Individual role classification for players defending corners in football (soccer)
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Choosing the right defensive corner-strategy is a crucial task for each coach in professional football (soccer). Although corners are repeatable and static situations, due to their low conversion rates, several studies in literature failed to find useable insights about the efficiency of various corner strategies. Our work aims to fill this gap. We hand-label the role of each defensive player from 213 corners in 33 matches, where we then employ an augmentation strategy to increase the number of data points. By combining a convolutional neural network with a long short-term memory neural network, we are able to detect the defensive strategy of each player based on positional data. We identify which of seven well-established roles a defensive player conducted (player-marking, zonal-marking, placed for counterattack, back-space, short defender, near-post, and far-post). The model achieves an overall weighted accuracy of 89.3%, and in the case of player-marking, we are able to accurately detect which offensive player the defender is marking 80.8% of the time. The performance of the model is evaluated against a rule-based baseline model, as well as by an inter-labeller accuracy. We demonstrate that rules can also be used to support the labelling process and serve as a baseline for weak supervision approaches. We show three concrete use-cases on how this approach can support a more informed and fact-based decision making process.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it