Detailed results

Model scores, event counts and comparison checks.

Loading onset

REASSEMBLE · 83 recordings · 3,898 events · ±200 ms.

Swipe to see all columns.

REASSEMBLE · 83 recordings · sorted by F1
Rank / Model	F1	Precision	Recall	Median timing error, ms
1. Haptera	40.58%	33.94%	50.44%	80.39
2. Gemini 3.1 Pro Preview	21.30%	15.36%	34.71%	56.97
3. Open V-JEPA2	12.09%	42.24%	7.05%	87.31
4. Open DINOv2	4.15%	23.00%	2.28%	119.98

1. Haptera

F1: 40.58%
Precision: 33.94%
Recall: 50.44%
Median timing error, ms: 80.39

2. Gemini 3.1 Pro Preview

F1: 21.30%
Precision: 15.36%
Recall: 34.71%
Median timing error, ms: 56.97

3. Open V-JEPA2

F1: 12.09%
Precision: 42.24%
Recall: 7.05%
Median timing error, ms: 87.31

4. Open DINOv2

F1: 4.15%
Precision: 23.00%
Recall: 2.28%
Median timing error, ms: 119.98

Contact state

REASSEMBLE · the same 83 recordings.

Swipe to see all columns.

REASSEMBLE · 83 recordings · sorted by contact recall
Model	Contact precision	No-contact precision	Contact recall	Coverage
Haptera	92.74%	99.72%	51.82%	76.25%
Gemini 3.1 Pro Preview	24.62%	79.55%	22.93%	99.88%

Haptera

Contact precision: 92.74%
No-contact precision: 99.72%
Contact recall: 51.82%
Coverage: 76.25%

Gemini 3.1 Pro Preview

Contact precision: 24.62%
No-contact precision: 79.55%
Contact recall: 22.93%
Coverage: 99.88%

RH20T timing

F1 at ±200 ms across three robot setups.

Swipe to see all columns.

RH20T · F1 at ±200 ms · sorted by mean F1
Model	F1 (mean)	Setup 2	Setup 6	Setup 7
Haptera	2.26%	1.12%	3.24%	2.42%
Open DINOv2	0.85%	0.67%	0.90%	0.98%
Open V-JEPA2	0.27%	0.20%	0.23%	0.39%

Haptera

F1 (mean): 2.26%
Setup 2: 1.12%
Setup 6: 3.24%
Setup 7: 2.42%

Open DINOv2

F1 (mean): 0.85%
Setup 2: 0.67%
Setup 6: 0.90%
Setup 7: 0.98%

Open V-JEPA2

F1 (mean): 0.27%
Setup 2: 0.20%
Setup 6: 0.23%
Setup 7: 0.39%

False alarms

False detections during periods when the sensor reference reports no event.

Swipe to see all columns.

Sensor-defined quiet intervals
Model	False detections	False detections/quiet hour	95% interval	Recall @±200 ms	F1 @±200 ms
Haptera	330	139.80	[108.09, 174.35]	50.44%	40.58%
Gemini 3.1 Pro Preview	2,168	918.44	[844.90, 987.39]	34.71%	21.30%
Open V-JEPA2	32	13.56	[9.18, 18.08]	7.05%	12.09%
Open DINOv2	34	14.40	[9.89, 18.92]	2.28%	4.15%

Timing thresholds and event counts

Swipe to see all columns.

Loading onset · both timing tolerances
Model	Allowed timing error	Predicted events	Events found	False detections	Events missed	Precision	Recall	F1	Median timing error, ms
Haptera	±200 ms	5,792	1,966	3,826	1,932	33.94%	50.44%	40.58%	80.39
Gemini 3.1 Pro Preview	±200 ms	8,809	1,353	7,456	2,545	15.36%	34.71%	21.30%	56.97
Open V-JEPA2	±200 ms	651	275	376	3,623	42.24%	7.05%	12.09%	87.31
Open DINOv2	±200 ms	387	89	298	3,809	23.00%	2.28%	4.15%	119.98
Haptera	±100 ms	5,792	1,185	4,607	2,713	20.46%	30.40%	24.46%	47.96
Gemini 3.1 Pro Preview	±100 ms	8,809	977	7,832	2,921	11.09%	25.06%	15.38%	35.96
Open V-JEPA2	±100 ms	651	151	500	3,747	23.20%	3.87%	6.64%	44.87
Open DINOv2	±100 ms	387	31	356	3,867	8.01%	0.80%	1.45%	47.21

Midpoint and shifted-time controls

Compare the saved predictions with guesses at the middle of each time block and with shifted prediction times.

Swipe to see all columns.

Midpoint and shifted-time controls
Model	Allowed timing error	F1	Midpoint F1	Mean shifted F1
Haptera	±200 ms	40.58%	38.14%	6.88%
Haptera	±100 ms	24.46%	22.27%	3.48%
Gemini 3.1 Pro Preview	±200 ms	21.30%	20.96%	6.73%
Gemini 3.1 Pro Preview	±100 ms	15.38%	11.21%	3.54%

Events found and missed

FoundMissed

Allowed timing error±200 ms±100 ms

Haptera

1,966 found / 1,932 missed

Share found 50.44%False detections 3,826

Gemini 3.1 Pro Preview

1,353 found / 2,545 missed

Share found 34.71%False detections 7,456

Haptera

1,185 found / 2,713 missed

Share found 30.40%False detections 4,607

Gemini 3.1 Pro Preview

977 found / 2,921 missed

Share found 25.06%False detections 7,832

3,898 reference events across 83 recordings.