Built on peer-reviewed sports-science methodology

Compares your recent training load (acute, ~7 days) against your longer-term baseline (chronic, ~28 days) to flag when load is spiking faster than your body has adapted to. Thresholds follow the commonly cited Gabbett bands: 0.8–1.3 sweet spot, 1.3–1.5 caution, above 1.5 high risk. The average is EWMA, not a simple rolling mean.

1. [1]Gabbett TJ The training–injury prevention paradox: should athletes be training smarter and harder?. British Journal of Sports Medicine, 2016.
2. [2]Murray NB, Gabbett TJ, Townshend AD, Blanch P Calculating acute:chronic workload ratios using exponentially weighted moving averages provides a more sensitive indicator of injury likelihood than rolling averages. British Journal of Sports Medicine, 2017. · why EWMA over rolling averages

Load is computed from sets × RPE, not heart rate. No wearable required, and the number reflects what you actually did, quantified the way sports science has done it reliably for two decades.

1. [3]Foster C, et al. A new approach to monitoring exercise training. Journal of Strength and Conditioning Research, 2001.
2. [4]Borg GA Psychophysical bases of perceived exertion. Medicine & Science in Sports & Exercise, 1982. · the RPE scale itself

Mean daily load over 7 days divided by its standard deviation. Too little variation in training stress is flagged independently of how much you're doing: monotony is its own overtraining risk, not a side effect of high load.

1. [5]Foster C Monitoring training in athletes with reference to overtraining syndrome. Medicine & Science in Sports & Exercise, 1998. · original monotony/strain framework

Each muscle region learns its own decay time-constant from your soreness-report history, instead of applying one generic recovery curve to everyone. The same individualization idea as fitness-fatigue impulse-response modeling: your time constant, not a population average.

1. [6]Banister EW, Calvert TW, Savage MV, Bach T A systems model of training for athletic performance. Australian Journal of Sports Medicine, 1975. · origin of the fitness-fatigue framework
2. [7]Busso T Variable dose-response relationship between exercise training and performance. Medicine & Science in Sports & Exercise, 2003. · individualized time constants specifically

Heart rate variability and resting HR are pulled passively from Apple Health and read against your own trailing baseline, the established way to monitor training status systemically, without ever needing a chest strap or a manual entry.

1. [8]Plews DJ, Laursen PB, Stanley J, Kilding AE, Buchheit M Training adaptation and heart rate variability in elite endurance athletes: opening the door to effective monitoring. Sports Medicine, 2013.
2. [9]Buchheit M Monitoring training status with HR measures: do all roads lead to Rome?. Frontiers in Physiology, 2014.

An optional, short reaction-speed test in the daily check-in, based on the psychomotor vigilance test (PVT), which research shows is sensitive to sleep loss and reduced alertness. Kovura's version is a shortened adaptation: five rounds (plus two unscored practice taps the first time), scored as the median so one slow lapse doesn't skew it. It has not been validated on its own. Each reading is compared only against your own readings from the last 14 days, once you have 3 of them, and counts as one input to Recovery Score, not a diagnosis.

1. [10]Dinges DF, Powell JW Microcomputer analyses of performance on a portable, simple visual RT task during sustained operations. Behavior Research Methods, Instruments, and Computers, 1985. · the original psychomotor vigilance test
2. [11]Basner M, Dinges DF Maximizing sensitivity of the psychomotor vigilance test (PVT) to sleep loss. Sleep, 2011.
3. [12]Basner M, Mollicone D, Dinges DF Validity and sensitivity of a brief psychomotor vigilance test (PVT-B) to total and partial sleep deprivation. Acta Astronautica, 2011. · the brief version

An opt-in, 60-second fingertip scan over the phone's camera and flash, for days without watch HRV. It computes rMSSD, the beat-to-beat HRV measure used in sport. Research has compared smartphone camera rMSSD with a chest strap and ECG at rest and found small differences. That study used a different app and five-minute readings; Kovura's own scan processing hasn't been tested against a chest strap or ECG yet, so it's read only against your own earlier scans, after seven of them.

1. [13]Plews DJ, Scott B, Altini M, Wood M, Kilding AE, Laursen PB Comparison of heart-rate-variability recording with smartphone photoplethysmography, Polar H7 chest strap, and electrocardiography. International Journal of Sports Physiology and Performance, 2017.

Short sleep slows the processes muscles recover with: in one study, a single night without sleep cut muscle protein synthesis by about 18%. One ordinary short night does far less than that, so Kovura keeps the effect small: last night's total sleep against your 14-day average runs each muscle's recovery clock at 80% to 110% of its normal speed, and your own soreness check-ins tune how much sleep counts, down to nothing.

1. [14]Lamon S, Morabito A, Arentson-Lantz E, et al. The effect of acute sleep deprivation on skeletal muscle protein synthesis and the hormonal environment. Physiological Reports, 2021. · one night of total sleep deprivation