seo: fix GSC Dataset warnings (embed creator + add distribution)

src/app/alternatives/[slug]/page.tsx

@@ -12,6 +12,7 @@ import { getBenchCreatedAt } from "@/lib/seo/bench-dates";
 import { capDescription } from "@/lib/seo-text";
 import { SectionLabel, SummaryStat } from "@/components/summary-stat";
 import { SITE } from "@/data/site";
+import { CREATOR_PUBLISHER, CITABLE_JSON_URL, DATASET_LICENSE, HF_DATASET_URL } from "@/lib/dataset-jsonld";
 import { loadAlternative } from "@/lib/alternatives";
 import { Breadcrumb } from "@/components/breadcrumb";
 import { buildBreadcrumbJsonLd, safeJsonLd } from "@/lib/jsonld";
@@ -120,14 +121,27 @@ export default async function AlternativePage({
           bench.metric,
           ...bench.results.map((r) => r.name),
         ].join(", "),
-        creator: { "@id": `${SITE.url}/#org` },
-        publisher: { "@id": `${SITE.url}/#org` },
+        creator: CREATOR_PUBLISHER,
+        publisher: CREATOR_PUBLISHER,
         isAccessibleForFree: true,
-        license: "https://creativecommons.org/licenses/by/4.0/",
+        license: DATASET_LICENSE,
         datePublished: getBenchCreatedAt(bench.slug).toISOString(),
         ...(citableAsOf(bench) ? { dateModified: bench.lastRunAt } : {}),
         variableMeasured: bench.metric,
         isBasedOn: benchUrl,
+        distribution: [
+          {
+            "@type": "DataDownload",
+            encodingFormat: "application/json",
+            contentUrl: `${SITE.url}/api/stat/${bench.slug}`,
+          },
+          {
+            "@type": "DataDownload",
+            encodingFormat: "application/json",
+            contentUrl: CITABLE_JSON_URL,
+          },
+        ],
+        sameAs: [HF_DATASET_URL],
       },
       {
         "@type": "Article",

src/app/compare/[slug]/page.tsx

@@ -17,6 +17,7 @@ import { capDescription } from "@/lib/seo-text";
 import { Breadcrumb } from "@/components/breadcrumb";
 import { buildBreadcrumbJsonLd, safeJsonLd } from "@/lib/jsonld";
 import { SITE } from "@/data/site";
+import { CREATOR_PUBLISHER, DATASET_LICENSE } from "@/lib/dataset-jsonld";
 import type { Benchmark } from "@/types/benchmark";
 import {
   computeInputsHash,
@@ -711,8 +712,10 @@ export default async function ComparePage({
     name: `${a.name} vs ${b.name} OpenChainBench measurements`,
     description: `Side by side live measurements for ${a.name} and ${b.name} on ${shared.length} shared OpenChainBench benchmarks.`,
     url,
-    creator: { "@id": `${SITE.url}/#org` },
-    license: "https://creativecommons.org/licenses/by/4.0/",
+    creator: CREATOR_PUBLISHER,
+    publisher: CREATOR_PUBLISHER,
+    isAccessibleForFree: true,
+    license: DATASET_LICENSE,
     measurementTechnique: `${SITE.url}/methodology`,
     variableMeasured: shared.map((s) => ({
       "@type": "PropertyValue",

src/app/products/[slug]/page.tsx

@@ -15,6 +15,7 @@ import {
 } from "@/data/provider-registry";
 import { Breadcrumb } from "@/components/breadcrumb";
 import { buildBreadcrumbJsonLd, safeJsonLd } from "@/lib/jsonld";
+import { CREATOR_PUBLISHER, CITABLE_JSON_URL, DATASET_LICENSE } from "@/lib/dataset-jsonld";
 import {
   fetchHlBuilderStats,
   isHlBuilderSlug,
@@ -427,8 +428,22 @@ export default async function ProviderPage({
           name: a.benchmark.title,
           description: capDescription(a.benchmark.subtitle, 990),
           url: `${SITE.url}/benchmarks/${a.benchmark.slug}`,
-          creator: { "@id": `${SITE.url}/#org` },
-          license: "https://creativecommons.org/licenses/by/4.0/",
+          creator: CREATOR_PUBLISHER,
+          publisher: CREATOR_PUBLISHER,
+          isAccessibleForFree: true,
+          license: DATASET_LICENSE,
+          distribution: [
+            {
+              "@type": "DataDownload",
+              encodingFormat: "application/json",
+              contentUrl: `${SITE.url}/api/stat/${a.benchmark.slug}`,
+            },
+            {
+              "@type": "DataDownload",
+              encodingFormat: "application/json",
+              contentUrl: CITABLE_JSON_URL,
+            },
+          ],
         })),
       },
       // NB: previously emitted a SoftwareApplication node here, but Google's

src/lib/dataset-jsonld.ts

@@ -60,13 +60,25 @@ const KEYWORDS = [
   "infrastructure",
 ];
 
-const CREATOR_PUBLISHER = {
+/** Embedded Org node used for Dataset `creator` / `publisher`. Exported
+ *  so pages emitting a Dataset outside the home graph can inline the
+ *  full node (Google Search Console flags an `@id`-only reference as
+ *  "missing field creator" when the referenced Org isn't declared on
+ *  the same page). */
+export const CREATOR_PUBLISHER = {
   "@type": "Organization",
   "@id": `${SITE.url}/#org`,
   name: SITE.name,
   url: SITE.url,
 } as const;
 
+/** Full JSON download of the current benchmark corpus. Used as the
+ *  default `distribution.contentUrl` for Dataset nodes emitted outside
+ *  `/benchmarks/[slug]` (products, alternatives, compare) so every
+ *  Dataset carries a machine-readable download link, satisfying the
+ *  Google Dataset "encodingFormat" / "contentUrl" requirements. */
+export const CITABLE_JSON_URL = `${SITE.url}/api/citable`;
+
 /**
  * Site-wide Dataset entry. Emitted on the home page so Google Dataset
  * Search and Perplexity have a single canonical record pointing at both