@Samwalton9-WMF

Based on the analysis, the following additions/modifications in addition to the initial criteria can improve the median risk score

• Reverted within 12 hours
• User edit count less 15 edits
• Time since user's first edit is less than 48 hours
• Absolute bytes difference is more than 5 bytes

• Restricting user related related metrics make minor improvements to the median risk, as majority of the reverted edits are made by anonymous users.
• While having at least an n number of absolute bytes difference, improves the median risk, a substantial number of edits are elimiated, as compared to the initial criteria.
• In addition to the time to revert, absolute bytes difference is only the control factor available for anonymous edits.

Here is the full analysis at various intervals for each dimension. We can discuss these results when we meet and decide on the adjustments.

After discussing with @Samwalton9-WMF

We have decided to finalize on the following criteria:

• Edit from account with <15 edits or anonymous user
• Reverted by a different editor
• Reverted within 12 hours
• User edit count less 15 edits
• Time since user's first edit is less than 48 hours
• Edit is in the main namespace

We decided not to add "Absolute bytes difference is more than 5 bytes" as we are not confident it will be a useful addition given the number of edits being eliminated from consideration, and subtle vandalism can be below 5 bytes.