Movement Standards
Every rep in a Cence competition is judged against this document — by the vision engine on every attempt, and by human review on every podium. If a rep doesn’t count, the verdict names the exact standard below that it violated. No hidden rules, no judgment calls behind closed doors.
Every attempt begins from a valid start. The counter does not arm until the start position is confirmed.
Overhand, underhand, or neutral grip, hands anywhere from shoulder-width to one-and-a-half times shoulder-width. Grip style is not judged and does not affect the count.
The attempt starts from a free hang — feet clear of the floor and of any support, arms extended per §3.
The attempt arms only when a valid dead hang (§3.1) is held for one full second. A countdown confirms the counter is live.
The top of the rep. Cence judges chin clearance geometrically, and says exactly which points it compares.
At the top of the rep, the tracked chin point must pass above the horizontal line of the bar. This is the measure that decides the rep.
The engine tracks facial and shoulder landmarks and derives the chin position from them; it does not track the jawline directly. Bar height is established at arming from the wrist points at full hang and re-checked each rep, since the bar itself may not be reliably visible against a gym background.
Elbow angle is read at the top of every rep and must agree with the §2.2 ruling. A chin reading that clears the bar while the elbows remain near-extended indicates a tracking fault, not a rep.
Where the corroborating measure contradicts the ruling measure beyond published tolerance, the engine does not resolve the conflict in either direction. The rep is marked unresolved and the reason is shown.
Clearance is judged per rep, not on average. There is no “close enough” band.
At the bottom of every rep the elbows return to full extension — the arm reads straight at the tracked joints. This is the only position from which a new rep begins.
The bottom must be reached with visible control. Continuous cycling is allowed as long as full extension is genuinely reached each time.
PL v1.0 governs the strict pull-up. Kipping and butterfly are different movements and will have their own standard — they are not scored down here, they are out of scope.
Hip and knee drive used to generate upward momentum voids the rep. The engine reads hip travel relative to the shoulder line across the ascent; movement beyond the published tolerance flags the rep.
Legs may hang straight or stay bent at a fixed angle. Either is fine; changing between them mid-rep to generate drive is read under §4.1.
Grip width and left-right pulling asymmetry are not judged under PL v1.0. The side-on camera required by §6 cannot measure them, and Cence does not score what it cannot see.
There is no minimum or maximum rep speed, as long as every rep individually meets §2 and §3.
Rest is permitted at the full hang (§3.1). Releasing the bar ends the continuous set. Time continues to run; the attempt window is fixed regardless of rest taken.
A competition attempt is a single continuous recording within the published time cap for that week’s event. When the window closes, the counted total is final.
The engine can only verify what it can see. Camera setup is part of the standard.
Pull-up attempts are judged side-on only, camera 6–10 feet away with the bar and your full body in frame for the entire attempt. Chin clearance under §2.2 is a comparison of two heights; from the front, that comparison is unavailable at any level of tracking confidence. The engine confirms side-on placement before the attempt arms.
The bar line is established at arming and must remain in frame. An attempt that drifts out of frame cannot be re-anchored mid-set.
Every rep carries a tracking-confidence reading. Reps below the published confidence floor are not silently counted or discarded — they are flagged for review.
The camera does not move during the attempt. Handheld or repositioned recordings are not accepted for competition.
Weight classes only mean something if the weight is real — and in a bodyweight pull, weight is part of the feat.
The standards we hold the engine to — published, like everything else.
| Expert agreement | A movement’s automated scoring must agree with expert human judges at 95% or better before it decides prize outcomes without rep-level review. |
| False acceptance | No more than 2% of non-compliant reps may be accepted by automated scoring at competition grade. |
| Unresolved rate | The share of reps marked unresolved under §2.4 is published per event. A rising unresolved rate is a tracking problem we disclose, not one we quietly resolve into counts. |
| Until then | Where automated scoring hasn’t yet cleared these gates, human review covers the gap — and we say so, plainly, on the event page. |
| Versioning | This standard is versioned. Changes are published before they apply to any competition window — never mid-event. Attempts are always judged by the version in force when the event opened. |