This submission is migrated from previous version of oj.uz, which used different machine for grading. This submission may have different result if resubmitted.
#pragma GCC optimize("O2")
#include <bits/stdc++.h>
#ifdef DEBUG
#include "debug.hpp"
#endif
using namespace std;
#define all(c)              (c).begin(), (c).end()
#define rall(c)             (c).rbegin(), (c).rend()
#define traverse(c, it)     for(auto it = (c).begin(); it != (c).end(); ++it)
#define rep(i, N)           for(int i = 0; i < (N); ++i)
#define rrep(i, N)          for(int i = (N) - 1; i >= 0; --i)
#define rep1(i, N)          for(int i = 1; i <= (N); ++i)
#define rep2(i, s, e)       for(int i = (s); i <= (e); ++i)
#define rep3(i, s, e, d)    for(int i = (s); (d) >= 0 ? i <= (e) : i >= (e); i += (d))
#ifdef DEBUG
#define debug(x...)         { \
                            ++dbg::depth; \
                            string dbg_vals = dbg::to_string(x); \
                            --dbg::depth; \
                            dbg::fprint(__func__, __LINE__, #x, dbg_vals); \
                            }
#define light_debug(x)      { \
                            dbg::light = true; \
                            dbg::dout << __func__ << ":" << __LINE__; \
                            dbg::dout << "  " << #x << " = " << x << endl; \
                            dbg::light = false; \
                            }
#else
#define debug(x...)         42
#define light_debug(x)      42
#endif
using ll = long long;
template<typename T>
inline T& ckmin(T& a, T b) { return a = a > b ? b : a; }
template<typename T>
inline T& ckmax(T& a, T b) { return a = a < b ? b : a; }
template<class Fun>
class y_combinator_result {
    Fun fun_;
public:
    template<class T>
    explicit y_combinator_result(T &&fun): fun_(std::forward<T>(fun)) {}
    template<class ...Args>
    decltype(auto) operator()(Args &&...args) {
        return fun_(std::ref(*this), std::forward<Args>(args)...);
    }
};
template<class Fun>
decltype(auto) y_combinator(Fun &&fun) {
    return y_combinator_result<std::decay_t<Fun>>(std::forward<Fun>(fun));
}
int main() {
    ios_base::sync_with_stdio(false);
    cin.tie(0);
    
    #ifdef DEBUG
    freopen("debug", "w", stderr);
    #endif
    int n, m, k; cin >> n >> m >> k;
    vector<vector<int>> adj(n); vector<int> edges(n - 1);
    rep(i, n - 1) {
        int u, v; cin >> u >> v; --u, --v;
        edges[i] = u ^ v;
        adj[u].push_back(i), adj[v].push_back(i);
    }
    vector<int> in(n), inv;
    vector<vector<int>> rmq;
    int t{}, h{};
    {
        vector<int> tour; tour.reserve(2 * n);
        y_combinator([&](auto dfs, int u, int p) -> void {
            in[u] = t++;
            tour.push_back(in[u]);
            for(int e : adj[u]) {
                if(int v = edges[e] ^ u; v != p)
                    dfs(v, u), tour.push_back(in[u]), ++t;
            }
        })(0, -1);
        debug(tour, t);
        inv.resize(t); fill(all(inv), -1); rep(i, n) inv[in[i]] = i;
        debug(in, inv);
        h = __lg(t) + 1;
        rmq = vector<vector<int>>(h, vector<int>(t));
        rep(i, t) rmq[0][i] = tour[i];
        rep(j, h - 1)
            rep(i, t) {
                rmq[j + 1][i] = rmq[j][i];
                if(i + (1 << j) < t)
                    ckmin(rmq[j + 1][i], rmq[j][i + (1 << j)]);
            }
        debug(rmq);
    }
    auto lca = [&](int u, int v) {
        u = in[u], v = in[v];
        if(u > v) swap(u, v);
        int p = __lg(v - u + 1);
        return inv[min(rmq[p][u], rmq[p][v + 1 - (1 << p)])];
    };
    vector<int> up(n);
    rep(_, m) {
        int s; cin >> s;
        vector<int> v(s); rep(i, s) cin >> v[i], --v[i]; v.push_back(v[0]);
        rep(i, s) ++up[v[i]];
        rep(i, s) --up[lca(v[i], v[i + 1])];
    }
    debug(up);
    vector<int> k_edges;
    y_combinator([&](auto dfs, int u, int p) -> int {
        int s{up[u]};
        for(int e : adj[u])
            if(e != p) s += dfs(edges[e] ^ u, e);
        if(s >= k) k_edges.push_back(p);
        return s;
    })(0, -1);
    cout << k_edges.size() << '\n';
    sort(all(k_edges));
    for(int& e : k_edges) cout << e + 1 << ' ';
    cout << '\n';
    
    #ifdef DEBUG
    dbg::dout << "\nExecution time: " << clock() * 1000 / CLOCKS_PER_SEC  << "ms" << endl;
    #endif
    return 0;
}
Compilation message (stderr)
railway.cpp: In function 'int main()':
railway.cpp:35:29: warning: statement has no effect [-Wunused-value]
   35 | #define debug(x...)         42
      |                             ^~
railway.cpp:96:9: note: in expansion of macro 'debug'
   96 |         debug(tour, t);
      |         ^~~~~
railway.cpp:35:29: warning: statement has no effect [-Wunused-value]
   35 | #define debug(x...)         42
      |                             ^~
railway.cpp:99:9: note: in expansion of macro 'debug'
   99 |         debug(in, inv);
      |         ^~~~~
railway.cpp:35:29: warning: statement has no effect [-Wunused-value]
   35 | #define debug(x...)         42
      |                             ^~
railway.cpp:110:9: note: in expansion of macro 'debug'
  110 |         debug(rmq);
      |         ^~~~~
railway.cpp:35:29: warning: statement has no effect [-Wunused-value]
   35 | #define debug(x...)         42
      |                             ^~
railway.cpp:127:5: note: in expansion of macro 'debug'
  127 |     debug(up);
      |     ^~~~~| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... | 
| # | Verdict  | Execution time | Memory | Grader output | 
|---|
| Fetching results... |