Hello, I have been recently exploring the CloudKit and related frameworks. I got the communication with my app working, as well as with my website using CloudKitJS. Where I am struggling is the Server-to-Server communication (which I would need for exporting data from public database in csv. I have tried Python package requests-cloudkit - https://github.com/lionheart/requests-cloudkit, which others were suggesting. I have created a Server-to-Server token, and have copied only the key between START and END line once creating the eckey.pem file. I then got this code: from requests_cloudkit import CloudKitAuth from restmapper import restmapper import json KEY_ID = '[my key ID from CK Dashboard]' SECRET_FILE_KEY = 'eckey.pem' AUTH = CloudKitAuth(KEY_ID, SECRET_FILE_KEY) PARAMS = { 		'query':{ 				'recordType': '[my record type]' 		}, } CloudKit = restmapper.RestMapper("https://api.apple-cloudkit.com/database/1/[my container]/development/") cloudkit = CloudKit(auth=AUTH) response = cloudkit.POST.public.records.query(json.dumps(PARAMS)) I am then getting the 401 Authentication failed response. I am stuck on this for days, so I would be grateful for any help or advice. 😊

Could I please ask what is (at least plainly) the deep learning architecture of the Apple's custom pose models available through Vision (for example with the VNDetectHumanBodyPoseRequest)? Or whether it is based on some publicly used architecture (such as ResNet) only with modifications or custom Apple dataset? I was not able to find this information anywhere in the Apple documentation and it would be highly beneficial to know this, as we are using this data in a research about which we want to publish a paper. Thanks beforehand!