Anti-Cheating & Reproducibility

Verification & Rules

The Top 15 teams per track on the Kaggle private leaderboard submit a verification package. The Organizing Committee reproduces each solution from the submitted code, model artifacts, configuration, and setup instructions to verify successful execution and consistency with the team's selected Kaggle submission. The organizer-run private-data evaluation also takes place during this period.

What you submit

Submission Package

By Sep 18, 2026, 23:59 UTC, Top 15 teams upload:

  • code/ — full training and inference code
  • checkpoints/model.pth — final model weights
  • inference.sh — single entry script (data_dir → CSV)
  • README.md — reproducibility artifact
  • final_submission.csv — final Kaggle submission
  • honor_declaration.pdf — signed
How verification runs

Reproduction and Private-Data Evaluation

The committee follows each team's README and uses the submitted code, model artifacts, and configuration to run the submitted solution.

  • Verifies successful execution and consistency with the selected Kaggle submission
  • Organizer-run private-data evaluation on organizer-controlled private data (30% of final scoring)
  • Issues → committee contacts the team privately for clarification or a closed verification session
  • Teams that cannot be verified may be replaced by reserve teams

Track-Specific Rules

Both Tracks · Strictly Forbidden

  • Manual labeling of test samples
  • Using test set ground-truth labels in training (any form)
  • Multi-account registration or collusion between teams

Small Model Track · Additional Restrictions

  • No large pretrained backbones
  • No closed-source APIs or LLMs for development
  • No API / LLM labeling of training data

Large Model Track

  • Any pretrained model allowed (including LVLMs)
  • Closed-source APIs encouraged
  • LLM-based pseudo-labeling of training data permitted
  • Prompt engineering is part of the expected toolkit

IP & Code Usage (Kaggle Standard)

  • Participants retain full copyright on all submitted code and models
  • All competition data are the exclusive property of AIoT Lab. Please download and review the detailed data license and terms here: LICENSE.txt
  • Non-finalist code is destroyed after the competition — no public release
  • Finalist teams (Champion Award, Top 6 per track) must open-source their solution under Apache 2.0 license within 30 days of UbiComp 2026 finals — standard Kaggle Winner License practice
  • Finalist teams unwilling to open-source may decline their finalist status; the slot is then passed to the next-ranked team