CUDA copy linked lists from device to host

I am trying to populate a number of linked lists on the device and then return those lists back to the hosts.

From my understanding I need to allocate memory for my struct Element, but I don't know how to go about it since I will have many linked lists, each with an unknown number of elements. I've tried a couple of different things but it still didn't work. So I'm back to the starting point. Here is my code:

//NODE CLASS
class Node{
public:
    int x,y;
    Node *parent;
    __device__ __host__ Node(){}
    __device__ __host__ Node(int cX, int cY){x = cX; y = cY;}
    __device__ __host__ int get_row() { return x; }
    __device__ __host__ int get_col() { return y; }
};

//LINKED LIST
class LinkedList{
public:
    __device__ __host__ struct Element{
            Node n1;
            Element *next;
    };

    __device__ __host__ LinkedList(){
        head = NULL;
    }

    __device__ __host__ void addNode(Node n){
        Element *el = new Element();
        el->n1 = n;

        el->next = head;
        head = el;
    }

    __device__ __host__ Node popFirstNode(){
        Element *cur = head;
        Node n;

        if(cur != NULL){
            n = cur -> n1;
            head = head -> next;
        }

        delete cur;
        return n;
    }
    __device__ __host__ bool isEmpty(){
        Element *cur = head;

        if(cur == NULL){
            return true;
        }

        return false;
    }

    Element *head;
};

//LISTS
__global__ void listsKernel(LinkedList* d_Results, int numLists){
    int idx = blockIdx.x * blockDim.x + threadIdx.x;

    Node n(1,1);

    if(idx < numLists){
        d_Results[idx].addNode(n);
        d_Results[idx].addNode(n);
        d_Results[idx].addNode(n);
        d_Results[idx].addNode(n);
    }
}

int main(){
    int numLists = 10;
    size_t size = numLists * sizeof(LinkedList); 
    LinkedList curList;

    LinkedList* h_Results = (LinkedList*)malloc(size);
    LinkedList* d_Results;
    cudaMalloc((void**)&d_Results, size);

    listsKernel<<<256,256>>>(d_Results, numLists);
    cudaMemcpy(h_Results, d_Results, sizeof(LinkedList)*numLists, cudaMemcpyDeviceToHost);

    for(int i = 0; i < numLists; i++){
        curList = h_Results[i];
        while(curList.isEmpty() == false){
            Node n = curList.popFirstNode();
            std::cout << "x: " << n.get_row() << " y: " << n.get_col();
        }
    }
}

As you can see I'm trying to populate 10 linked lists on the device and then return them back to the host, but the code above results in unhandled exception - Access violation reading location. I am assuming it is not coping the pointers from the device.

Any help would be great.