Hume states that all reasoning related to questions of fact involves deriving a relationship between cause and effect (Hume, 296). However, the relationship between cause and effect is also not discovered by reason, but also by observation and experience (Hume, 297). Since they are related through observation alone, we can never know for sure whether causal relationships exist, and he claims that effects are distinct from their causes (Sepielli). He gives the example of two billiard balls, one of which moves in a straight line towards the other. He believes that hundreds of events can result from the collision of billiard balls, and we cannot be sure which one will occur (Hume, 298). Even if we looked at the billiard balls and the table (Sepielli), and observed the same observation each time the balls moved closer to each other, Hume believes that we can only use these observations to learn more about the balls that would be affected here, in the present, but we can't use them to know what will happen in the future. In this case, the problem of Hume's induction can be summarized as follows. If we truly believe that the future will be like the past, and we want to justify this belief, but we cannot justify it demonstratively or by producing similar observations repeatedly, then how are we supposed to justify this ?