TELLAUDIT REPORT № TA-2026-0042

RHP №21 · bullpen audit

PITCHES: 42 (24 FB / 18 CH)
CAMERA: SIDE VIEW · 30FPS
SESSION: APR 18, 2026
STATUS: FINAL

TIPPING DETECTED1 CONFIRMED TELL · 1 WATCH ITEM · 4 CUES CLEAN

An opponent watching nothing but your glove can call fastball-or-changeup 76% of the time.

What an opponent's model would score

CUE	PAIR	TRAIN ACC	HOLDOUT ACC	AUC	P	VERDICT
Glove drive (hand break)	FB / CH	78.6%	76.2%	0.91	<0.01	CONFIRMED
Leg-lift tempo	FB / CH	64.3%	57.1%	0.61	0.11	WEAK
Pre-set wiggle	FB / CH	57.1%	52.9%	0.58	0.31	CLEAN
Hand-break timing	FB / CH	55.0%	51.4%	0.55	0.44	CLEAN
Head position	FB / CH	52.4%	50.0%	0.52	0.62	CLEAN
Glove set height	FB / CH	51.2%	48.6%	0.50	0.71	CLEAN

Tell № 01 · glove drive at hand break

Your glove drives 2.2 inches past its fastball set at hand break, on 16 of 18 changeups in this session. Measured reach on the heater and overdrive on changeup.

CONFIRMED

SET01:08

LIFT02:04

BREAK02:11

EVIDENCE

PLANT02:26

RELEASE02:28

FR 070-078 · GLOVE REACHES PAST THE FB PATH BEFORE CH. AMBER BOX = DETECTION REGION. REAL POSE TRACK.

OPPONENT'S VIEW
"When the glove gets out front, changeup is coming. You can pick it up from the on-deck circle."

THE FIX · ONE-PATH DRIVE

Review the footage with your pitching coach, choose one glove-side cue, and test it in short bullpen sets. Film the reps and make sure the changeup matches the fastball at hand break.

AUC 0.91 · p<0.01 (PERMUTATION, N=2000) · TRAIN 78.6% (n=28) · HOLDOUT 76.2% (n=14)

Watch item · leg-lift tempo

Lift-to-break ran ~80ms slower before changeups in training data, but the edge didn't survive the holdout (57.1%, p=0.11). It's suggestive and still unproven. We'd need more pitches before we'd call it actionable. We track it across your next session, and if it's real, more pitches will say so.

WEAK

AUC 0.61 · p=0.11 · BELOW THE CONFIRMATION BAR

Tested clean

Glove set height

✓ NO SIGNAL

Pre-set wiggle

✓ NO SIGNAL

Hand-break timing

✓ NO SIGNAL

Head position

✓ NO SIGNAL

Four of six cue families came back indistinguishable. Those are real results too, and we're honest about them.

Methodology

SPLIT: 28 train / 14 holdout and stratified by pitch type. Reported accuracy is holdout-only.

SIGNIFICANCE: permutation test with 2,000 shuffles against the 50% baseline.

POSE PIPELINE: markerless keypoints from your video. The cues are interpretable geometry: heights, timings and widths.