hanzo.ai/components/benchmarks/JsonLd.tsx

import { BENCHMARKS, benchUrl, paperUrl, type Bench } from '@/lib/benchmarks'

/**
 * What a bench page says to a machine.
 *
 * Three entities, because three different things are true of one page and
 * flattening them loses the part that matters:
 *
 *   Dataset          the benchmark itself — somebody else's work, under
 *                    somebody else's licence. `url` is this page, which is what
 *                    schema.org means by it (the page DESCRIBING the dataset),
 *                    and `sameAs` is the repo or dataset card that actually
 *                    holds it, so the claim is "we describe this" and never
 *                    "we made this".
 *   WebPage          this page, `about` the dataset, published by the
 *                    Organization the root layout already declares — referenced
 *                    by its `@id` rather than described a second time.
 *   BreadcrumbList   /benchmarks → this one. Two levels, which is all there is.
 *
 * A ScholarlyArticle joins them where a paper of ours reports the numbers, and
 * its `about` points back at the same Dataset node, so the paper, the page and
 * the benchmark are one graph rather than three assertions that happen to share
 * a subject.
 *
 * A bench with no runs gets the page and the breadcrumb and no Dataset:
 * `variableMeasured` on a benchmark nothing has been run on would describe
 * measurements that do not exist.
 */

const SITE = 'https://hanzo.ai'
const ORG = `${SITE}/#organization`
const INDEX = `${SITE}/benchmarks`

/**
 * `</script>` inside a JSON string ends the block and the rest of the page
 * becomes markup. Nothing here contains one today, which is exactly the
 * condition under which it later will.
 */
const embed = (value: unknown) => JSON.stringify(value).replace(/</g, '\\u003c')

export function BenchJsonLd({ b, measures }: { b: Bench; measures?: string[] }) {
  const url = benchUrl(b.slug)
  const dataset = b.dataset
    ? {
        '@type': 'Dataset',
        '@id': `${url}#dataset`,
        name: b.dataset.name,
        description: b.lede,
        url,
        sameAs: [b.dataset.url, b.dataset.paper.url],
        license: b.dataset.license,
        isAccessibleForFree: true,
        creator: { '@type': 'Organization', name: b.dataset.paper.authors },
        citation: {
          '@type': 'ScholarlyArticle',
          name: b.dataset.paper.title,
          url: b.dataset.paper.url,
        },
        ...(measures?.length ? { variableMeasured: measures } : {}),
        measurementTechnique: b.harness.command,
      }
    : null

  const graph = [
    ...(dataset ? [dataset] : []),
    {
      '@type': 'WebPage',
      '@id': url,
      url,
      name: `${b.title} — Hanzo AI`,
      description: b.lede,
      isPartOf: { '@type': 'WebPage', '@id': INDEX, name: 'Benchmarks', url: INDEX },
      publisher: { '@id': ORG },
      ...(dataset ? { about: { '@id': `${url}#dataset` } } : {}),
    },
    {
      '@type': 'BreadcrumbList',
      itemListElement: [
        { '@type': 'ListItem', position: 1, name: 'Benchmarks', item: INDEX },
        { '@type': 'ListItem', position: 2, name: b.name, item: url },
      ],
    },
    ...b.papers.map((p) => ({
      '@type': 'ScholarlyArticle',
      name: p.title,
      url: paperUrl(p),
      author: { '@id': ORG },
      ...(dataset ? { about: { '@id': `${url}#dataset` } } : {}),
    })),
  ]

  return (
    <script
      type="application/ld+json"
      dangerouslySetInnerHTML={{ __html: embed({ '@context': 'https://schema.org', '@graph': graph }) }}
    />
  )
}

/**
 * The index, as the list it is.
 *
 * An `ItemList` of the bench pages rather than a Dataset of its own: /benchmarks
 * measures nothing itself, it says what has been measured and where each one
 * lives.
 */
export function IndexJsonLd() {
  const graph = [
    {
      '@type': 'ItemList',
      '@id': `${INDEX}#list`,
      name: 'Hanzo benchmarks',
      numberOfItems: BENCHMARKS.length,
      itemListElement: BENCHMARKS.map((b, i) => ({
        '@type': 'ListItem',
        position: i + 1,
        name: b.name,
        url: benchUrl(b.slug),
      })),
    },
    {
      '@type': 'BreadcrumbList',
      itemListElement: [{ '@type': 'ListItem', position: 1, name: 'Benchmarks', item: INDEX }],
    },
  ]
  return (
    <script
      type="application/ld+json"
      dangerouslySetInnerHTML={{ __html: embed({ '@context': 'https://schema.org', '@graph': graph }) }}
    />
  )
}