Isaac Wasserman

I can confirm this behavior. In each of the attacks, `model(x)` is called. I believe this should be `model.predict(x)` instead.

It happens in checks.py: ``` def check_dynamic(model, x, is_tf_model=False, logger=None): if is_tf_model: msg = 'the check for dynamic defenses is not currently supported' else: msg = None sys.settrace(tracefunc) model(x) sys.settrace(None)...

Thanks for your response. My understanding is that messages that have the ID 295 should contain information about the gear status in the form of an integer 0-4. However, when...

Yes, very suspicious 🙃. Unfortunately, messages with the ID 956 have a similar problem. Decoding those messages yields: `{'SPORT_ON': 0, 'GEAR': 48, 'SPORT_GEAR': 3, 'SPORT_GEAR_ON': 0, 'DRIVE_ENGAGED': 0, 'ECON_ON': 0}`...

> Can you change gears to monitor change in signals? Unfortunately, I don't have access to the vehicle from which the data was collected. > are you sure that you...

The CXR model has a similar issue, predicting 7/699 positives. The DERM model does significantly better, predicting 95/135 positives.

It looks like the defaults just have Linux in mind, but you can override the executable location: ```python async def main(): # Start the browser with no additional webdriver configuration!...

Yeah, I haven't changed anything, but I'm noticing this as well. Have you found any solution?