How often it counts the set right.
Current tracker counts compared with the counts lifters saved.
Data covers to .
One rep makes the difference.
Example: tracker 7, saved count 8.
An illustrative example, not a recorded set.
Loaded . Totals include sets counted by every earlier version of the rep counter.
422 Matched saved count
204 Did not match
Set agreement. Each set is counted once.
Count agreement by exercise. Rep differences share one scale: missed left, extra right. Saved counts are lifter reports, not independent video labels.
- Exercise
- pulldown_pullup
- Sets
- 106
- Matched
- 87 / 106
- Missed reps
- 59
- Extra reps
- 4
- Rep difference
- Exercise
- curl
- Sets
- 105
- Matched
- 72 / 105
- Missed reps
- 90
- Extra reps
- 15
- Rep difference
- Exercise
- bench_press
- Sets
- 92
- Matched
- 64 / 92
- Missed reps
- 44
- Extra reps
- 19
- Rep difference
- Exercise
- deadlift
- Sets
- 67
- Matched
- 44 / 67
- Missed reps
- 27
- Extra reps
- 16
- Rep difference
- Exercise
- lateral_raise
- Sets
- 61
- Matched
- 37 / 61
- Missed reps
- 53
- Extra reps
- 25
- Rep difference
- Exercise
- row
- Sets
- 58
- Matched
- 27 / 58
- Missed reps
- 97
- Extra reps
- 19
- Rep difference
- Exercise
- squat
- Sets
- 50
- Matched
- 45 / 50
- Missed reps
- 5
- Extra reps
- 2
- Rep difference
- Exercise
- triceps_extension
- Sets
- 45
- Matched
- 22 / 45
- Missed reps
- 95
- Extra reps
- 8
- Rep difference
- Exercise
- overhead_press
- Sets
- 37
- Matched
- 20 / 37
- Missed reps
- 17
- Extra reps
- 12
- Rep difference
- Exercise
- lunge
- Sets
- 5
- Matched
- 4 / 5
- Missed reps
- 2
- Extra reps
- 0
- Rep difference
| Exercise | Sets | Matched | Missed reps | Extra reps | Rep difference |
|---|---|---|---|---|---|
| pulldown_pullup | 106 | 87 / 106 | 59 | 4 | |
| curl | 105 | 72 / 105 | 90 | 15 | |
| bench_press | 92 | 64 / 92 | 44 | 19 | |
| deadlift | 67 | 44 / 67 | 27 | 16 | |
| lateral_raise | 61 | 37 / 61 | 53 | 25 | |
| row | 58 | 27 / 58 | 97 | 19 | |
| squat | 50 | 45 / 50 | 5 | 2 | |
| triceps_extension | 45 | 22 / 45 | 95 | 8 | |
| overhead_press | 37 | 20 / 37 | 17 | 12 | |
| lunge | 5 | 4 / 5 | 2 | 0 |
A matching count means the tracker and saved count agree. It does not independently establish a correct count or measure how accurate the reps-left estimate is. Results combine older versions of the tracker; they do not isolate the current one.
What a training plan looks like.
No real training plans exist yet, so this one is made up. A plan (lifters call it a “block”) is a run of training weeks. What is real is the shape: what the app records and the rule it uses to choose your weight. Below it, the research the estimate is built on.
Your weight follows your effort
The weight only goes up when the estimated effort showed you had room, and it waits until the lighter “deload” week is over. Week four of each wave is that deload week: the weight holds and the effort eases off on purpose. Its week tick is amber.
Every set in the plan. Reps left means how many more reps you could have done. The estimate comes from the app, not the camera, and is shown in purple.
- Week
- W1
- Heaviest set
- 210 lbs
- Target (reps left)
- 3
- Estimated (reps left)
- 6 (4–10)
- Decision
- Room · add weight
- Week
- W2
- Heaviest set
- 220 lbs
- Target (reps left)
- 2
- Estimated (reps left)
- 2 (1–3)
- Decision
- On target
- Week
- W3
- Heaviest set
- 225 lbs
- Target (reps left)
- 1
- Estimated (reps left)
- 4 (3–5)
- Decision
- Room · add weight
- Week
- W4
- Heaviest set
- 225 lbs
- Target (reps left)
- 4
- Estimated (reps left)
- 4 (3–5)
- Decision
- Deload · on target
- Week
- W5
- Heaviest set
- 235 lbs
- Target (reps left)
- 3
- Estimated (reps left)
- 6 (4–10)
- Decision
- Room · add weight
- Week
- W6
- Heaviest set
- 245 lbs
- Target (reps left)
- 2
- Estimated (reps left)
- 2 (1–3)
- Decision
- On target
- Week
- W7
- Heaviest set
- 250 lbs
- Target (reps left)
- 1
- Estimated (reps left)
- 0 (0–1)
- Decision
- On target
- Week
- W8
- Heaviest set
- 250 lbs
- Target (reps left)
- 4
- Estimated (reps left)
- 4 (3–5)
- Decision
- Deload · on target
- Week
- W9
- Heaviest set
- 255 lbs
- Target (reps left)
- 3
- Estimated (reps left)
- 2 (1–3)
- Decision
- On target
- Week
- W10
- Heaviest set
- 260 lbs
- Target (reps left)
- 2
- Estimated (reps left)
- 2 (1–3)
- Decision
- On target
- Week
- W11
- Heaviest set
- 265 lbs
- Target (reps left)
- 1
- Estimated (reps left)
- 1 (0–2)
- Decision
- On target
- Week
- W12
- Heaviest set
- 265 lbs
- Target (reps left)
- 4
- Estimated (reps left)
- 4 (3–5)
- Decision
- Deload · on target
| Week | Heaviest set | Target (reps left) | Estimated (reps left) | Decision |
|---|---|---|---|---|
| W1 | 210 lbs | 3 | 6 (4–10) | Room · add weight |
| W2 | 220 lbs | 2 | 2 (1–3) | On target |
| W3 | 225 lbs | 1 | 4 (3–5) | Room · add weight |
| W4 | 225 lbs | 4 | 4 (3–5) | Deload · on target |
| W5 | 235 lbs | 3 | 6 (4–10) | Room · add weight |
| W6 | 245 lbs | 2 | 2 (1–3) | On target |
| W7 | 250 lbs | 1 | 0 (0–1) | On target |
| W8 | 250 lbs | 4 | 4 (3–5) | Deload · on target |
| W9 | 255 lbs | 3 | 2 (1–3) | On target |
| W10 | 260 lbs | 2 | 2 (1–3) | On target |
| W11 | 265 lbs | 1 | 1 (0–2) | On target |
| W12 | 265 lbs | 4 | 4 (3–5) | Deload · on target |
Where the guess goes wrong.
What the lifter said they had left, next to what the app estimated, on the same sets. Rows are what the lifter said; columns are what the app estimated from the slowdown. Anything to the right of the diagonal had more left in it than the lifter believed. This grid is example data, drawn to show how the comparison reads, not a result.
Pro tracks this over time: your number beside the estimate, set after set, so the gap closes.
What the estimate stands on.
The link from slowdown to reps left is adapted conservatively from research on how fast the bar moves. Those studies measured the speed of the bar in a straight line, with known weights. CernoFit measures how fast your joints turn (angular joint velocity) from a phone camera, so the ranges are kept wide and the confidence honest.
Losing speed within a set is an established sign of fatigue in your muscles and nervous system[1], and the speed of the lifting phase falls as the reps you have left (reps in reserve, or RIR) run out, with strong relationships across the powerlifts[2].
Every slowdown range the estimate applies, read from packages/core.
- Slowdown
- ≥ 45%
- Reps left
- 0
- Range
- 0–1
- Confidence
- medium
- Basis
- at or near failure
- Slowdown
- ≥ 30%
- Reps left
- 1
- Range
- 0–2
- Confidence
- medium
- Basis
- pronounced slowdown, very close to failure
- Slowdown
- ≥ 20%
- Reps left
- 2
- Range
- 1–3
- Confidence
- medium
- Basis
- clear fatigue, a couple of reps left
- Slowdown
- ≥ 10%
- Reps left
- 4
- Range
- 3–5
- Confidence
- medium
- Basis
- moderate slowdown, several reps in reserve
- Slowdown
- ≥ 0%
- Reps left
- 6
- Range
- 4–10
- Confidence
- low
- Basis
- far from failure; estimates this far out are rough
| Slowdown | Reps left | Range | Confidence | Basis |
|---|---|---|---|---|
| ≥ 45% | 0 | 0–1 | medium | at or near failure |
| ≥ 30% | 1 | 0–2 | medium | pronounced slowdown, very close to failure |
| ≥ 20% | 2 | 1–3 | medium | clear fatigue, a couple of reps left |
| ≥ 10% | 4 | 3–5 | medium | moderate slowdown, several reps in reserve |
| ≥ 0% | 6 | 4–10 | low | far from failure; estimates this far out are rough |
Read from packages/core/src/rirEstimate.ts. Sets under 4 reps get one step lower confidence.
- [1]Sánchez-Medina & González-Badillo (2011). Velocity loss as an indicator of neuromuscular fatigue during resistance training. Med Sci Sports Exerc.
- [2]Zourdos et al. (2016). Novel resistance training-specific RPE scale measuring repetitions in reserve. J Strength Cond Res.
- [3]Zourdos et al. (2021). Proximity to failure and total repetitions performed in a set influence accuracy of intraset RIR-based RPE. J Strength Cond Res 35(2S).
- [4]Steele et al. (2017). Ability to predict repetitions to momentary failure is not perfectly accurate, though improves with resistance training experience. PeerJ.
- [5]Remmert et al. (2023). Changes in intraset RIR prediction accuracy during six weeks of bench press training in trained men. Percept Mot Skills.
- [6]Renner, Mitter & Baca (2024). Concurrent validity of novel smartphone-based apps monitoring barbell velocity in powerlifting exercises. PLOS One.
- [7]Stronger by Science (2024). How to perfect your ability to predict repetitions in reserve.