Sports science

No number without a source.

Every sports-science constant in the engine has a citation in the literature — and a test that breaks if someone quietly changes it.

01 — The house rule

Three obligations per constant

Since May 2026 this is binding convention, not good intentions. Anyone touching a number satisfies all three — otherwise the change does not land.

64
sourced constants
19
topic areas
38
tests pinning those values

Counted on 2026-09-05 — all values taken from docs/SPORTS-SCIENCE-CITATIONS.md when the page was built.

  1. Citation right at the code

    Above every constant sits the original paper it came from — author, year, reference, with a DOI where one exists.

  2. A test that pins the value

    A dedicated test checks exactly that value or its property. If someone changes it because “an athlete sees it differently”, the test fails and forces an argument with the source.

  3. An entry in the citation index

    A central index ties together concept, source, the affected place in the code and the matching test. Nothing lives only in someone’s head.

02 — The building blocks

What the decision rests on

Nine model families, not a single readiness score. The blocks themselves are established training science — the work lies in bringing them together without contradictions, across several sports, and applying them to your history.

Training load

How much a session cost you — and how that accumulates over weeks into fitness and fatigue. Two moving averages with different memory: one forgets in days, the other in weeks.

Coggan (2003), Training and Racing using a Power Meter · Banister (1991), Modeling elite athletic performance · Calvert, Banister et al. (1976), IEEE Trans Syst Man Cybern · Morton, Fitz-Clarke, Banister (1990), J Appl Physiol 69(3):1171-7

Load spikes

The ratio of the past week to the past four weeks. The favourable range sits around 0.8 to 1.3; from about 1.5 injury risk rises sharply. That is exactly where the app puts the brakes on — even when you feel great.

Hulin, Gabbett et al. (2014), Br J Sports Med 48(8):708-12 · doi:10.1136/bjsports-2013-092524 · Gabbett (2016), Br J Sports Med 50(5):273-80

Recovery and heart-rate variability

The reference is not a textbook norm but your own rolling seven-day average. Only the deviation from it is a signal.

Plews, Laursen et al. (2013), Sports Med 43:773-81 · Plews, Laursen (2017), Int J Sports Physiol Perform · Tanaka, Monahan, Seals (2001), J Am Coll Cardiol 37(1):153-6 · Karvonen et al. (1957), Ann Med Exp Biol Fenn 35(3):307-15

Intensity distribution

The bulk of training belongs in the easy range, the small part in the genuinely hard — and the middle ground is the most common trap for ambitious athletes. The app watches this distribution across weeks, not single days.

Seiler (2010), Int J Sports Physiol Perform 5(3):276-91 · Stöggl, Sperlich (2014), Front Physiol 5:33 · doi:10.3389/fphys.2014.00033 · Daniels (2014), Daniels’ Running Formula · Friel (2009), The Cyclist’s Training Bible

A fitness model with three time constants

Endurance, neuromuscular capacity and fatigue build and decay at different speeds. So the model tracks three curves, not one — otherwise you explain a loss of form wrongly.

Busso (2003), Med Sci Sports Exerc · Fitz-Clarke, Morton, Banister (1994), J Appl Physiol 76(3):1151-9

Periodisation and race taper

Before a race, volume drops while intensity stays — and enough time sits between two hard sessions. Both are old, well-evidenced findings, not coaching folklore.

Mujika (2003), Int J Sports Med · Issurin (2010), Sports Med 40(3):189-206 · Bishop, Jones, Woods (2008), J Strength Cond Res 22(3):1015-24

Heat and altitude

Heat adaptation builds in days and decays over weeks; altitude only takes effect above a certain threshold. Both shift what is realistic today — so both are tracked rather than ignored.

Périard, Racinais, Sawka (2015), Scand J Med Sci Sports 25(S1):20-38 · doi:10.1111/sms.12408 · Daanen, Racinais, Périard (2018), Sports Med 48(2):409-430 · Rusko et al. (2004), J Sports Sci 22(10):928-945 · Chapman et al. (2014), J Appl Physiol 116(6):595-603 · Gore et al. (2013), Br J Sports Med 47(S1):i31-i39 · ACSM Position Stand (2007), Med Sci Sports Exerc 39(3):556-72 · Ely et al. (2007), Med Sci Sports Exerc 39(3):487-93

Strength as a discipline of its own

Here strength is not an add-on but a primary discipline — not least because it decays faster than endurance and therefore needs its own rules.

Helms et al. (2018), Sports 6(3):85 · Mujika, Padilla (2010), Sports Medicine 30(2):79-87

Safety thresholds

Individual signals can veto a hard session regardless of everything else. They are deliberately conservative and come from clinical guidelines, not training theory.

American Thoracic Society Guideline · Wallaert et al. (1990) · Apple Sleep-Apnoe-Hinweise (FDA De Novo, 2024) · Borg (1982), Med Sci Sports Exerc 14(5):377-81

03 — In everyday use

What this actually means

You feel strong, the app holds you back

Then your load spike is probably above the threshold. Perception lags behind load — the number does not.

Short night, variability below your baseline

Easy instead of hard. Not because one limit was crossed, but because both signals point the same way.

Ten days to race day

Volume comes down, intensity stays. Precisely the opposite of what most people do out of nerves.

04 — Limits

What this app is not

Not a medical device

DecisionEngine makes no diagnosis and replaces no medical assessment. Pain, persistent exhaustion or unusual readings belong with a doctor, not in an app.

The cited literature describes groups of people. You are one person. That is exactly why the app also learns from your own feedback — the literature provides the starting point, not the last word.

A word on the load-spike ratio: it is contested in the field — Impellizzeri and colleagues (2020) fundamentally criticised its statistical basis, and the original studies come from cricket and rugby, not endurance sport. We therefore use it as one signal among several, never as a verdict on its own, and with deliberately conservative thresholds.

And what is not yet properly evidenced in the implementation is deliberately left out: menstrual-cycle phases, for instance, are covered in the literature but not yet in the engine — half-done would be worse than not at all here.

05 — Further reading

The principal sources

A selection from the internal citation index. If you want to dig deeper, these references lead to the original papers.

  • Banister, E.W. (1991). Modeling elite athletic performance. Physiological Testing of Elite Athletes, Human Kinetics, 403-422.
  • Bishop, P.A., Jones, E., Woods, A.K. (2008). Recovery from training: a brief review. J Strength Cond Res 22(3):1015-24. doi:10.1519/JSC.0b013e31816eb518
  • Borg, G.A.V. (1982). Psychophysical bases of perceived exertion. Med Sci Sports Exerc 14(5):377-81. doi:10.1249/00005768-198205000-00012
  • Busso, T. (2003). Variable dose-response relationship between exercise training and performance. Med Sci Sports Exerc. doi:10.1249/01.MSS.0000074465.13621.37
  • Calvert, T.W., Banister, E.W. et al. (1976). A systems model of the effects of training on physical performance. IEEE Trans Syst Man Cybern SMC-6(2):94-102. doi:10.1109/TSMC.1976.5409179
  • Chapman, R.F. et al. (2014). Defining the “dose” of altitude training. J Appl Physiol 116(6):595-603. doi:10.1152/japplphysiol.00634.2013
  • Coggan, A.R. (2003). Training and Racing using a Power Meter.
  • Daanen, H.A.M., Racinais, S., Périard, J.D. (2018). Heat acclimation decay and re-induction. Sports Med 48(2):409-430. doi:10.1007/s40279-017-0808-x
  • Daniels, J.T. (2014). Daniels’ Running Formula (3rd ed.), Human Kinetics.
  • Ely, M.R. et al. (2007). Impact of weather on marathon-running performance. Med Sci Sports Exerc 39(3):487-93. doi:10.1249/mss.0b013e31802d3aba
  • Fitz-Clarke, J.R., Morton, R.H., Banister, E.W. (1991). Optimizing athletic performance by influence curves. J Appl Physiol 71(3):1151-1158. doi:10.1152/jappl.1991.71.3.1151
  • Friel, J. (2009). The Cyclist’s Training Bible (4th ed.), VeloPress.
  • Gabbett, T.J. (2016). The training-injury prevention paradox. Br J Sports Med 50(5):273-80. doi:10.1136/bjsports-2015-095788
  • Gore, C.J., Sharpe, K., Garvican-Lewis, L.A. et al. (2013). Altitude training and haemoglobin mass. Br J Sports Med 47(S1):i31-i39. doi:10.1136/bjsports-2013-092840
  • Helms, E.R. et al. (2018). RPE and velocity relationships for loading strength athletes. Sports 6(3):85.
  • Hulin, B.T., Gabbett, T.J. et al. (2014). Spikes in acute workload are associated with increased injury risk. Br J Sports Med 48(8):708-12. doi:10.1136/bjsports-2013-092524
  • Impellizzeri, F.M., Tenan, M.S., Kempton, T., Novak, A., Coutts, A.J. (2020). Acute:chronic workload ratio: conceptual issues and fundamental pitfalls. Int J Sports Physiol Perform 15(6):907-913. doi:10.1123/ijspp.2019-0864
  • Issurin, V.B. (2010). New horizons for the methodology and physiology of training periodization. Sports Med 40(3):189-206. doi:10.2165/11319770-000000000-00000
  • Karvonen, M.J. et al. (1957). The effects of training on heart rate. Ann Med Exp Biol Fenn 35(3):307-15.
  • Morton, R.H., Fitz-Clarke, J.R., Banister, E.W. (1990). Modeling human performance in running. J Appl Physiol 69(3):1171-7. doi:10.1152/jappl.1990.69.3.1171
  • Mujika, I. (2003). The effects of training and detraining on performance. Int J Sports Med.
  • Mujika, I., Padilla, S. (2000). Detraining: loss of training-induced adaptations. Sports Medicine 30(2):79-87. doi:10.2165/00007256-200030020-00002
  • Périard, J.D., Racinais, S., Sawka, M.N. (2015). Adaptations and mechanisms of human heat acclimatization. Scand J Med Sci Sports 25(S1):20-38. doi:10.1111/sms.12408
  • Plews, D.J., Laursen, P.B. et al. (2013). Training adaptation and heart rate variability in elite endurance athletes. Sports Med 43:773-81. doi:10.1007/s40279-013-0071-8
  • Rusko, H.K. et al. (2004). Altitude and endurance training. J Sports Sci 22(10):928-945. doi:10.1080/02640410400005933
  • Seiler, S. (2010). What is best practice for training intensity and duration distribution? Int J Sports Physiol Perform 5(3):276-91. doi:10.1123/ijspp.5.3.276
  • Stöggl, T., Sperlich, B. (2014). Polarized training has greater impact on key endurance variables. Front Physiol 5:33. doi:10.3389/fphys.2014.00033
  • Tanaka, H., Monahan, K.D., Seals, D.R. (2001). Age-predicted maximal heart rate revisited. J Am Coll Cardiol 37(1):153-6. doi:10.1016/S0735-1097(00)01054-8
  • American College of Sports Medicine (2007). Position stand: exertional heat illness during training and competition. Med Sci Sports Exerc 39(3):556-72. doi:10.1249/MSS.0b013e31802fa199
Convinced? Join the waitlist → How this app is built Back to the home page