The fastest IRONMAN® race courses for age group triathletes are in the United States of America - an internet-based cross-sectional study using a machine learning approach with more than 670'000 race records (Preprint)
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
<sec> <title>BACKGROUND</title> The majority of participants in IRONMAN® triathlon races are age group athletes. We have extensive knowledge about recreational athletes' training and competition participation. Nonetheless, age group athletes have to achieve fast race times to qualify for the IRONMAN® World Championship in ‘IRONMAN® Hawaii’. They would therefore benefit from knowing where the fastest IRONMAN® race courses in the world are. </sec> <sec> <title>OBJECTIVE</title> The aim of the present study was to investigate where in the world the fastest IRONMAN® race courses for age group triathletes are. </sec> <sec> <title>METHODS</title> Data from 677,702 IRONMAN® age group finishers´ records (544,963 males and 132,739 females) from 228 countries participating in 67 different IRONMAN® event locations between 2002 and 2022 were analyzed. Data were analyzed using different machine learning (ML) regression models. Five different algorithms (Random Forest Regressor, XG Boost Regressor, Ada Boost Regressor, Cat Boot Regressor, and Decision Tree Regressor) were used. The models' used gender, country of origin, and event location as independent variables to predict the final race time. </sec> <sec> <title>RESULTS</title> Most of the successful IRONMAN® age group triathletes originated from the United States of America (USA) (274,553), followed by athletes from the United Kingdom (55,410) and Canada (38,264). Most of the athletes competed in Ironman® Wisconsin (38,545), followed by Ironman® Florida (38,157) and Ironman® Lake Placid (34,341). All five predictive models identified the ‘country’ as the most important predictor variable. A decision tree algorithm, trained with data from 2002 - 2022, forecasts that the best IRONMAN® age group finish times will be around 11:14:33 (h:min:s) and will be achieved by males in age groups 45 years or younger, not from the USA, the United Kingdom and Canada, and competing in IRONMAN® Wisconsin, Florida, Lake Placid, Arizona, Hawaii, or Austria. </sec> <sec> <title>CONCLUSIONS</title> The fastest race courses for age group IRONMAN® triathletes are in the USA (e.g., IRONMAN® Wisconsin, Florida, Lake Placid, Arizona, and Hawaii). However, the fastest IRONMAN® age group triathletes do not originate from the USA but from Australia, Germany, France, Spain, Sweden, Brazil, or Austria. Any IRONMAN® age group triathlete intending to achieve a fast IRONMAN® race time should consider participating in an IRONMAN® race held in the USA. </sec> <sec> <title>CLINICALTRIAL</title> - </sec>
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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