diff --git a/backend/app/eval/gold.py b/backend/app/eval/gold.py
index e67f8271..98c094e0 100644
--- a/backend/app/eval/gold.py
+++ b/backend/app/eval/gold.py
@@ -448,7 +448,7 @@ async def _analysis_value(exp: Mapping[str, Any], at: int, found: _Analyses) ->
     try:
         request = judgements.request_of(exp, found.ctx.variables(), found.snapshot)
     except judgements.ParamsInvalid as e:
-        raise _NoValue(f"{where}的{e.message}") from None
+        raise _NoValue(f"{where}算不出期望，{e.message}") from None
     try:
         result = await analysis_ops.run(request, lambda name: inp if name == judgements.GOLD_REF else None,
                                         settings=settings, context=context, refuse_data_errors=True)
diff --git a/backend/app/eval/judgements.py b/backend/app/eval/judgements.py
index dedb09aa..d84e3c79 100644
--- a/backend/app/eval/judgements.py
+++ b/backend/app/eval/judgements.py
@@ -189,7 +189,8 @@ def _two_periods(snapshot: Mapping[str, Any], period: str) -> tuple[Any, Any]:
         order = sorted(range(2), key=lambda k: items[k].ordinal)
     else:
         order = sorted(range(2), key=lambda k: str(values[k]))
-    return values[order[0]], values[order[1]]
+    # 写成文字交给分析工具的参数（期次是数的也一样：算子按写出来的样子认期次列里的值）
+    return str(values[order[0]]), str(values[order[1]])
 
 
 def request_of(exp: Mapping[str, Any], variables: Mapping[str, str], snapshot: Mapping[str, Any]) -> dict[str, Any]:
diff --git a/backend/tests/test_eval_analysis.py b/backend/tests/test_eval_analysis.py
index 44255487..edab6cd7 100644
--- a/backend/tests/test_eval_analysis.py
+++ b/backend/tests/test_eval_analysis.py
@@ -315,3 +315,13 @@ def test_the_summary_counts_outcomes_by_kind():
     assert summary["outcomes_by_kind"] == {"contribution": {"traced": 1}, "verdict": {"wrong": 1},
                                            "scalar": {"untraced": 1}}
     assert summary["outcomes"] == {"traced": 1, "wrong": 1, "untraced": 1}
+
+
+def test_e1_follows_the_analysis_inputs_down_the_drill():
+    """逐题 E1 拿产出答案的查询：引用的是下钻那一层的分析结论时，顺着上一层的结论找到两层各自读的查询。"""
+    from app.eval.score import _query_inputs
+
+    found = {"a1": {"inputs": ["q1"]}, "a2": {"inputs": ["a1", "q2"]}}
+    assert _query_inputs(found["a2"], found, {"q1": {}, "q2": {}}) == ["q1", "q2"]
+    assert _query_inputs({"inputs": ["gone"]}, found, {"q1": {}}) == [], "取不回的输入不算"
+