Designed around the power and the network we actually have.

Fixing the camera, controlling the lighting and taking one bottle at a time turns a hard computer vision problem, object detection in an uncontrolled scene, into a much easier one: single-object classification under known conditions. That is what lets a small quantized model run accurately on inexpensive hardware, without an accelerator and without a cloud call.

Machines that accept a whole bag of mixed material need much more compute, mechanism and maintenance, and produce a less trustworthy count for it.

Records are signed on the device the moment a deposit is verified, then written to a local hash-chained store. Each record includes the hash of the one before it, so any later alteration breaks the chain visibly. When connectivity returns, the queue submits to the ledger in order.

In practice the machine goes on paying and counting through an outage without losing its evidential integrity. Nothing is lost, and nothing can be quietly rewritten in the gap.

We record deposits on Hedera. The reason is narrow and specific: we want the recovery record to be checkable by people who have no reason to trust us.

A database we control is only ever as credible as our reputation. A public consensus record is checkable independently, with timestamps we can't backdate and entries we can't delete. For a claim that will end up in a compliance filing or an assurance process, that difference is what makes the record usable.

We use Hedera specifically for transaction costs low enough to justify writing a record for a single bottle, and finality fast enough to matter operationally.

We are not issuing a token to the public, and there is nothing here to speculate on. We use the ledger as a filing cabinet, nothing more.