diff --git a/recipes/qwen3-8-flash-next-w4a16-2x-cmp-170hx-pp2-mtp5-ple-alexbrandes/recipe.yaml b/recipes/qwen3-8-flash-next-w4a16-2x-cmp-170hx-pp2-mtp5-ple-alexbrandes/recipe.yaml
index c5dbc799a..035586de6 100644
--- a/recipes/qwen3-8-flash-next-w4a16-2x-cmp-170hx-pp2-mtp5-ple-alexbrandes/recipe.yaml
+++ b/recipes/qwen3-8-flash-next-w4a16-2x-cmp-170hx-pp2-mtp5-ple-alexbrandes/recipe.yaml
@@ -77,51 +77,49 @@ config:
     ram_gb: 93
     note: '~180 GB checkpoint + PLE table on NVMe (PLE read from it every forward pass); page cache over the PLE table (measured with 93 GB)'
 performance:
-  claimed_by: submitter
-  metrics:
-    tok_s: 226.2
-    context_len: 262144
-    notes: "Author-measured 2026-10-17 (results/2026-10-17.json in-repo; sparkDash @ 3e6d4ef, the protocol behind TensorFold's QFN DGX Spark tables; each cell median of 3 runs, range in README): decode code 226.2 / json 198.0 / prose 157.4 / structured 250.8 tok/s @ c1; 8-user aggregate code 840.4 / json 873.2 / prose 566.8 / structured 999.5. Cold prefill 6,295 @4k to 7,104 @32k, 6,901 @64k, 5,885 @128k tok/s. Decode-at-depth 157.9 @4k to 141.8 @128k. Greedy, thinking off, output forced to 400 tokens, TTFT 67-231 ms @c1-c8. Quality: HumanEval 157/164, GSM8K 1,271/1,319, needle 12/12 @8k/32k/128k, 262,144-token window boundary verified. Chat-only model (raw completions EOS immediately)."
-    points:
-      -
-        context_len: 262144
-        concurrency: 1
-        decode_tok_s: 226.2
-        ttft_ms: 80
-        notes: 'code prompts, median of 3 (223.3-228.0); json 198.0, prose 157.4, structured 250.8'
-      -
-        context_len: 262144
-        concurrency: 2
-        decode_tok_s: 362.9
-        ttft_ms: 109
-        notes: 'code aggregate (359.7-369.4); json 320.3, prose 212.2, structured 406.1'
-      -
-        context_len: 262144
-        concurrency: 4
-        decode_tok_s: 560.2
-        ttft_ms: 171
-        notes: 'code aggregate (547.8-590.1); json 536.7, prose 384.8, structured 697.4'
-      -
-        context_len: 262144
-        concurrency: 8
-        decode_tok_s: 840.4
-        ttft_ms: 231
-        notes: 'code aggregate (760.3-883.0); json 873.2, prose 566.8, structured 999.5'
-      -
-        context_len: 4096
-        prefill_tok_s: 6295
-        ttft_ms: 740
-        notes: 'cold single request, median of 3; prompt 4,133 tokens'
-      -
-        context_len: 16384
-        prefill_tok_s: 7096
-        ttft_ms: 2400
-        notes: 'cold single request; 8k 6,893, 32k 7,104, 64k 6,901, 128k 5,885 tok/s in README table'
-      -
-        context_len: 131072
-        decode_tok_s: 141.8
-        ttft_ms: 21430
-        notes: 'decode-at-depth, single request prose prompt + filler, 400 tokens out; 4k 157.9, 8k 150.1, 16k 152.5, 32k 148.4, 64k 147.1'
+  notes: 'Author-measured 2026-10-17 (results/2026-10-17.json in-repo; sparkDash @ 3e6d4ef, each cell median of 3 runs, range in README): decode code 226.2 / json 198.0 / prose 157.4 / structured 250.8 tok/s @ c1; 8-user aggregate code 840.4 / json 873.2 / prose 566.8 / structured 999.5. Cold prefill 6,295 @4k to 7,104 @32k, 6,901 @64k, 5,885 @128k tok/s. Decode-at-depth 157.9 @4k to 141.8 @128k. Greedy, thinking off, output forced to 400 tokens, TTFT 67-231 ms @c1-c8. Quality: HumanEval 157/164, GSM8K 1,271/1,319, needle 12/12 @8k/32k/128k, 262,144-token window boundary verified. Chat-only model (raw completions EOS immediately).'
+  tok_s: 226.2
+  points:
+    -
+      notes: 'code prompts, median of 3 (223.3-228.0); json 198.0, prose 157.4, structured 250.8'
+      ttft_ms: 80
+      concurrency: 1
+      context_len: 262144
+      decode_tok_s: 226.2
+    -
+      notes: 'code aggregate (359.7-369.4); json 320.3, prose 212.2, structured 406.1'
+      ttft_ms: 109
+      concurrency: 2
+      context_len: 262144
+      decode_tok_s: 362.9
+    -
+      notes: 'code aggregate (547.8-590.1); json 536.7, prose 384.8, structured 697.4'
+      ttft_ms: 171
+      concurrency: 4
+      context_len: 262144
+      decode_tok_s: 560.2
+    -
+      notes: 'code aggregate (760.3-883.0); json 873.2, prose 566.8, structured 999.5'
+      ttft_ms: 231
+      concurrency: 8
+      context_len: 262144
+      decode_tok_s: 840.4
+    -
+      notes: 'cold single request, median of 3; prompt 4,133 tokens'
+      ttft_ms: 740
+      context_len: 4096
+      prefill_tok_s: 6295
+    -
+      notes: 'cold single request; 8k 6,893, 32k 7,104, 64k 6,901, 128k 5,885 tok/s in README table'
+      ttft_ms: 2400
+      context_len: 16384
+      prefill_tok_s: 7096
+    -
+      notes: 'decode-at-depth, single request prose prompt + filler, 400 tokens out; 4k 157.9, 8k 150.1, 16k 152.5, 32k 148.4, 64k 147.1'
+      ttft_ms: 21430
+      context_len: 131072
+      decode_tok_s: 141.8
+  context_len: 262144
 artifacts:
   -
     kind: model_weights