Summary of SHL Challenge 2025: Locomotion and Transportation Mode Recognition Using Foundation Models
Bibliographic record
Abstract
The paper summarizes the contributions of participants to the seventh Sussex-Huawei Locomotion-Transportation (SHL) Recognition Challenge organized at the HASCA Workshop of UbiComp/ISWC 2025. Motivated by the growing interest in foundation models, particularly large language models, this year's edition will explore their application to transportation mode recognition. The goal is to recognize eight locomotion and transportation activities (Still, Walk, Run, Bike, Bus, Car, Train, Subway) from the motion (accelerometer, gyroscope, magnetometer) sensor data of a smartphone in a way which is user-independent and smartphone position-independent. The training data of a ''train'' user is available from smartphones placed at four body positions (Hand, Torso, Bag and Hips). The testing data originates from ''test'' users with a smartphone placed at three body positions (Torso, Bag or Hips). Participants will be required to develop a solution that leverages a recognized and well-established foundation model. We introduce the dataset used in the challenge and the protocol of the competition. We present a meta-analysis of the contributions from 7 submissions, their approaches, the software tools used, computational cost and the achieved results. Overall, three submissions achieved an F1 score between 80% and 90%, two between 70% and 80%, and two below 60%, with a latency of maximum of 5 seconds. The top performance is comparable to the results achieved with non-foundation models in previous challenges.
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 | 0.020 | 0.035 |
| Meta-epidemiology (narrow) | 0.009 | 0.001 |
| Meta-epidemiology (broad) | 0.006 | 0.004 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.006 | 0.007 |
| Open science | 0.007 | 0.008 |
| Research integrity | 0.006 | 0.005 |
| Insufficient payload (model declined to judge) | 0.024 | 0.036 |
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".