#include<bits/stdc++.h>
#pragma GCC optimize("O3,unroll-loops")
#pragma GCC target("avx2,bmi,bmi2,lzcnt,p#include<bits/stdc++.h>
#pragma GCC optimize("O3,unroll-loops")
#pragma GCC target("avx2,bmi,bmi2,lzcnt,popcnt")
#define pb push_back
#define fi first
#define se second
using namespace std;
using ll = long long;
using ld = long double;
using ull = unsigned long long;
mt19937 rng(chrono::steady_clock::now().time_since_epoch().count());
const int maxN = 1e6 + 5;
const int mod = 1e9 + 7;
const ll oo = 1e18;
int k, m, n;
int a[maxN];
vector<vector<int>> vc;
int id[maxN];
const int base = 23543653;
int pw[maxN];
map<int, int> mp;
int inv[maxN];
int poww(int k, int n)
{
int res = 1;
while(n)
{
if(n & 1) res = (1ll * res * k) % mod;
k = (1ll * k * k) % mod;
n /= 2;
}
return res;
}
void ReadInput()
{
pw[0] = 1;
for(int i=1; i<maxN; i++)
pw[i] = (1ll * pw[i - 1] * base) % mod;
cin >> k >> m >> n;
vc.resize(m + 5, vector<int> (k + 5));
for(int i=1; i<=m; i++)
for(int j=1; j<=k; j++)
cin >> vc[i][j];
for(int i=1; i<=m; i++)
{
for(int j=1; j<=k; j++)
id[vc[i][j]] = j;
int val = 0;
for(int j=1; j<=k; j++)
val = (val + 1ll * id[j] * pw[j - 1] % mod) % mod;
mp[val] = i;
}
vector<pair<int, int>> val;
for(int i=1; i<=n; i++)
{
cin >> a[i];
val.pb({a[i], i});
}
sort(val.begin(), val.end());
for(int i=1; i<=n; i++)
a[val[i - 1].se] = i;
for(int i=0; i<=n; i++)
inv[i] = poww(pw[i], mod - 2);
}
int st[4 * maxN], lazy[4 * maxN];
inline void refind(int id)
{
st[id] = st[id * 2] + st[id * 2 + 1];
if(st[id] >= mod) st[id] -= mod;
}
inline void down(int id)
{
int t = lazy[id];
if(!t) return;
if(t > 0)
{
st[id * 2] = (1ll * st[id * 2] * pw[t]) % mod;
st[id * 2 + 1] = (1ll * st[id * 2 + 1] * pw[t]) % mod;
}
else if(t < 0)
{
st[id * 2] = (1ll * st[id * 2] * inv[-t]) % mod;
st[id * 2 + 1] = (1ll * st[id * 2 + 1] * inv[-t]) % mod;
}
lazy[id * 2] += t;
lazy[id * 2 + 1] += t;
lazy[id] = 0;
}
void update(int id, int l, int r, int pos, int val)
{
if(l == r && l == pos)
{
st[id] = val;
return;
}
down(id);
int mid = (l + r) / 2;
if(pos <= mid) update(id * 2, l, mid, pos, val);
else update(id * 2 + 1, mid + 1, r, pos, val);
refind(id);
}
void range_upd(int id, int l, int r, int u, int v, int val)
{
if(l > v || r < u || !st[id]) return;
if(l >= u && r <= v)
{
if(val > 0) st[id] = (1ll * st[id] * pw[val]) % mod;
else st[id] = (1ll * st[id] * inv[-val]) % mod;
lazy[id] += val;
return;
}
int mid = (l + r) / 2;
down(id);
range_upd(id * 2, l, mid, u, v, val);
range_upd(id * 2 + 1, mid + 1, r, u, v, val);
refind(id);
}
int get(int id, int l, int r, int u, int v)
{
if(l > v || r < u || !st[id]) return 0;
if(l >= u && r <= v) return st[id];
int mid = (l + r) / 2;
down(id);
auto L = get(id * 2, l, mid, u, v), R = get(id * 2 + 1, mid + 1, r, u, v);
int val = L + R;
if(val >= mod) val -= mod;
return val;
}
int bit[maxN];
inline void update(int pos, short val)
{
for(; pos <= n; pos += (pos & (-pos)))
bit[pos] += val;
}
inline int get(int pos)
{
int res = 0;
for(; pos; pos -= (pos & (-pos)))
res += bit[pos];
return res;
}
void Solve()
{
int cur = 0;
int tmp = 0;
for(int i=0; i<k; i++)
{
tmp += pw[i];
if(tmp >= mod) tmp -= mod;
}
for(int i=1; i<=n; i++)
{
if(i > k)
{
update(1, 1, n, a[i - k], 0);
update(a[i - k], -1);
// range_upd(1, 1, n, a[i - k] + 1, n, -1);
if(a[i - k] < a[i]) range_upd(1, 1, n, a[i - k] + 1, a[i], -1);
else if(a[i] - k > a[i]) range_upd(1, 1, n, a[i] + 1, a[i - k], 1);
// range_upd(1, 1, n, a[i - k] + 1, n, -1);
}
update(a[i], 1);
int val = get(a[i] - 1);
if(i <= k)
range_upd(1, 1, n, a[i] + 1, n, 1);
update(1, 1, n, a[i], (1ll * i * pw[val]) % mod);
int res = st[1];
if(i >= k)
{
res -= cur;
if(res < 0) res += mod;
if(mp[res])
{
int i = mp[res];
for(int j=1; j<=k; j++)
cout << vc[i][j] << " ";
return;
}
cur += tmp;
if(cur >= mod) cur -= mod;
}
}
// cout << 1.0 * clock() / CLOCKS_PER_SEC;return;
cout << 0;
}
#define taskname "sol"
int32_t main()
{
if (fopen(taskname ".inp", "r"))
{
freopen(taskname ".inp", "r", stdin);
//freopen(taskname ".out", "w", stdout);
}
ios_base::sync_with_stdio(false);
cin.tie(nullptr);
int T = 1;
//cin >> T;
for(int itest=1; itest<=T; itest++)
{
ReadInput();
Solve();
}
}
opcnt")
#define pb push_back
#define fi first
#define se second
using namespace std;
using ll = long long;
using ld = long double;
using ull = unsigned long long;
mt19937 rng(chrono::steady_clock::now().time_since_epoch().count());
const int maxN = 1e6 + 5;
const int mod = 1e9 + 7;
const ll oo = 1e18;
int k, m, n;
int a[maxN];
vector<vector<int>> vc;
int id[maxN];
const int base = 23543653;
int pw[maxN];
map<int, int> mp;
int inv[maxN];
int poww(int k, int n)
{
int res = 1;
while(n)
{
if(n & 1) res = (1ll * res * k) % mod;
k = (1ll * k * k) % mod;
n /= 2;
}
return res;
}
void ReadInput()
{
pw[0] = 1;
for(int i=1; i<maxN; i++)
pw[i] = (1ll * pw[i - 1] * base) % mod;
cin >> k >> m >> n;
vc.resize(m + 5, vector<int> (k + 5));
for(int i=1; i<=m; i++)
for(int j=1; j<=k; j++)
cin >> vc[i][j];
for(int i=1; i<=m; i++)
{
for(int j=1; j<=k; j++)
id[vc[i][j]] = j;
int val = 0;
for(int j=1; j<=k; j++)
val = (val + 1ll * id[j] * pw[j - 1] % mod) % mod;
mp[val] = i;
}
vector<pair<int, int>> val;
for(int i=1; i<=n; i++)
{
cin >> a[i];
val.pb({a[i], i});
}
sort(val.begin(), val.end());
for(int i=1; i<=n; i++)
a[val[i - 1].se] = i;
int tmp = poww(base, mod - 2);
inv[0] = 1;
for(int i=1; i<=n; i++)
inv[i] = (1ll * inv[i - 1] * tmp) % mod;
}
int st[4 * maxN], lazy[4 * maxN];
inline void refind(int id)
{
st[id] = st[id * 2] + st[id * 2 + 1];
if(st[id] >= mod) st[id] -= mod;
}
inline void down(int id)
{
int t = lazy[id];
if(!t) return;
if(t > 0)
{
st[id * 2] = (1ll * st[id * 2] * pw[t]) % mod;
st[id * 2 + 1] = (1ll * st[id * 2 + 1] * pw[t]) % mod;
}
else if(t < 0)
{
st[id * 2] = (1ll * st[id * 2] * inv[-t]) % mod;
st[id * 2 + 1] = (1ll * st[id * 2 + 1] * inv[-t]) % mod;
}
lazy[id * 2] += t;
lazy[id * 2 + 1] += t;
lazy[id] = 0;
}
void update(int id, int l, int r, int pos, int val)
{
if(l == r && l == pos)
{
st[id] = val;
return;
}
down(id);
int mid = (l + r) / 2;
if(pos <= mid) update(id * 2, l, mid, pos, val);
else update(id * 2 + 1, mid + 1, r, pos, val);
refind(id);
}
void range_upd(int id, int l, int r, int u, int v, int val)
{
if(l > v || r < u || !st[id]) return;
if(l >= u && r <= v)
{
if(val > 0) st[id] = (1ll * st[id] * pw[val]) % mod;
else st[id] = (1ll * st[id] * inv[-val]) % mod;
lazy[id] += val;
return;
}
int mid = (l + r) / 2;
down(id);
range_upd(id * 2, l, mid, u, v, val);
range_upd(id * 2 + 1, mid + 1, r, u, v, val);
refind(id);
}
int get(int id, int l, int r, int u, int v)
{
if(l > v || r < u || !st[id]) return 0;
if(l >= u && r <= v) return st[id];
int mid = (l + r) / 2;
down(id);
auto L = get(id * 2, l, mid, u, v), R = get(id * 2 + 1, mid + 1, r, u, v);
int val = L + R;
if(val >= mod) val -= mod;
return val;
}
int bit[maxN];
inline void update(int pos, int val)
{
for(; pos <= n; pos += (pos & (-pos)))
bit[pos] += val;
}
inline int get(int pos)
{
int res = 0;
for(; pos; pos -= (pos & (-pos)))
res += bit[pos];
return res;
}
void Solve()
{
int cur = 0;
int tmp = 0;
for(int i=0; i<k; i++)
{
tmp += pw[i];
if(tmp >= mod) tmp -= mod;
}
for(int i=1; i<=n; i++)
{
if(i > k)
{
update(1, 1, n, a[i - k], 0);
update(a[i - k], -1);
// range_upd(1, 1, n, a[i - k] + 1, n, -1);
if(a[i - k] < a[i]) range_upd(1, 1, n, a[i - k] + 1, a[i], -1);
else if(a[i] - k > a[i]) range_upd(1, 1, n, a[i] + 1, a[i - k], 1);
// range_upd(1, 1, n, a[i - k] + 1, n, -1);
}
update(a[i], 1);
int val = get(a[i] - 1);
if(i <= k)
range_upd(1, 1, n, a[i] + 1, n, 1);
update(1, 1, n, a[i], (1ll * i * pw[val]) % mod);
int res = st[1];
if(i >= k)
{
res -= cur;
if(res < 0) res += mod;
if(mp[res])
{
int i = mp[res];
for(int j=1; j<=k; j++)
cout << vc[i][j] << " ";
return;
}
cur += tmp;
if(cur >= mod) cur -= mod;
}
}
// cout << 1.0 * clock() / CLOCKS_PER_SEC;return;
cout << 0;
}
#define taskname "sol"
int32_t main()
{
if (fopen(taskname ".inp", "r"))
{
freopen(taskname ".inp", "r", stdin);
//freopen(taskname ".out", "w", stdout);
}
ios_base::sync_with_stdio(false);
cin.tie(nullptr);
int T = 1;
//cin >> T;
for(int itest=1; itest<=T; itest++)
{
ReadInput();
Solve();
}
}