Well yes, observation is the foundation of science.
There’s also this from the above paper:
‘High latency can have a negative impact on player enjoyment. After pressing a button, players expect that the effects of the corresponding action will appear instantaneously on the screen. If it takes too long, it can make the game unenjoyable, and in some cases, fully disrupt the gameplay. Here, we compare the RTT and jitter buffer delay metrics for different games and resolutions.
Dataset D8 presents the WebRTC internals that correspond to the same traffic captures as in Sections VII-B and VIII-A.
Figure 13a shows the ecdf of the RTT for both Tomb Raider and Spitlings during the ’play’ state at 1080p, as well as the RTT for Tomb Raider at 720p and 4K. All of them show similar RTT values, averaging between 10.28 ms and 12.30 ms. In all cases, the 95 % percentile of the RTT values is lower than the duration of a single video frame (16.67 ms), meaning that in these tests Stadia had the opportunity to interact with the player’s actions without any perceptible delay.
As expected, since the available link capacity was large enough, the game and resolution have no impact on the perceived latency. Only when the traffic load is close to the network capacity, such as in the previous section, the RTT is affected.’
I guess my perceptions are just not sufficiently enhanced to pick up on something happening at between 10.28 and 12.30 milliseconds…maybe that’s why I find it imperceptible!