Kyumin Lee
Worcester Polytechnic Institute
WSDM 2027 · Hong Kong
WSDM Cup 2027: Call for Proposals
Propose a challenge that brings researchers and practitioners together around meaningful problems and new datasets.
Who can proposeIndustry & academia
Challenge proposals from institutions and research groups.
Challenge designData & evaluation
Describe the problem, data, metrics, and timeline.
PublicationArchival proposal
In a companion volume for WSDM workshops.
Important Dates
| Milestone | Date |
|---|---|
| Proposals due | Oct 20, 2026 |
| Proposal acceptance notifications | Oct 27, 2026 |
| Cup preparation | Oct. 27 – Nov. 15, 2026 |
| Cup starts | Nov 16, 2026 (Monday) |
| Cup ends | Feb 5, 2027 (Friday) |
| Winners announced | WSDM 2027 conference |
Note:
Exact dates will be confirmed upon finalization of the WSDM 2027 conference schedule.
Overview
We are pleased to open the call for proposals for hosting challenge problems for the WSDM Cup 2027, a
high-impact ML/AI competition event co-located with the WSDM 2027 main conference.
Competitions of this form are a crucial part of the research ecosystem, bringing together world-class experts
from around the world to independently evaluate their best ideas on important problems. Past experience has
shown this process to generate remarkable progress on specific challenges while achieving a depth of
validation that lives up to the highest ideals of empirical rigor for AI and ML as research fields.
We are seeking proposals for challenge problems and datasets from both industrial and academic institutions,
with an emphasis on novel challenges that address the most topical and pressing issues facing the WSDM
community today.
We are particularly interested in — but do not limit our attention to — tasks that leverage new insights and
solutions aided by Generative AI and emerging agentic systems. Much like many similar shared tasks, we view
these challenges as competitions that allow academic and industry practitioners to come together to explore
interesting problems and discuss successes, challenges, and future directions. Past WSDM Cup tasks have
provided new datasets and evaluation methodologies, and have introduced important tasks to audiences who may
have been previously unfamiliar with them.
We strongly encourage all interested institutions and research groups to submit proposals and be part of this
important challenge. Hosting a challenge is a fantastic way to bring a strong spotlight to under-studied areas
or emerging topics, to showcase expertise, to establish new benchmarks, and to contribute to advancing the
field on real-world problems. The winning proposal for the WSDM Cup Challenge will be an archival submission
included in a companion volume for WSDM workshops.
Requirements
Submissions will be reviewed on their ability to meet the following requirements:
Problem Description
A clear, well-justified description of the problem, including why it is broadly important for the WSDM
community in terms of novelty, significance, or timeliness.
Scope and Feasibility
A challenging but manageable and well-scoped problem. There should be a reasonable assessment that the
problem is both approachable and has sufficient headroom for advances and discoveries. An ideal challenge
will address new problems that have arisen due to the increasing prevalence of generative and agentic
systems, or offer a meaningful twist on an existing problem area that was previously infeasible.
Data Description
A concise and well-defined description of any data to be provided, including collection timelines (which
should allow adequate time for verification and leakage checks well in advance of the competition start
date), licensing considerations, and confirmation that any private test data has never appeared in any
published or internet-accessible form.
Accessibility
The proposal should describe how researchers who are generally familiar with AI and ML, but not
necessarily the specific problem domain, may engage with the challenge, and what additional materials will
be provided for context. Domain-specific tasks are welcome, provided that in-depth domain knowledge is not
required to analyze failure cases.
Evaluation
A clear description of evaluation metrics and protocols. Metrics and evaluation procedures must be
carefully thought through and described in exact detail. Automated evaluation is strongly preferred due to
considerations of cost, scale, and repeatability.
Timeline
A complete competition timeline covering data collection, preparation and validation, the competition
period, post-competition verification, and knowledge sharing following the close of the competition.
Submission
Submission Format
Proposals are not anonymous. Please include the names, affiliations, and contact information of all organizers
in your submission. This information helps us assess the team's expertise and capacity to run the challenge,
including data preparation, infrastructure support, and participant engagement throughout the competition period.
Please submit your proposals via CMT3 Microsoft CMT.
Your submission will form an archival submission to a
companion volume for WSDM 2027 workshops, further broadening awareness of your efforts.
We look forward to your proposals and to another exciting WSDM Cup.
WSDM Cup Chairs
Xinrun Wang
Singapore Management University