#include<bits/stdc++.h>
using namespace std;
typedef long long ll;
typedef unsigned long long ull;
typedef long double ld;
typedef pair<int,int> PII;
typedef pair<ll,ll> PLL;
#define endl '\n'
#define debug(x) cout<<#x<<": "<<x<<endl
#define lowbit(x) (x&-x)
#define gcd __gcd
#define i128 __int128
#define rep(i, a, b) for(ll i = (a); i <= (b); i++)
#define per(i, a, b) for(ll i = (a); i >= (b); i--)
const int N=5e5+10,M=1e3+10;
const ll mod=1e9+7;
const ld eps=1e-12;
const ld pi=3.14159265358979;
mt19937_64 rnd(chrono::steady_clock::now().time_since_epoch().count());
//unordered_map<int,int>mp;
#define poly vector<int>

ll sum = 0;
ll f[N],g[N],inv[N];//注意int,下面用要强制转换成ll

void init_inverse1()//求1开始的连续逆元
{
	inv[1]=1;
	for(int i=2;i<N;i++)
		inv[i]=(ll)(mod-mod/i)*inv[mod%i]%mod;
}

void init_combinatorial()
{
	init_inverse1();//用init_inverse2()会稍微快一点
	f[0]=g[0]=1;
	for(int i=1;i<N;i++)
		f[i]=(ll)f[i-1]*i%mod;
	for(int i=1;i<N;i++)
		g[i]=(ll)g[i-1]*inv[i]%mod;
}

ll getC(int n,int m)//n大m小
{
	if(n<m) return 0;
	return ((ll)f[n]*g[m]%mod)*g[n-m]%mod;
}

ll qpow(ll a,ll b)
{
	ll res=1;
	a%=mod;
	while(b)
	{
		if(b&1) res=res*a%mod;
		a=a*a%mod;
		b>>=1;
	}
	return res;
}

void solve()
{
	ll n;
	cin >> n;
	sum+=n;
	bool vis[n + 5], finall[n + 5];
	memset(vis, 0, sizeof(vis));
	memset(finall, 0, sizeof(finall));
	ll w[n + 5];
	array<ll, 3> a[n + 5];
	ll b[n + 5];
	vector<ll>ve[n + 5];
	ll add[n + 5], q[n + 5];
	memset(add, 0, sizeof(add));
	memset(q, 0, sizeof(q));
	rep(i, 1, n) {
		cin >> a[i][0];
		a[i][2] = i;
		a[i][1] = 1;
		b[i] = a[i][0];
	}
	if(sum>=67) {
		cout << sum<<"||";
		rep(i,1,n) {
			cout<<a[i][0] <<"||";
		}
	}
	rep(i, 1, n) {
		ll x;
		cin >> x;
		ve[x].push_back(i);
		if(b[i] < b[x]) {
			a[i][1] = 0;
		}
	}
	rep(i, 1, n) {
		cin >> w[i];
	}
	rep(i, 1, n) {
		swap(a[i][0], a[i][1]);
	}
	sort(a + 1, a + n + 1);
	rep(i, 1, n) {
		if(a[i][0]) break;
		ll y = a[i][2];
		// debug(y);
		if(!vis[y]) add[y] = 1;
		vis[y] = 1;
		queue<int>qu;
		qu.push(y);
		while(!qu.empty()) {
			int cur = qu.front();
			qu.pop();
			if(finall[cur]) continue;
			finall[cur] = 1;
			for(auto t : ve[cur]) {
				if(!vis[t]) {
				    if(b[cur] > b[t]) {
						 add[t] = 1;
					 }
					 else if(b[cur] + w[cur] > b[t]) {
						 q[t] = q[cur] + 1;
						 add[t] = getC(n, q[t] + 1) * g[n];
						 add[t] %= mod;
						 add[t] *= f[n - q[t] - 1];
						 add[t] %= mod;
					 }
					 else {
						 add[t] = 0;
					 }	
					 vis[t] = 1;
				}
				if(!finall[t]) qu.push(t);
			}
		}
	}
	rep(i, 1, n) {
		// debug(b[i]);
		// debug(add[i]);
		// debug(w[i]);
		cout << (b[i] + (add[i] * w[i]) % mod) % mod << " \n"[i==n];
	}
	//  debug(((ll)2 + qpow(6, mod - 2)) % mod);
}

int main()
{
	ios::sync_with_stdio(0);
	cin.tie(0),cout.tie(0);
	
	int T=1;
	cin>>T;
	init_inverse1();
	init_combinatorial();
	while(T--)
	{
		
		solve();
	}
	return 0;
}