplification
TalentCLEF Skill and job-title intelligence for human capital management
Touché Argumentation retrieval and generation systems

Past CLEF working notes on CEUR-WS: CLEF 2025 (Vol-4038) · CLEF 2024 (Vol-3740) · CLEF 2023 (Vol-3497).