💬 Feedback & Suggestions

Hi @seokwoo_song Please refer to this post for clarification on model limits: Clarification on Track 1 “8B parameter limit”

View post 0

💬 Feedback & Suggestions

Hello all, Thanks for the feedback. We’re reviewing it and exploring how we can better support you with the submission process.

View post 0

💬 Feedback & Suggestions

Hello @vk_c,

1. You can use this Discourse forum for all queries and feedback. Additionally, we have a Discord text channel for collaboration: AIcrowd
2. All the details on compute credits, how they are distributed, and the process to apply for them can be found here: 🪙 How to claim compute credits
3. The challenge is open to all individuals.

All the best!

View post 0

💬 Feedback & Suggestions

Hello @cheong_wei_xun
Details on compute credits and how to claim them can be found here: 🪙 How to claim compute credits

View post 0

Questions about tracks and credits

Hello!

1. Yes, a team is able to join and make submissions for both the tracks. Please ensure to form your team by 12th December 2025.
2. Details on the credits and how to claim them will be announced soon. Thank you for your patience and for participating in this challenge.

View post 0

When can we use the starter kit?

Hello @seokwoo_song

The starter kit can be found here: AIcrowd / Challenges / Orak Game Agent Challenge 2025 / orak-2025-starter-kit · GitLab

All the best!

View post 0

When will the sponsored Brev credits be made available?

Hello @inchangbaek,
Details on the credits and how to claim them will be announced soon. Thank you for your patience and for participating in this challenge.

View post 0

💬 Feedback & Suggestions

We are constantly trying to improve this challenge for you and would appreciate any feedback you might have!

Please reply to this thread with your suggestions and feedback on making the challenge better for you!

• What have been your major pain points so far?
• What would you like to see improved?

All The Best!

View post 0

👥 Looking for teammates?

Solving challenges is more fun with a team!

Introduce yourself here, and find others who are looking to team up!

• Introduce yourself and share a bit about your background.
• What brings you to this challenge?

Team registration deadline: 12 Dec 2025

All the best!

View post 0

🏆 Final Results & Next Steps

View post 0

Open-Source License

Hello @slimmer
MIT license would also be fine. Please use either Apache 2.0 or MIT license.

View post 0

Important Update

Update (October 10th, 2025)
This announcement has been superseded by a newer post:
Phase 2 — We hear you ! Here’s how we’re updating the plan
Please refer to the latest update for the final Phase 2 format, dataset, and scoring details.
(This original announcement remains for archival reference only.)

Please note some key updates about the challenge:

Phase 1 (Competition Phase)

• Ends on Sunday, 19 October 2025.
• Includes submission of the Solution Documentation.

Phase 2

• Expected to open between 20 and 22 October 2025, 23:59 UTC.
• The Solution Documentation deadline is extended to this window.

Phase 2 Format

• Multiple one-year datasets will be sliced into shorter, equal-length context windows.
• Slices will include a mix of previously seen and new sites.
• In Phase 2, participants will make a single prediction per time series. This is to prevent look-ahead.
• Phase 2 is designed to ensure fairness and reward models that can generalise, are context-aware, and are transferable across sites.

Scoring and Final Ranking

• The final ranking will factor in two components with equal weight:
  1. the score from the Phase 1 private dataset (SiteF), and
  2. the score from Phase 2.
• Within Phase 2, scores will be the equal-weighted average across all slices and sites.

Scoring Code and Starter Kit

• We will publish the scoring script and a minimal code sample in the starter kit.
• These materials will be available when Phase 2 opens.

Challenge Description Clarification

• Participants must predict each timestamp t₀ using only inputs where t_input ≤ t₀.
• Training data includes ground-truth time series and demand response flags.
• Models should learn consumption patterns both when demand response is inactive and when it is active.

Picture12390×632 35.4 KB

View post 2

Live Q&A with Challenge Organisers 📊 Join the Townhall on Sept 22!

Hello, The recording and slides are shared here: 📹 Townhall Recording & Q&A with Challenge Organisers | How to use digital twin data to predict demand response capacity

View post 0

Clarification on Future Data and Back Cast

View post 0

📹 Townhall Recording & Q&A with Challenge Organisers | How to use digital twin data to predict demand response capacity

Hi Ryan, Thanks for flagging this. The end date in the pill on challenge banner is now fixed.

View post 2

📹 Townhall Recording & Q&A with Challenge Organisers | How to use digital twin data to predict demand response capacity

Each participant can only make one submission.

• If you are competing as part of a team, your team submits one entry total.
• If you are competing individually, you submit one entry on your own.

View post 0

📹 Townhall Recording & Q&A with Challenge Organisers | How to use digital twin data to predict demand response capacity

Hello all,

Thank you to everyone who joined FlexTrack Challenge 2025 Townhall #1. In this session, we introduced the challenge and explored how digital twin data from commercial buildings can be used to forecast demand response flags and capacities.

If you missed it, you can catch up here:
Watch the recording: https://youtu.be/oKBcMxAQ3vg
Download the slides: Flextrack Townhall – Google Drive

Highlights from the session:

• Context on the evolving role of prosumers, batteries, and smart devices in the National Electricity Market (NEM)
• Overview of the synthetic dataset, generated from digital twins of commercial office buildings
• Key variables like weather, HVAC setpoints, internal loads, and demand response flags
• Approach to building generalizable, context-aware models that work across multiple building sites
• Details on evaluation metrics, submission format, and documentation requirements
• Q&A on temporal modelling, model transferability, and real-world use cases for aggregators and VPP operators
• New! Top teams will have the chance to co-author a research publication based on their solutions
• Synthetic data design: sites modeled across different Australian climate zones for realistic diversity
• Final submission reminder: competition phase ends October 19, 2025, with one combined CSV per team

If you have questions or ideas to share, drop them in the comments below so the community and organisers can help.

Team FlexTrack

View post 1

Live Q&A with Challenge Organisers 📊 Join the Townhall on Sept 22!

We will share the recording in the next day or two!

View post 4

New to the challenge - participation rules

Hi Priya,

The competition phase is open to all!

All the best

View post 0

Why does it show that the competition round is completed?

Hi @priya12
Yes, you can directly participate in Phase 2.

View post 0