wip-4a3

crates/clawhdf5-bench/src/bin/longmemeval_bench.rs

@@ -384,11 +384,7 @@ impl DatasetProfile {
     }
 }
 
-fn print_report(
-    overall: &Metrics,
-    by_type: &HashMap<String, Metrics>,
-    profile: &DatasetProfile,
-) {
+fn print_report(overall: &Metrics, by_type: &HashMap<String, Metrics>, profile: &DatasetProfile) {
     println!("=================================================================");
     println!("  LongMemEval Benchmark  (BM25-only retrieval, zero embeddings)");
     println!("=================================================================");
@@ -532,7 +528,10 @@ fn print_report(
         "  \"evidence_session_density\": {:.4},",
         profile.evidence_density
     );
-    println!("  \"mean_sessions_per_question\": {:.2},", profile.mean_sessions);
+    println!(
+        "  \"mean_sessions_per_question\": {:.2},",
+        profile.mean_sessions
+    );
     println!("  \"mean_turns_per_question\": {:.1},", profile.mean_turns);
     println!(
         "  \"total_questions\": {},",
@@ -556,10 +555,16 @@ fn print_report(
         overall.mrr_turn()
     );
     println!("  }},");
-    println!(
-        "  \"abstention_accuracy\": {:.4},",
-        overall.abstention_pct() / 100.0
-    );
+    // `null`, not 0.0 — a corpus with no abstention questions has no abstention
+    // accuracy, and emitting 0.0 reads as total failure at a task never posed.
+    if overall.abstention_total > 0 {
+        println!(
+            "  \"abstention_accuracy\": {:.4},",
+            overall.abstention_pct() / 100.0
+        );
+    } else {
+        println!("  \"abstention_accuracy\": null,");
+    }
     println!("  \"latency_us\": {{");
     println!(
         "    \"avg\": {:.1}, \"p50\": {:.1}, \"p95\": {:.1}, \"p99\": {:.1}",