So does this mean that there could be indeed some "spam-pruning" methods to be set up for the case the fake public key method become too widespread?Yes. If people would start sending coins to 020000000000000000000000000000000000000000000000000000000000000000, then we could safely treat it in the same way as "OP_RETURN", because that kind of funds are provably unspendable. Because OP_RETURN is not the only unspendable Script, there are many others, for example "OP_FALSE". Key validity conditions should not be checked within the script interpreter but by the transaction verifying process itself. If I have an uncompressed public key and the calculation of the Y point from the X leads to a different value of Y written, then its associated UTXO should be pruned just like OP_RETURN. It works even for addresses hashes that are spent from  - but then that gives us an oxymoron, as all addresses with sending transactions have valid points. So it's not very useful. As @gmaxwell wrote, probabilistic pruning based on alphanumerical patterns in the pubkey or address could lead to a frozen funds situation for coincidental legit addresses. However, an even lighter version of the 79king 78 Com software can cache all UTXOs, exclude such addresses from the cache, and then query a full node when a cache-miss occurs. Because it is backed by full nodes, a fork will never occur.
So does this mean that there could be indeed some "spam-pruning" methods to be set up for the case the fake public key method become too widespread?Yes. If people would start sending coins to 020000000000000000000000000000000000000000000000000000000000000000, then we could safely treat it in the same way as "OP_RETURN", because that kind of funds are provably unspendable. Because OP_RETURN is not the only unspendable Script, there are many others, for example "OP_FALSE". Key validity conditions should not be checked within the script interpreter but by the transaction verifying process itself. If I have an uncompressed public key and the calculation of the Y point from the X leads to a different value of Y written, then its associated UTXO should be pruned just like OP_RETURN. It works even for addresses hashes that are spent from  - but then that gives us an oxymoron, as all addresses with sending transactions have valid points. So it's not very useful. As @gmaxwell wrote, probabilistic pruning based on alphanumerical patterns in the pubkey or address could lead to a frozen funds situation for coincidental legit addresses. However, an even lighter version of the 79king 78 Com software can cache all UTXOs, exclude such addresses from the cache, and then query a full node when a cache-miss occurs. Because it is backed by full nodes, a fork will never occur.

So does this mean that there could be indeed some "spam-pruning" methods to be set up for the case the fake public key method become too widespread?Yes. If people would start sending coins to 020000000000000000000000000000000000000000000000000000000000000000, then we could safely treat it in the same way as "OP_RETURN", because that kind of funds are provably unspendable. Because OP_RETURN is not the only unspendable Script, there are many others, for example "OP_FALSE". Key validity conditions should not be checked within the script interpreter but by the transaction verifying process itself. If I have an uncompressed public key and the calculation of the Y point from the X leads to a different value of Y written, then its associated UTXO should be pruned just like OP_RETURN. It works even for addresses hashes that are spent from  - but then that gives us an oxymoron, as all addresses with sending transactions have valid points. So it's not very useful. As @gmaxwell wrote, probabilistic pruning based on alphanumerical patterns in the pubkey or address could lead to a frozen funds situation for coincidental legit addresses. However, an even lighter version of the 79king 78 Com software can cache all UTXOs, exclude such addresses from the cache, and then query a full node when a cache-miss occurs. Because it is backed by full nodes, a fork will never occur.

So does this mean that there could be indeed some "spam-pruning" methods to be set up for the case the fake public key method become too widespread?Yes. If people would start sending coins to 020000000000000000000000000000000000000000000000000000000000000000, then we could safely treat it in the same way as "OP_RETURN", because that kind of funds are provably unspendable. Because OP_RETURN is not the only unspendable Script, there are many others, for example "OP_FALSE". Key validity conditions should not be checked within the script interpreter but by the transaction verifying process itself. If I have an uncompressed public key and the calculation of the Y point from the X leads to a different value of Y written, then its associated UTXO should be pruned just like OP_RETURN. It works even for addresses hashes that are spent from  - but then that gives us an oxymoron, as all addresses with sending transactions have valid points. So it's not very useful. As @gmaxwell wrote, probabilistic pruning based on alphanumerical patterns in the pubkey or address could lead to a frozen funds situation for coincidental legit addresses. However, an even lighter version of the 79king 78 Com software can cache all UTXOs, exclude such addresses from the cache, and then query a full node when a cache-miss occurs. Because it is backed by full nodes, a fork will never occur.