結果
| 問題 | No.3529 2p Teleportations |
| コンテスト | |
| ユーザー |
 yamada
|
| 提出日時 | 2026-05-04 23:53:34 |
| 言語 | C++23 (gcc 15.2.0 + boost 1.89.0) |
| 結果 |
AC
|
| 実行時間 | 236 ms / 2,000 ms |
| コード長 | 20,973 bytes |
| 記録 | |
| コンパイル時間 | 3,117 ms |
| コンパイル使用メモリ | 425,672 KB |
| 実行使用メモリ | 7,972 KB |
| 最終ジャッジ日時 | 2026-05-04 23:53:53 |
| 合計ジャッジ時間 | 14,276 ms |
|
ジャッジサーバーID （参考情報） |
judge1_0 / judge3_1 |
（要ログイン）
| ファイルパターン | 結果 |
|---|---|
| sample | AC * 1 |
| other | AC * 49 |
ソースコード
// Begin include: "../../template/template.hpp"
using namespace std;
// intrinstic
#include <immintrin.h>
#include <algorithm>
#include <array>
#include <bitset>
#include <cassert>
#include <cctype>
#include <cfenv>
#include <cfloat>
#include <chrono>
#include <cinttypes>
#include <climits>
#include <cmath>
#include <complex>
#include <cstdarg>
#include <cstddef>
#include <cstdint>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <deque>
#include <fstream>
#include <functional>
#include <initializer_list>
#include <iomanip>
#include <ios>
#include <iostream>
#include <istream>
#include <iterator>
#include <limits>
#include <list>
#include <map>
#include <memory>
#include <new>
#include <numeric>
#include <ostream>
#include <queue>
#include <random>
#include <set>
#include <sstream>
#include <stack>
#include <streambuf>
#include <string>
#include <tuple>
#include <type_traits>
#include <typeinfo>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>
// Begin include: "util.hpp"
namespace yamada {
using ll = long long;
using i64 = long long;
using u64 = unsigned long long;
using i128 = __int128_t;
using u128 = __uint128_t;
using lld = long double;
template <typename T>
using V = vector<T>;
template <typename T>
using VV = vector<vector<T>>;
template <typename T>
using VVV = vector<vector<vector<T>>>;
template <typename T>
using VVVV = vector<vector<vector<vector<T>>>>;
using vl = vector<long long>;
using vd = V<double>;
using vs = V<string>;
using vvl = vector<vector<long long>>;
using vvvl = vector<vector<vector<long long>>>;
using vvvvl = vector<vector<vector<vector<long long>>>>;
template <typename T>
using minpq = priority_queue<T, vector<T>, greater<T>>;
template <typename T>
using maxpq = priority_queue<T, vector<T>, less<T>>;
template <typename T, typename U>
struct P : pair<T, U> {
template <typename... Args>
P(Args... args) : pair<T, U>(args...) {}
using pair<T, U>::first;
using pair<T, U>::second;
P &operator+=(const P &r) {
first += r.first;
second += r.second;
return *this;
}
P &operator-=(const P &r) {
first -= r.first;
second -= r.second;
return *this;
}
P &operator*=(const P &r) {
first *= r.first;
second *= r.second;
return *this;
}
template <typename S>
P &operator*=(const S &r) {
first *= r, second *= r;
return *this;
}
P operator+(const P &r) const { return P(*this) += r; }
P operator-(const P &r) const { return P(*this) -= r; }
P operator*(const P &r) const { return P(*this) *= r; }
template <typename S>
P operator*(const S &r) const {
return P(*this) *= r;
}
P operator-() const { return P{-first, -second}; }
};
using pl = P<ll, ll>;
using vp = V<pl>;
using vvp = VV<pl>;
constexpr int inf = 1001001001;
constexpr long long infLL = 4004004004004004004LL;
template <typename T, typename U>
inline bool amin(T &x, U y) { return (y < x) ? (x = y, true) : false; }
template <typename T, typename U>
inline bool amax(T &x, U y) { return (x < y) ? (x = y, true) : false; }
template <typename T>
inline T Max(const vector<T> &v) { return *max_element(begin(v), end(v)); }
template <typename T>
inline T Min(const vector<T> &v) { return *min_element(begin(v), end(v)); }
template <typename T>
inline long long Sum(const vector<T> &v) { return accumulate(begin(v), end(v), T(0)); }
template <typename T>
int lb(const vector<T> &v, const T &a) { return lower_bound(begin(v), end(v), a) - begin(v); }
template <typename T>
int ub(const vector<T> &v, const T &a) { return upper_bound(begin(v), end(v), a) - begin(v); }
constexpr long long TEN(int n) {
long long ret = 1, x = 10;
for (; n; x *= x, n >>= 1) ret *= (n & 1 ? x : 1);
return ret;
}
template <typename T>
vector<T> mkrui(const vector<T> &v, bool rev = false) {
vector<T> ret(v.size() + 1);
if (rev) {
for (int i = int(v.size()) - 1; i >= 0; i--) ret[i] = v[i] + ret[i + 1];
} else {
for (int i = 0; i < int(v.size()); i++) ret[i + 1] = ret[i] + v[i];
}
return ret;
};
template <typename T>
vector<T> mkuni(const vector<T> &v) {
vector<T> ret(v);
sort(ret.begin(), ret.end());
ret.erase(unique(ret.begin(), ret.end()), ret.end());
return ret;
}
template <typename F>
vector<int> mkord(int N, F f) {
vector<int> ord(N);
iota(begin(ord), end(ord), 0);
sort(begin(ord), end(ord), f);
return ord;
}
template <typename T>
vector<int> mkinv(vector<T> &v) {
int max_val = *max_element(begin(v), end(v));
vector<int> inv(max_val + 1, -1);
for (int i = 0; i < (int)v.size(); i++) inv[v[i]] = i;
return inv;
}
vector<int> mkiota(int n) {
vector<int> ret(n);
iota(begin(ret), end(ret), 0);
return ret;
}
template <typename T>
T mkrev(const T &v) {
T w{v};
reverse(begin(w), end(w));
return w;
}
template <typename T>
bool nxp(T &v) { return next_permutation(begin(v), end(v)); }
// 返り値の型は入力の T に依存
// i 要素目 : [0, a[i])
template <typename T>
vector<vector<T>> product(const vector<T> &a) {
vector<vector<T>> ret;
vector<T> v;
auto dfs = [&](auto rc, int i) -> void {
if (i == (int)a.size()) {
ret.push_back(v);
return;
}
for (int j = 0; j < a[i]; j++) v.push_back(j), rc(rc, i + 1), v.pop_back();
};
dfs(dfs, 0);
return ret;
}
template <typename T, typename U>
vector<U> Digit(T a, const U &x, int siz = -1) {
vector<U> ret;
while (a > 0) {
ret.emplace_back(a % x);
a /= x;
}
if (siz >= 0) while ((int)ret.size() < siz) ret.emplace_back(0);
return ret;
}
// F : function(void(T&)), mod を取る操作
// T : 整数型のときはオーバーフローに注意する
template <typename T>
T Power(T a, long long n, const T &I, const function<void(T &)> &f) {
T res = I;
for (; n; f(a = a * a), n >>= 1) {
if (n & 1) f(res = res * a);
}
return res;
}
// T : 整数型のときはオーバーフローに注意する
template <typename T>
T Power(T a, long long n, const T &I = T{1}) {
return Power(a, n, I, function<void(T &)>{[](T &) -> void {}});
}
template <typename T>
T Rev(const T &v) {
T res = v;
reverse(begin(res), end(res));
return res;
}
template <typename T>
vector<T> Transpose(const vector<T> &v) {
using U = typename T::value_type;
if(v.empty()) return {};
int H = v.size(), W = v[0].size();
vector res(W, T(H, U{}));
for (int i = 0; i < H; i++) for (int j = 0; j < W; j++) res[j][i] = v[i][j];
return res;
}
template <typename T>
vector<T> Rotate(const vector<T> &v, int clockwise = true) {
using U = typename T::value_type;
int H = v.size(), W = v[0].size();
vector res(W, T(H, U{}));
for (int i = 0; i < H; i++) for (int j = 0; j < W; j++) {
if (clockwise) res[W - 1 - j][i] = v[i][j];
else res[j][H - 1 - i] = v[i][j];
}
return res;
}
template <typename T, typename F>
T bisect(T ok, T bad, F pred) {
if (ok == bad) return ok;
while (bad - ok > 1) { T mid = ok + (bad - ok) / 2; (pred(mid) ? ok : bad) = mid; }
return bad;
}
template <typename T, typename F>
T bisect_double(T ok, T bad, F pred, int iter = 100) {
if (ok == bad) return ok;
while (iter--) { T mid = ok + (bad - ok) / 2; (pred(mid) ? ok : bad) = mid; }
return bad;
}
template <typename T>
bool inLR(T L, T x, T R){ return (L <= x && x < R); }
bool YESNO(bool b) { std::cout << (b ? "YES\n" : "NO\n"); return b; }
bool YesNo(bool b) { std::cout << (b ? "Yes\n" : "No\n"); return b; }
template <typename mint>
std::string toFraction(mint a, int M) {
for (int deno = 1; deno <= M; deno++) {
mint inv = ((mint)deno).inverse();
for (int nume = -M; nume <= M; nume++) {
mint val = inv * nume;
if (val == a) {
if (deno == 1) return std::to_string(nume);
return std::to_string(nume) + "/" + std::to_string(deno);
}
}
}
return "NF";
}
template <typename mint>
void mout(mint a, int M = 100) { std::cout << toFraction(a, M) << "\n"; }
template <typename mint>
void mout(std::vector<mint> A, int M = 100) {
for (int i = 0; i < (int)A.size(); i++) {
std::cout << toFraction(A[i], M) << (i == (int)A.size() - 1 ? "\n" : " ");
}
}
bool is_square(uint64_t n) {
if (n < 2) return true;
uint64_t r = static_cast<uint64_t>(sqrtl(static_cast<long double>(n)));
if (r * r == n) return true;
++r;
return r * r == n;
}
template <typename T>
struct CumulativeSum {
std::vector<T> S;
CumulativeSum(std::vector<T> &A) {
int N = A.size();
S.resize(N + 1);
for (int i = 0; i < N; i++) S[i + 1] = S[i] + A[i];
}
T query(int l, int r) { return (l <= r ? S[r] - S[l] : (T)0); }
inline T operator()(int l, int r) { return query(l, r); }
};
long long floor(long long a, long long b) {
assert(b != 0);
if (b < 0) a = -a, b = -b;
return a / b - (a % b < 0);
}
long long under(long long a, long long b) {
assert(b != 0);
if (b < 0) a = -a, b = -b;
return a / b - (a % b <= 0);
}
long long ceil(long long a, long long b) {
assert(b != 0);
if (b < 0) a = -a, b = -b;
return a / b + (a % b > 0);
}
long long over(long long a, long long b) {
assert(b != 0);
if (b < 0) a = -a, b = -b;
return a / b + (a % b >= 0);
}
long long modulo(long long a, long long b) {
assert(b > 0);
long long c = a % b;
return c < 0 ? c + b : c;
}
} // namespace yamada
// End include: "util.hpp"
// Begin include: "bitop.hpp"
namespace yamada {
__attribute__((target("popcnt"))) inline int popcnt(const u64 &a) {
return __builtin_popcountll(a);
}
inline int lsb(const u64 &a) { return a ? __builtin_ctzll(a) : 64; }
inline int ctz(const u64 &a) { return a ? __builtin_ctzll(a) : 64; }
inline int msb(const u64 &a) { return a ? 63 - __builtin_clzll(a) : -1; }
template <typename T>
inline int gbit(const T &a, int i) {
return (a >> i) & 1;
}
template <typename T>
inline void sbit(T &a, int i, bool b) {
if (gbit(a, i) != b) a ^= T(1) << i;
}
constexpr long long PW(int n) { return 1LL << n; }
constexpr long long MSK(int n) { return (1LL << n) - 1; }
} // namespace yamada
// End include: "bitop.hpp"
// Begin include: "inout.hpp"
namespace yamada {
template <typename T, typename U>
ostream &operator<<(ostream &os, const pair<T, U> &p) {
os << p.first << " " << p.second;
return os;
}
template <typename T, typename U>
istream &operator>>(istream &is, pair<T, U> &p) {
is >> p.first >> p.second;
return is;
}
template <typename T>
ostream &operator<<(ostream &os, const vector<T> &v) {
int s = (int)v.size();
for (int i = 0; i < s; i++) os << (i ? " " : "") << v[i];
return os;
}
template <typename T>
istream &operator>>(istream &is, vector<T> &v) {
for (auto &x : v) is >> x;
return is;
}
istream &operator>>(istream &is, __int128_t &x) {
string S;
is >> S;
x = 0;
int flag = 0;
for (auto &c : S) {
if (c == '-') {
flag = true;
continue;
}
x *= 10;
x += c - '0';
}
if (flag) x = -x;
return is;
}
istream &operator>>(istream &is, __uint128_t &x) {
string S;
is >> S;
x = 0;
for (auto &c : S) {
x *= 10;
x += c - '0';
}
return is;
}
ostream &operator<<(ostream &os, __int128_t x) {
if (x == 0) return os << 0;
if (x < 0) os << '-', x = -x;
string S;
while (x) S.push_back('0' + x % 10), x /= 10;
reverse(begin(S), end(S));
return os << S;
}
ostream &operator<<(ostream &os, __uint128_t x) {
if (x == 0) return os << 0;
string S;
while (x) S.push_back('0' + x % 10), x /= 10;
reverse(begin(S), end(S));
return os << S;
}
void in() {}
template <typename T, class... U>
void in(T &t, U &...u) {
cin >> t;
in(u...);
}
void out() { cout << "\n"; }
template <typename T, class... U, char sep = ' '>
void out(const T &t, const U &...u) {
cout << t;
if (sizeof...(u)) cout << sep;
out(u...);
}
struct IoSetupYamada {
IoSetupYamada() {
cin.tie(nullptr);
ios::sync_with_stdio(false);
cout << fixed << setprecision(15);
cerr << fixed << setprecision(7);
}
} iosetupyamada;
} // namespace yamada
// End include: "inout.hpp"
// Begin include: "macro.hpp"
#define each(x, v) for (auto&& x : v)
#define each2(x, y, v) for (auto&& [x, y] : v)
#define each3(x, y, z, v) for (auto&& [x, y, z] : v)
#define all(v) (v).begin(), (v).end()
#define rep1(a) for (long long _ = 0; _ < (long long)(a); ++_)
#define rep2(i, a) for (long long i = 0; i < (long long)(a); ++i)
#define rep3(i, a, b) for (long long i = a; i < (long long)(b); ++i)
#define rep4(i, a, b, c) for (long long i = a; i < (long long)(b); i += c)
#define overload4(a, b, c, d, e, ...) e
#define rep(...) overload4(__VA_ARGS__, rep4, rep3, rep2, rep1)(__VA_ARGS__)
#define rep1r(a) for (long long i = (long long)(a)-1; i >= 0LL; --i)
#define rep2r(i, a) for (long long i = (long long)(a)-1; i >= 0LL; --i)
#define rep3r(i, a, b) for (long long i = (long long)(b)-1; i >= (long long)(a); --i)
#define overload3(a, b, c, d, ...) d
#define repr(...) overload3(__VA_ARGS__, rep3r, rep2r, rep1r)(__VA_ARGS__)
#define eb emplace_back
#define mkp make_pair
#define mkt make_tuple
#define fi first
#define se second
#define vv(type, name, h, ...) \
vector<vector<type> > name(h, vector<type>(__VA_ARGS__))
#define vvv(type, name, h, w, ...) \
vector<vector<vector<type>>> name( \
h, vector<vector<type>>(w, vector<type>(__VA_ARGS__)))
#define vvvv(type, name, a, b, c, ...) \
vector<vector<vector<vector<type>>>> name( \
a, vector<vector<vector<type>>>( \
b, vector<vector<type>>(c, vector<type>(__VA_ARGS__))))
#define ini(...) \
int __VA_ARGS__; \
in(__VA_ARGS__)
#define inl(...) \
long long __VA_ARGS__; \
in(__VA_ARGS__)
#define ins(...) \
string __VA_ARGS__; \
in(__VA_ARGS__)
#define in2(s, t) \
for (int i = 0; i < (int)s.size(); i++) { \
in(s[i], t[i]); \
}
#define in3(s, t, u) \
for (int i = 0; i < (int)s.size(); i++) { \
in(s[i], t[i], u[i]); \
}
#define in4(s, t, u, v) \
for (int i = 0; i < (int)s.size(); i++) { \
in(s[i], t[i], u[i], v[i]); \
}
#define die(...) \
do { \
yamada::out(__VA_ARGS__);\
return; \
} while (0)
// End include: "macro.hpp"
namespace yamada {
void solve();
}
int main() { yamada::solve(); }
// End include: "../../template/template.hpp"
// Begin include: "../../modint/arbitrary-modint.hpp"
// Begin include: "barrett-reduction.hpp"
#include <utility>
using namespace std;
struct Barrett {
using u32 = unsigned int;
using i64 = long long;
using u64 = unsigned long long;
u32 m;
u64 im;
Barrett() : m(), im() {}
Barrett(int n) : m(n), im(u64(-1) / m + 1) {}
constexpr inline i64 quo(u64 n) {
u64 x = u64((__uint128_t(n) * im) >> 64);
u32 r = n - x * m;
return m <= r ? x - 1 : x;
}
constexpr inline i64 rem(u64 n) {
u64 x = u64((__uint128_t(n) * im) >> 64);
u32 r = n - x * m;
return m <= r ? r + m : r;
}
constexpr inline pair<i64, int> quorem(u64 n) {
u64 x = u64((__uint128_t(n) * im) >> 64);
u32 r = n - x * m;
if (m <= r) return {x - 1, r + m};
return {x, r};
}
constexpr inline i64 pow(u64 n, i64 p) {
u32 a = rem(n), r = m == 1 ? 0 : 1;
while (p) {
if (p & 1) r = rem(u64(r) * a);
a = rem(u64(a) * a);
p >>= 1;
}
return r;
}
};
// End include: "barrett-reduction.hpp"
template <int id>
struct ArbitraryModIntBase {
int x;
ArbitraryModIntBase() : x(0) {}
ArbitraryModIntBase(int64_t y) {
int z = y % get_mod();
if (z < 0) z += get_mod();
x = z;
}
ArbitraryModIntBase &operator+=(const ArbitraryModIntBase &p) {
if ((x += p.x) >= get_mod()) x -= get_mod();
return *this;
}
ArbitraryModIntBase &operator-=(const ArbitraryModIntBase &p) {
if ((x += get_mod() - p.x) >= get_mod()) x -= get_mod();
return *this;
}
ArbitraryModIntBase &operator*=(const ArbitraryModIntBase &p) {
x = rem((unsigned long long)x * p.x);
return *this;
}
ArbitraryModIntBase &operator/=(const ArbitraryModIntBase &p) {
*this *= p.inverse();
return *this;
}
ArbitraryModIntBase operator-() const { return ArbitraryModIntBase(-x); }
ArbitraryModIntBase operator+() const { return *this; }
ArbitraryModIntBase operator+(const ArbitraryModIntBase &p) const {
return ArbitraryModIntBase(*this) += p;
}
ArbitraryModIntBase operator-(const ArbitraryModIntBase &p) const {
return ArbitraryModIntBase(*this) -= p;
}
ArbitraryModIntBase operator*(const ArbitraryModIntBase &p) const {
return ArbitraryModIntBase(*this) *= p;
}
ArbitraryModIntBase operator/(const ArbitraryModIntBase &p) const {
return ArbitraryModIntBase(*this) /= p;
}
bool operator==(const ArbitraryModIntBase &p) const { return x == p.x; }
bool operator!=(const ArbitraryModIntBase &p) const { return x != p.x; }
ArbitraryModIntBase inverse() const {
int a = x, b = get_mod(), u = 1, v = 0, t;
while (b > 0) {
t = a / b;
swap(a -= t * b, b);
swap(u -= t * v, v);
}
return ArbitraryModIntBase(u);
}
ArbitraryModIntBase pow(int64_t n) const {
ArbitraryModIntBase ret(1), mul(x);
while (n > 0) {
if (n & 1) ret *= mul;
mul *= mul;
n >>= 1;
}
return ret;
}
friend ostream &operator<<(ostream &os, const ArbitraryModIntBase &p) {
return os << p.x;
}
friend istream &operator>>(istream &is, ArbitraryModIntBase &a) {
int64_t t;
is >> t;
a = ArbitraryModIntBase(t);
return (is);
}
int get() const { return x; }
inline unsigned int rem(unsigned long long p) { return barrett().rem(p); }
static inline Barrett &barrett() {
static Barrett b;
return b;
}
static inline int &get_mod() {
static int mod = 0;
return mod;
}
static void set_mod(int md) {
assert(0 < md && md <= (1LL << 30) - 1);
get_mod() = md;
barrett() = Barrett(md);
}
};
using ArbitraryModInt = ArbitraryModIntBase<-1>;
/**
* @brief modint (2^{30} 未満の任意 mod 用)
*/
// End include: "../../modint/arbitrary-modint.hpp"
// Begin include: "../../data-structure/union-find.hpp"
struct UnionFind {
vector<int> data, nxt;
UnionFind(int N) : data(N, -1), nxt(N) {
for (int i = 0; i < N; i++) nxt[i] = i;
}
int find(int k) { return data[k] < 0 ? k : data[k] = find(data[k]); }
int unite(int x, int y) {
if ((x = find(x)) == (y = find(y))) return false;
if (data[x] > data[y]) swap(x, y);
data[x] += data[y];
data[y] = x;
swap(nxt[x], nxt[y]);
return true;
}
// f(x, y) : x に y をマージ
template <typename F>
int unite(int x, int y, const F &f) {
if ((x = find(x)) == (y = find(y))) return false;
if (data[x] > data[y]) swap(x, y);
data[x] += data[y];
data[y] = x;
f(x, y);
swap(nxt[x], nxt[y]);
return true;
}
// g(x, y) : y に x をマージ
template <typename F, typename G>
int unite(int x, int y, const F &f, const G &g) {
if ((x = find(x)) == (y = find(y))) return false;
if (data[x] > data[y]) {
g(x, y);
swap(x, y);
}
else f(x, y);
data[x] += data[y];
data[y] = x;
return true;
}
int size(int k) { return -data[find(k)]; }
int same(int x, int y) { return find(x) == find(y); }
vector<int> enumerate(int i) {
vector<int> res{i};
for (int j = nxt[i]; j != i; j = nxt[j]) res.push_back(j);
return res;
}
vector<vector<int> > groups() {
vector<vector<int> > ret;
for (int i = 0; i < (int)data.size(); ++i) if (i == find(i)) {
ret.emplace_back(enumerate(i));
}
return ret;
}
};
// End include: "../../data-structure/union-find.hpp"
using namespace yamada;
vl op(vl A,vl B){
ll N=A.size();
vl ans(N);
rep(i,N)ans[i]=B[A[i]];
return ans;
}
ll check(ll K,vl per,vl A){
ll N=per.size();
auto B=per;
rep(K-1)B=op(B,per);
ll ans=N;
rep(i,N)if(B[i]==A[i])--ans;
/* out("A:",A); */
/* out("B:",B); */
/* cout.flush(); */
return ans;
}
ll inv(ll x,ll mod){
using mint=ArbitraryModInt;
mint::set_mod(mod);
return ((mint)x).inverse().get();
}
void tc()
{
inl(N,K); K*=2;
vl A(N); in(A); each(a,A)--a;
{
vl B(N);
rep(i,N)B[A[i]]=i;
A=B;
}
UnionFind uf(N);
rep(i,N)uf.unite(i,A[i]);
auto grs=uf.groups();
sort(all(grs),[](V<int> x,V<int> y){return x.size()<y.size();});
ll G=grs.size();
vl ans(N);
for(ll l=0,r=0; l<G; l=r){
while(r<G && grs[l].size()==grs[r].size())++r;
ll n=grs[l].size();
if(n%2){
rep(gi,l,r){
auto gr=grs[gi];
vl ord{gr[0]};
rep(n-1)ord.eb(A[ord.back()]);
ll d=inv(K,n);
rep(oi,n)ans[ord[oi]]=ord[(oi+d)%n];
}
continue;
}
rep(gi,l,r-1,2){
VV<int> gr;
rep(i,2)gr.eb(grs[gi+i]);
vvl ord(2);
rep(i,2){
ord[i].eb(gr[i][0]);
rep(n-1)ord[i].eb(A[ord[i].back()]);
}
ll d=inv(K/2,n);
rep(oi,n){
ans[ord[0][oi]]=ord[1][oi];
ans[ord[1][oi]]=ord[0][(oi+d)%n];
}
}
if((r-l)%2==0)continue;
auto gr=grs[r-1];
vl ord{gr[0]};
rep(n-1)ord.eb(A[ord.back()]);
ll on=ord.back(); ord.pop_back();
--n;
ll d=inv(K,n);
rep(oi,n)ans[ord[oi]]=ord[(oi+d)%n];
ans[on]=ans[ord[n-1]];
}
each(a,ans)++a;
out(ans); cout.flush();
each(a,ans)--a;
/* assert(check(K,ans,A)<sqrt(N)); */
}
void yamada::solve() { ini(T); while(T--)tc(); }