Verify matched-valid demonstration throughput and end-to-end acquisition time

Verify the matched valid-demonstration throughput and end-to-end acquisition time for the Robot-only, Ego-R, and Ego-V acquisition configurations.

Background

The paper reports recorded episode rates and equipment costs for robot teleoperation (Robot-only), Rokoko-based human capture with a tactile glove (Ego-R), and vision-based inverse-kinematics human capture with a tactile glove (Ego-V). However, the table explicitly distinguishes recorded rates from matched valid-demonstration throughput and end-to-end time accounting, leaving those quantities unverified. Establishing them is necessary to substantiate the claimed efficiency advantage under a consistent validity and timing analysis.

References

Rates refer to recorded episodes, while matched valid-demo throughput and end-to-end time accounting remain [TO VERIFY].

— TACROSS: An Efficient and Low-Cost Scalable Human Touch System Across Heterogeneous Tactile Sensors for Dexterous Robot Learning  (2610.11945 - Chen et al., 8 Oct 2026) in Table caption, Section 3.1, “Data Acquisition Cost and Efficiency”

In addition, the absence of a robot-demonstration baseline leaves direct sample-efficiency comparisons between human and robot data for future work.

— Human2Dex: Dexterous Robot Learning from Wrist-Centric Human Demonstrations  (2610.13119 - Zhang et al., 9 Oct 2026) in Section Discussion and Limitations