#939378 (C++23) No.2568 列辞書順列列

提出ソース
結果

問題	No.2568 列辞書順列列
ユーザー	ZrjaK
提出日時	2023-12-20 10:58:07
言語	C++23 (gcc 12.3.0 + boost 1.83.0)
結果	AC
実行時間	62 ms / 3,000 ms
コード長	23,842 bytes
コンパイル時間	7,079 ms
コンパイル使用メモリ	333,768 KB
実行使用メモリ	6,944 KB
最終ジャッジ日時	2024-09-27 09:27:26
合計ジャッジ時間	10,267 ms
ジャッジサーバーID （参考情報）	judge4 / judge3
このコードへのチャレンジ
（要ログイン）
テストケース

テストケース表示
入力	結果	実行時間実行使用メモリ
testcase_00	AC	2 ms 6,816 KB
testcase_01	AC	2 ms 6,940 KB
testcase_02	AC	6 ms 6,944 KB
testcase_03	AC	6 ms 6,940 KB
testcase_04	AC	48 ms 6,944 KB
testcase_05	AC	48 ms 6,944 KB
testcase_06	AC	47 ms 6,940 KB
testcase_07	AC	48 ms 6,940 KB
testcase_08	AC	46 ms 6,940 KB
testcase_09	AC	46 ms 6,944 KB
testcase_10	AC	46 ms 6,940 KB
testcase_11	AC	46 ms 6,944 KB
testcase_12	AC	62 ms 6,940 KB
testcase_13	AC	59 ms 6,940 KB
testcase_14	AC	58 ms 6,940 KB
testcase_15	AC	57 ms 6,940 KB
testcase_16	AC	57 ms 6,940 KB
testcase_17	AC	48 ms 6,940 KB
testcase_18	AC	47 ms 6,940 KB
testcase_19	AC	47 ms 6,940 KB
testcase_20	AC	47 ms 6,940 KB
testcase_21	AC	48 ms 6,940 KB
testcase_22	AC	46 ms 6,944 KB
testcase_23	AC	50 ms 6,944 KB
testcase_24	AC	48 ms 6,944 KB
testcase_25	AC	48 ms 6,944 KB
testcase_26	AC	48 ms 6,944 KB
権限があれば一括ダウンロードができます
ソースコード

raw source code
#ifdef ONLINE_JUDGE
#pragma GCC optimize("Ofast,unroll-loops")
#pragma GCC target("avx2,bmi,bmi2,lzcnt,popcnt")
#endif
#include <bits/stdc++.h>
#include <ext/rope>
#include <ext/pb_ds/assoc_container.hpp>
#include <ext/pb_ds/hash_policy.hpp>
#include <ext/pb_ds/tree_policy.hpp>
#include <ext/pb_ds/trie_policy.hpp>
#include <ext/pb_ds/priority_queue.hpp>
using namespace std;
using namespace __gnu_cxx;
using namespace __gnu_pbds;
template <class T> using pbds_set = tree<T, null_type, less_equal<T>, rb_tree_tag,tree_order_statistics_node_update>;
using Trie = trie<string, null_type, trie_string_access_traits<>, pat_trie_tag, trie_prefix_search_node_update>;
// template <class T> using heapq = __gnu_pbds::priority_queue<T, greater<T>, pairing_heap_tag>;
template <class T> using heapq = std::priority_queue<T, vector<T>, greater<T>>;
using ll   =                long long;
using u32  =                unsigned int;
using u64  =                unsigned long long;
using i128 =                __int128;
using u128 =                __uint128_t;
using f128 =                __float128;
using ld   =                long double;
using ui   =                unsigned int;
using ull  =                unsigned long long;
using pii  =                pair<int, int>;
using pll  =                pair<ll, ll>;
using pdd  =                pair<ld, ld>;
using vi   =                vector<int>;
using vvi  =                vector<vector<int>>;
using vll  =                vector<ll>;
using vvll =                vector<vector<ll>>;
using vpii =                vector<pii>;
using vpll =                vector<pll>;
template <class T>
constexpr T infty = 0;
template <>
constexpr int infty<int> = 1'000'000'000;
template <>
constexpr ll infty<ll> = ll(infty<int>) * infty<int> * 2;
template <>
constexpr u32 infty<u32> = infty<int>;
template <>
constexpr u64 infty<u64> = infty<ll>;
template <>
constexpr i128 infty<i128> = i128(infty<ll>) * infty<ll>;
template <>
constexpr double infty<double> = infty<ll>;
template <>
constexpr long double infty<long double> = infty<ll>;
template <class T>
using vc = vector<T>;
template <class T>
using vvc = vector<vc<T>>;
template <class T>
using vvvc = vector<vvc<T>>;
template <class T>
using vvvvc = vector<vvvc<T>>;
template <class T>
using vvvvvc = vector<vvvvc<T>>;
template <class T>
using pq = std::priority_queue<T>;
template <class T>
using pqg = std::priority_queue<T, vector<T>, greater<T>>;
#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 lb                  lower_bound
#define ub                  upper_bound
#define pb                  push_back
#define pf                  push_front
#define eb                  emplace_back
#define fi                  first
#define se                  second
#define overload4(_1, _2, _3, _4, name, ...) name
#define overload3(_1, _2, _3, name, ...) name
#define rep1(n)             for(ll _ = 0; _ < n; ++_)
#define rep2(i, n)          for(ll i = 0; i < n; ++i)
#define rep3(i, a, b)       for(ll i = a; i < b; ++i)
#define rep4(i, a, b, c)    for(int i = a; i < b; i += c)
#define rep(...)            overload4(__VA_ARGS__, rep4, rep3, rep2, rep1) (__VA_ARGS__)
#define rrep1(n)            for(ll i = n; i--; )
#define rrep2(i, n)         for(ll i = n; i--; )
#define rrep3(i, a, b)      for(ll i = a; i > b; i--)
#define rrep4(i, a, b, c)   for(ll i = a; i > b; i -= c)
#define rrep(...)           overload4(__VA_ARGS__, rrep4, rrep3, rrep2, rrep1) (__VA_ARGS__)
#define each1(i, a)         for(auto&& i : a)
#define each2(x, y, a)      for(auto&& [x, y] : a)
#define each3(x, y, z, a)   for(auto&& [x, y, z] : a)
#define each(...)           overload4(__VA_ARGS__, each3, each2, each1) (__VA_ARGS__)
#define FOR1(a)             for (ll _ = 0; _ < ll(a); ++_)
#define FOR2(i, a)          for (ll i = 0; i < ll(a); ++i)
#define FOR3(i, a, b)       for (ll i = a; i < ll(b); ++i)
#define FOR4(i, a, b, c)    for (ll i = a; i < ll(b); i += (c))
#define FOR1_R(a)           for (ll i = (a)-1; i >= ll(0); --i)
#define FOR2_R(i, a)        for (ll i = (a)-1; i >= ll(0); --i)
#define FOR3_R(i, a, b)     for (ll i = (b)-1; i >= ll(a); --i)
#define FOR(...)            overload4(__VA_ARGS__, FOR4, FOR3, FOR2, FOR1) (__VA_ARGS__)
#define FOR_R(...)          overload3(__VA_ARGS__, FOR3_R, FOR2_R, FOR1_R) (__VA_ARGS__)
#define FOR_subset(t, s)    for (ll t = (s); t >= 0; t = (t == 0 ? -1 : (t - 1) & (s)))
#define len(x)              (int)x.size()
#define elif                else if
#define all1(i)             begin(i), end(i)
#define all2(i, a)          begin(i), begin(i) + a
#define all3(i, a, b)       begin(i) + a, begin(i) + b
#define all(...)            overload3(__VA_ARGS__, all3, all2, all1) (__VA_ARGS__)
#define rall1(i)            rbegin(i), rend(i)
#define rall2(i, a)         rbegin(i), rbegin(i) + a
#define rall3(i, a, b)      rbegin(i) + a, rbegin(i) + b
#define rall(...)           overload3(__VA_ARGS__, rall3, rall2, rall1) (__VA_ARGS__)
#define mst(x, a)           memset(x, a, sizeof(x))
#define bitcnt(x)           (__builtin_popcountll(x))
#define endl                "\n"
#define MIN(v)              *min_element(all(v))
#define MAX(v)              *max_element(all(v))
#define LB(c, x)            distance((c).begin(), lower_bound(all(c), (x)))
#define UB(c, x)            distance((c).begin(), upper_bound(all(c), (x)))
#define UNIQUE(x)           sort(all(x)), x.erase(unique(all(x)), x.end()), x.shrink_to_fit()
#define SORT(a)             sort(all(a))
#define REV(a)              reverse(all(a))
int popcnt(int x) { return __builtin_popcount(x); }
int popcnt(u32 x) { return __builtin_popcount(x); }
int popcnt(ll x) { return __builtin_popcountll(x); }
int popcnt(u64 x) { return __builtin_popcountll(x); }
// (0, 1, 2, 3, 4) -> (-1, 0, 1, 1, 2)
int topbit(int x) { return (x == 0 ? -1 : 31 - __builtin_clz(x)); }
int topbit(u32 x) { return (x == 0 ? -1 : 31 - __builtin_clz(x)); }
int topbit(ll x) { return (x == 0 ? -1 : 63 - __builtin_clzll(x)); }
int topbit(u64 x) { return (x == 0 ? -1 : 63 - __builtin_clzll(x)); }
// (0, 1, 2, 3, 4) -> (-1, 0, 1, 0, 2)
int lowbit(int x) { return (x == 0 ? -1 : __builtin_ctz(x)); }
int lowbit(u32 x) { return (x == 0 ? -1 : __builtin_ctz(x)); }
int lowbit(ll x) { return (x == 0 ? -1 : __builtin_ctzll(x)); }
int lowbit(u64 x) { return (x == 0 ? -1 : __builtin_ctzll(x)); }
template<class T> auto max(const T& a){ return *max_element(all(a)); }
template<class T> auto min(const T& a){ return *min_element(all(a)); }
template <typename T, typename U>
T ceil(T x, U y) {
    return (x > 0 ? (x + y - 1) / y : x / y);
}
template <typename T, typename U>
T floor(T x, U y) {
    return (x > 0 ? x / y : (x - y + 1) / y);
}
template <typename T, typename U>
pair<T, T> divmod(T x, U y) {
    T q = floor(x, y);
    return {q, x - q * y};
}
template <typename T, typename U>
T SUM(const vector<U> &A) {
    T sum = 0;
    for (auto &&a: A) sum += a;
    return sum;
}
template <typename T, typename U>
vector<T> cumsum(vector<U> &A, int off = 1) {
    int N = A.size();
    vector<T> B(N + 1);
    for (int i = 0; i < N; i++) B[i + 1] = B[i] + A[i];
    if (off == 0) B.erase(B.begin());
    return B;
}
template <typename T>
vector<int> argsort(const vector<T> &A) {
  vector<int> ids(len(A));
  iota(all(ids), 0);
  sort(all(ids),
       [&](int i, int j) { return (A[i] == A[j] ? i < j : A[i] < A[j]); });
  return ids;
}
template <typename T>
vc<T> rearrange(const vc<T> &A, const vc<int> &I) {
  vc<T> B(len(I));
  FOR(i, len(I)) B[i] = A[I[i]];
  return B;
}
template <typename T>
T POP(deque<T> &que) {
  T a = que.front();
  que.pop_front();
  return a;
}
template <typename T>
T POP(pq<T> &que) {
  T a = que.top();
  que.pop();
  return a;
}
template <typename T>
T POP(pqg<T> &que) {
  assert(!que.empty());
  T a = que.top();
  que.pop();
  return a;
}
template <typename T>
T POP(vc<T> &que) {
  assert(!que.empty());
  T a = que.back();
  que.pop_back();
  return a;
}
template <typename F>
ll binary_search(F check, ll ok, ll ng, bool check_ok = true) {
  if (check_ok) assert(check(ok));
  while (abs(ok - ng) > 1) {
    auto x = (ng + ok) / 2;
    (check(x) ? ok : ng) = x;
  }
  return ok;
}
template <typename F>
double binary_search_real(F check, double ok, double ng, int iter = 100) {
  while (iter--) {
    double x = (ok + ng) / 2;
    (check(x) ? ok : ng) = x;
  }
  return (ok + ng) / 2;
}
template <class T, class S> inline bool chmax(T &a, const S &b) {
    return (a < b ? a = b, 1 : 0);
}
template <class T, class S> inline bool chmin(T &a, const S &b) {
    return (a > b ? a = b, 1 : 0);
}
mt19937 rng( chrono::steady_clock::now().time_since_epoch().count() );
#define Ran(a, b) rng() % ( (b) - (a) + 1 ) + (a)
struct custom_hash {
    static uint64_t splitmix64(uint64_t x) {
        // http://xorshift.di.unimi.it/splitmix64.c
        x += 0x9e3779b97f4a7c15;
        x = (x ^ (x >> 30)) * 0xbf58476d1ce4e5b9;
        x = (x ^ (x >> 27)) * 0x94d049bb133111eb;
        return x ^ (x >> 31);
    }

    size_t operator()(uint64_t x) const {
        static const uint64_t FIXED_RANDOM = chrono::steady_clock::now().time_since_epoch().count();
        return splitmix64(x + FIXED_RANDOM);
    }

    size_t operator()(pair<uint64_t,uint64_t> x) const {
        static const uint64_t FIXED_RANDOM = chrono::steady_clock::now().time_since_epoch().count();
        return splitmix64(x.first + FIXED_RANDOM) ^ (splitmix64(x.second + FIXED_RANDOM) >> 1);
    }
};
#define FASTIO
#include <unistd.h>

// https://judge.yosupo.jp/submission/21623

namespace fastio {
static constexpr uint32_t SZ = 1 << 17;
char ibuf[SZ];
char obuf[SZ];
char out[100];
// pointer of ibuf, obuf

uint32_t pil = 0, pir = 0, por = 0;

struct Pre {
  char num[10000][4];
  constexpr Pre() : num() {
    for (int i = 0; i < 10000; i++) {
      int n = i;
      for (int j = 3; j >= 0; j--) {
        num[i][j] = n % 10 | '0';
        n /= 10;
      }
    }
  }
} constexpr pre;

inline void load() {
  memcpy(ibuf, ibuf + pil, pir - pil);
  pir = pir - pil + fread(ibuf + pir - pil, 1, SZ - pir + pil, stdin);
  pil = 0;
  if (pir < SZ) ibuf[pir++] = '\n';
}

inline void flush() {
  fwrite(obuf, 1, por, stdout);
  por = 0;
}

void rd(char &c) {
  do {
    if (pil + 1 > pir) load();
    c = ibuf[pil++];
  } while (isspace(c));
}

void rd(string &x) {
  x.clear();
  char c;
  do {
    if (pil + 1 > pir) load();
    c = ibuf[pil++];
  } while (isspace(c));
  do {
    x += c;
    if (pil == pir) load();
    c = ibuf[pil++];
  } while (!isspace(c));
}

template <typename T>
void rd_real(T &x) {
  string s;
  rd(s);
  x = stod(s);
}

template <typename T>
void rd_integer(T &x) {
  if (pil + 100 > pir) load();
  char c;
  do
    c = ibuf[pil++];
  while (c < '-');
  bool minus = 0;
  if constexpr (is_signed<T>::value || is_same_v<T, i128>) {
    if (c == '-') { minus = 1, c = ibuf[pil++]; }
  }
  x = 0;
  while ('0' <= c) { x = x * 10 + (c & 15), c = ibuf[pil++]; }
  if constexpr (is_signed<T>::value || is_same_v<T, i128>) {
    if (minus) x = -x;
  }
}

void rd(int &x) { rd_integer(x); }
void rd(ll &x) { rd_integer(x); }
void rd(i128 &x) { rd_integer(x); }
void rd(u32 &x) { rd_integer(x); }
void rd(u64 &x) { rd_integer(x); }
void rd(u128 &x) { rd_integer(x); }
void rd(double &x) { rd_real(x); }
void rd(long double &x) { rd_real(x); }
void rd(f128 &x) { rd_real(x); }

template <class T, class U>
void rd(pair<T, U> &p) {
  return rd(p.first), rd(p.second);
}
template <size_t N = 0, typename T>
void rd_tuple(T &t) {
  if constexpr (N < std::tuple_size<T>::value) {
    auto &x = std::get<N>(t);
    rd(x);
    rd_tuple<N + 1>(t);
  }
}
template <class... T>
void rd(tuple<T...> &tpl) {
  rd_tuple(tpl);
}

template <size_t N = 0, typename T>
void rd(array<T, N> &x) {
  for (auto &d: x) rd(d);
}
template <class T>
void rd(vc<T> &x) {
  for (auto &d: x) rd(d);
}

void read() {}
template <class H, class... T>
void read(H &h, T &... t) {
  rd(h), read(t...);
}

void wt(const char c) {
  if (por == SZ) flush();
  obuf[por++] = c;
}
void wt(const string s) {
  for (char c: s) wt(c);
}
void wt(const char *s) {
  size_t len = strlen(s);
  for (size_t i = 0; i < len; i++) wt(s[i]);
}

template <typename T>
void wt_integer(T x) {
  if (por > SZ - 100) flush();
  if (x < 0) { obuf[por++] = '-', x = -x; }
  int outi;
  for (outi = 96; x >= 10000; outi -= 4) {
    memcpy(out + outi, pre.num[x % 10000], 4);
    x /= 10000;
  }
  if (x >= 1000) {
    memcpy(obuf + por, pre.num[x], 4);
    por += 4;
  } else if (x >= 100) {
    memcpy(obuf + por, pre.num[x] + 1, 3);
    por += 3;
  } else if (x >= 10) {
    int q = (x * 103) >> 10;
    obuf[por] = q | '0';
    obuf[por + 1] = (x - q * 10) | '0';
    por += 2;
  } else
    obuf[por++] = x | '0';
  memcpy(obuf + por, out + outi + 4, 96 - outi);
  por += 96 - outi;
}

template <typename T>
void wt_real(T x) {
  ostringstream oss;
  oss << fixed << setprecision(15) << double(x);
  string s = oss.str();
  wt(s);
}

void wt(int x) { wt_integer(x); }
void wt(ll x) { wt_integer(x); }
void wt(i128 x) { wt_integer(x); }
void wt(u32 x) { wt_integer(x); }
void wt(u64 x) { wt_integer(x); }
void wt(u128 x) { wt_integer(x); }
void wt(double x) { wt_real(x); }
void wt(long double x) { wt_real(x); }
void wt(f128 x) { wt_real(x); }

template <class T, class U>
void wt(const pair<T, U> val) {
  wt(val.first);
  wt(' ');
  wt(val.second);
}
template <size_t N = 0, typename T>
void wt_tuple(const T t) {
  if constexpr (N < std::tuple_size<T>::value) {
    if constexpr (N > 0) { wt(' '); }
    const auto x = std::get<N>(t);
    wt(x);
    wt_tuple<N + 1>(t);
  }
}
template <class... T>
void wt(tuple<T...> tpl) {
  wt_tuple(tpl);
}
template <class T, size_t S>
void wt(const array<T, S> val) {
  auto n = val.size();
  for (size_t i = 0; i < n; i++) {
    if (i) wt(' ');
    wt(val[i]);
  }
}
template <class T>
void wt(const vector<T> val) {
  auto n = val.size();
  for (size_t i = 0; i < n; i++) {
    if (i) wt(' ');
    wt(val[i]);
  }
}

void print() { wt('\n'); }
template <class Head, class... Tail>
void print(Head &&head, Tail &&... tail) {
  wt(head);
  if (sizeof...(Tail)) wt(' ');
  print(forward<Tail>(tail)...);
}

// gcc expansion. called automaticall after main.

void __attribute__((destructor)) _d() { flush(); }
} // namespace fastio

using fastio::read;
using fastio::print;
using fastio::flush;

#define INT(...)   \
  int __VA_ARGS__; \
  read(__VA_ARGS__)
#define LL(...)   \
  ll __VA_ARGS__; \
  read(__VA_ARGS__)
#define U32(...)   \
  u32 __VA_ARGS__; \
  read(__VA_ARGS__)
#define U64(...)   \
  u64 __VA_ARGS__; \
  read(__VA_ARGS__)
#define STR(...)      \
  string __VA_ARGS__; \
  read(__VA_ARGS__)
#define CHAR(...)   \
  char __VA_ARGS__; \
  read(__VA_ARGS__)
#define DBL(...)      \
  double __VA_ARGS__; \
  read(__VA_ARGS__)

#define VEC(type, name, size) \
  vector<type> name(size);    \
  read(name)
#define VV(type, name, h, w)                     \
  vector<vector<type>> name(h, vector<type>(w)); \
  read(name)

void YES(bool t = 1) { print(t ? "YES" : "NO"); }
void NO(bool t = 1) { YES(!t); }
void Yes(bool t = 1) { print(t ? "Yes" : "No"); }
void No(bool t = 1) { Yes(!t); }
void yes(bool t = 1) { print(t ? "yes" : "no"); }
void no(bool t = 1) { yes(!t); }
const i128 ONE = 1;
template <typename Iterable>
auto print_all(const Iterable& v, std::string sep = " ", std::string end = "\n") -> decltype(fastio::wt(*v.begin())) {
    for (auto it = v.begin(); it != v.end();) {
        fastio::wt(*it);
        if (++it != v.end()) fastio::wt(sep);
    }
    fastio::wt(end);
}
ll gcd(ll x, ll y) {
    if(!x) return y;
    if(!y) return x;
    int t = __builtin_ctzll(x | y);
    x >>= __builtin_ctzll(x);
    do {
        y >>= __builtin_ctzll(y);
        if (x > y) swap(x, y);
        y -= x;
    } while (y);
    return x << t;
}
ll lcm(ll x, ll y) { return x * y / gcd(x, y); }
ll exgcd(ll a, ll b, ll &x, ll &y) {
    if(!b) return x = 1, y = 0, a;
    ll d = exgcd(b, a % b, x, y);
    ll t = x;
    x = y;
    y = t - a / b * x;
    return d;
}
ll max(ll x, ll y) { return x > y ? x : y; }
ll min(ll x, ll y) { return x < y ? x : y; }
ll Mod(ll x, int mod) { return (x % mod + mod) % mod; }
ll pow(ll x, ll y, ll mod){
    ll res = 1, cur = x;
    while (y) {
        if (y & 1) res = res * cur % mod;
        cur = ONE * cur * cur % mod;
        y >>= 1;
    }
    return res % mod;
}
ll probabilityMod(ll x, ll y, ll mod) {
    return x * pow(y, mod-2, mod) % mod;
}
vvi getGraph(int n, int m, bool directed = false) {
    vvi res(n);
    rep(_, 0, m) {
        INT(u, v);
        u--, v--;
        res[u].emplace_back(v);
        if(!directed) res[v].emplace_back(u);
    }
    return res;
}
vector<vpii> getWeightedGraph(int n, int m, bool directed = false) {
    vector<vpii> res(n);
    rep(_, 0, m) {
        INT(u, v, w);
        u--, v--;
        res[u].emplace_back(v, w);
        if(!directed) res[v].emplace_back(u, w);
    }
    return res;
}
template <class... Args> auto ndvector(size_t n, Args &&...args) {
    if constexpr (sizeof...(args) == 1) {
        return vector(n, args...);
    } else {
        return vector(n, ndvector(args...));
    }
}
const ll LINF = 0x1fffffffffffffff;
const ll MINF = 0x7fffffffffff;
const int INF = 0x3fffffff;
const int MOD = 1000000007;
const int MODD = 998244353;
const int N = 1e6 + 10;

#line 2 "mod/modint_common.hpp"

struct has_mod_impl {
  template <class T>
  static auto check(T &&x) -> decltype(x.get_mod(), std::true_type{});
  template <class T>
  static auto check(...) -> std::false_type;
};

template <class T>
class has_mod : public decltype(has_mod_impl::check<T>(std::declval<T>())) {};

template <typename mint>
mint inv(int n) {
  static const int mod = mint::get_mod();
  static vector<mint> dat = {0, 1};
  assert(0 <= n);
  if (n >= mod) n %= mod;
  while (len(dat) <= n) {
    int k = len(dat);
    int q = (mod + k - 1) / k;
    dat.eb(dat[k * q - mod] * mint::raw(q));
  }
  return dat[n];
}

template <typename mint>
mint fact(int n) {
  static const int mod = mint::get_mod();
  assert(0 <= n && n < mod);
  static vector<mint> dat = {1, 1};
  while (len(dat) <= n) dat.eb(dat[len(dat) - 1] * mint::raw(len(dat)));
  return dat[n];
}

template <typename mint>
mint fact_inv(int n) {
  static vector<mint> dat = {1, 1};
  if (n < 0) return mint(0);
  while (len(dat) <= n) dat.eb(dat[len(dat) - 1] * inv<mint>(len(dat)));
  return dat[n];
}

template <class mint, class... Ts>
mint fact_invs(Ts... xs) {
  return (mint(1) * ... * fact_inv<mint>(xs));
}

template <typename mint, class Head, class... Tail>
mint multinomial(Head &&head, Tail &&... tail) {
  return fact<mint>(head) * fact_invs<mint>(std::forward<Tail>(tail)...);
}

template <typename mint>
mint C_dense(int n, int k) {
  static vvc<mint> C;
  static int H = 0, W = 0;
  auto calc = [&](int i, int j) -> mint {
    if (i == 0) return (j == 0 ? mint(1) : mint(0));
    return C[i - 1][j] + (j ? C[i - 1][j - 1] : 0);
  };
  if (W <= k) {
    FOR(i, H) {
      C[i].resize(k + 1);
      FOR(j, W, k + 1) { C[i][j] = calc(i, j); }
    }
    W = k + 1;
  }
  if (H <= n) {
    C.resize(n + 1);
    FOR(i, H, n + 1) {
      C[i].resize(W);
      FOR(j, W) { C[i][j] = calc(i, j); }
    }
    H = n + 1;
  }
  return C[n][k];
}

template <typename mint, bool large = false, bool dense = false>
mint C(ll n, ll k) {
  assert(n >= 0);
  if (k < 0 || n < k) return 0;
  if constexpr (dense) return C_dense<mint>(n, k);
  if constexpr (!large) return multinomial<mint>(n, k, n - k);
  k = min(k, n - k);
  mint x(1);
  FOR(i, k) x *= mint(n - i);
  return x * fact_inv<mint>(k);
}

template <typename mint, bool large = false>
mint C_inv(ll n, ll k) {
  assert(n >= 0);
  assert(0 <= k && k <= n);
  if (!large) return fact_inv<mint>(n) * fact<mint>(k) * fact<mint>(n - k);
  return mint(1) / C<mint, 1>(n, k);
}

// [x^d](1-x)^{-n}
template <typename mint, bool large = false, bool dense = false>
mint C_negative(ll n, ll d) {
  assert(n >= 0);
  if (d < 0) return mint(0);
  if (n == 0) { return (d == 0 ? mint(1) : mint(0)); }
  return C<mint, large, dense>(n + d - 1, d);
}
#line 3 "mod/modint.hpp"

template <int mod>
struct modint {
  static constexpr u32 umod = u32(mod);
  static_assert(umod < u32(1) << 31);
  u32 val;

  static modint raw(u32 v) {
    modint x;
    x.val = v;
    return x;
  }
  constexpr modint() : val(0) {}
  constexpr modint(u32 x) : val(x % umod) {}
  constexpr modint(u64 x) : val(x % umod) {}
  constexpr modint(u128 x) : val(x % umod) {}
  constexpr modint(int x) : val((x %= mod) < 0 ? x + mod : x){};
  constexpr modint(ll x) : val((x %= mod) < 0 ? x + mod : x){};
  constexpr modint(i128 x) : val((x %= mod) < 0 ? x + mod : x){};
  bool operator<(const modint &other) const { return val < other.val; }
  modint &operator+=(const modint &p) {
    if ((val += p.val) >= umod) val -= umod;
    return *this;
  }
  modint &operator-=(const modint &p) {
    if ((val += umod - p.val) >= umod) val -= umod;
    return *this;
  }
  modint &operator*=(const modint &p) {
    val = u64(val) * p.val % umod;
    return *this;
  }
  modint &operator/=(const modint &p) {
    *this *= p.inverse();
    return *this;
  }
  modint operator-() const { return modint::raw(val ? mod - val : u32(0)); }
  modint operator+(const modint &p) const { return modint(*this) += p; }
  modint operator-(const modint &p) const { return modint(*this) -= p; }
  modint operator*(const modint &p) const { return modint(*this) *= p; }
  modint operator/(const modint &p) const { return modint(*this) /= p; }
  bool operator==(const modint &p) const { return val == p.val; }
  bool operator!=(const modint &p) const { return val != p.val; }
  modint inverse() const {
    int a = val, b = mod, u = 1, v = 0, t;
    while (b > 0) {
      t = a / b;
      swap(a -= t * b, b), swap(u -= t * v, v);
    }
    return modint(u);
  }
  modint pow(ll n) const {
    assert(n >= 0);
    modint ret(1), mul(val);
    while (n > 0) {
      if (n & 1) ret *= mul;
      mul *= mul;
      n >>= 1;
    }
    return ret;
  }
  static constexpr int get_mod() { return mod; }
  // (n, r), r は 1 の 2^n 乗根
  static constexpr pair<int, int> ntt_info() {
    if (mod == 120586241) return {20, 74066978};
    if (mod == 167772161) return {25, 17};
    if (mod == 469762049) return {26, 30};
    if (mod == 754974721) return {24, 362};
    if (mod == 880803841) return {23, 211};
    if (mod == 943718401) return {22, 663003469};
    if (mod == 998244353) return {23, 31};
    if (mod == 1045430273) return {20, 363};
    if (mod == 1051721729) return {20, 330};
    if (mod == 1053818881) return {20, 2789};
    return {-1, -1};
  }
  static constexpr bool can_ntt() { return ntt_info().fi != -1; }
};

#ifdef FASTIO
template <int mod>
void rd(modint<mod> &x) {
  fastio::rd(x.val);
  assert(0 <= x.val && x.val < mod);
}
template <int mod>
void wt(modint<mod> x) {
  fastio::wt(x.val);
}
#endif

using modint107 = modint<1000000007>;
using modint998 = modint<998244353>;

using mint = modint998;

void solve() {
    INT(n, m, q);
    VEC(int, a, n);
    vc<mint> cum = {0};
    rrep(i, n - 1, -1) {
        cum.eb(cum.back() + mint(a[i] - 1) * mint(m).pow(n - i - 1));
    }
    REV(cum);
    rep(q) {
        INT(l, r);
        l--;
        mint ans = mint(cum[l] - cum[r]) / mint(m).pow(n - r);
        print(ans + 1);
    }
    
}

signed main() {
    int T = 1;
    // read(T);
    while (T--) {
        solve();
    }
    return 0;
}
yukicoder

結果

テストケース

ソースコード
