docs: register the two scale benchmarks and correct the stale note

bench_scale and bench_parallel were runnable but documented nowhere, so the
directory listing did not say they existed. The file header of
bench_scale also still claimed the harness warms up, which it stopped
doing when the cold cost was given its own column.

README.md

@@ -97,6 +97,12 @@ cargo run -p apsis-rs --features sim --example integrate_sim
 
 # 热点路径基准（release 下运行）
 cargo run --release -p apsis-rs --features full --example bench
+
+# 规模扫描：输入规模递增，观察每单位工作量的增长趋势
+cargo run --release -p apsis-rs --features full --example bench_scale
+
+# 并行扫描：同一批工作量在 1/2/4/8/16 线程下的加速比与效率
+cargo run --release -p apsis-rs --features full --example bench_parallel
 ```
 
 ## 许可

crates/apsis-rs/examples/bench_scale.rs

@@ -13,9 +13,11 @@
 //! satellite, building the inter-satellite topology and routing through it,
 //! and planning a task set with precedence.
 //!
-//! Everything is measured in release mode with a fixed iteration count, and
-//! the harness warms up before timing so that lazy initialisation is not
-//! charged to the first call.
+//! Everything is measured in release mode. There is deliberately no warm-up:
+//! the first call pays for whatever the path allocates or caches on first
+//! use, and a caller waits for that too, so the cold cost is reported on its
+//! own column beside the steady state rather than being hidden behind a
+//! discarded run.
 //!
 //! Usage:
 //!