Messages classed as Not-Spam are pieces of mail which have been determined by the SpamExperts filter to be safe of unsolicited or inappropriate content.
Messages with a Main Class of Not-Spam can have any of the following Sub Classes:
Sub Class:
dnswl
The sending server's IP address is listed on several DNS-Allow lists. This means that no spam has been seen recently from this sending server.
Training the message as spam will correct the system.
Extra Class
The Extra Class of messages with this Sub Class will show the Allow list the sending server's IP is listed on,
batv
The message falsely claimed to be a bounce of a message that was sent by the user.
statistical-method1-cluster
The message content was statistically very similar to other messages that have been trained before on this cluster.
Extra Class
The Extra Class of messages with this Sub Class will show a number from 0 - 1 indicating how similar the message was.
statistical-method2-cluster
The message content was statistically very similar to other messages that have been trained before on this cluster.
Extra Class
The Extra Class of messages with this Sub Class will show a number from 0 - 1 indicating how similar the message was.
statistical-method1-global
The message content was statistically very similar to other messages that have been trained before globally.
Extra Class
The Extra Class of messages with this Sub Class will show a number from 0 - 1 indicating how similar the message was.
statistical-method2-global
The message content was statistically very similar to other messages that have been trained before globally.
Extra Class
The Extra Class of messages with this Sub Class will show a number from 0 - 1 indicating how similar the message was.
sender-reputation
The sender of the message was known to send predominately this type of mail.
combined-statistical
No specific classifiers were certain of the message's classification, and a best guess was made based on the statistical similarity to messages that have been trained in the past.
The "combined" result provides a weighted classification score of the different classifiers. Depending on the configured Quarantine Threshold, the message will be rejected as spam or accepted.
If the message is not legitimate, Train as spam. This will adjust the scoring in our various databases.
If the message is legitimate, Release and train from quarantine. This will adjust the scoring in our various databases.
heuristic-set1
The message matched multiple patterns that are commonly found in spam messages.
Extra Class
The Extra Class of messages with this Sub Class will show the pattern(s) found in spam messages.
heuristic-set2
The message matched multiple patterns that are commonly found in spam messages.
Extra Class
The Extra Class of messages with this Sub Class will show the pattern(s) found in spam messages.
combined
No specific classifiers were certain of the message's classification, and a best guess was made.
The "combined" result provides a weighted classification score of the different classifiers. Depending on the configured Quarantine Threshold, the message will be rejected as spam or accepted.
If the message is not legitimate, Train as spam. This will adjust the scoring in our various databases.
If the message is legitimate, Release and train from quarantine. This will adjust the scoring in our various databases.
Extra Class
The Extra Class for messages with this Sub Class will show the weighted classification score between 0 - 1.