{
  "schema_version": "proof-evidence-v1",
  "id": "proof-substrate-benchmark",
  "slug": "substrate-benchmark",
  "title": "Controlled benchmark is not public yet",
  "audience": [
    "technical evaluator",
    "buyer"
  ],
  "proof_type": "benchmark",
  "maturity": "benchmark pending",
  "claim_status": "null result",
  "visibility": "planned",
  "sanitization_status": "passed",
  "use_case": "A technical evaluator wants a controlled, reproducible answer to whether structured project context improves agent work.",
  "claim": "No numeric lift claim is public until the preregistered benchmark runs and clears its validity gates.",
  "diff_summary": "This case exists to show claim discipline. The current public result is deliberately a null result.",
  "review_manifest": {
    "evidence_room_url": "/proof/substrate-benchmark#evidence-room",
    "evidence_packet_url": "/proof/substrate-benchmark/evidence.json",
    "fact_count": 3,
    "visible_value_count": 7,
    "data_point_count": 7,
    "source_count": 2,
    "proof_quality_score": 4.2,
    "weakest_quality_dimension": "visual-hierarchy"
  },
  "quality_review": {
    "overall_score": 4.2,
    "overall_label": "Inspectable with caveats",
    "overall_note": "This is a cold-review rubric, not a sales claim. It checks whether the case can be understood, inspected, bounded, and acted on.",
    "dimensions": [
      {
        "id": "cold-audience-clarity",
        "label": "Cold-audience clarity",
        "score": 5,
        "signal": "A reviewer gets the situation, contrast, and buyer decision without reading the JSON.",
        "next": "Tighten the opening latch or before/after language when the case still needs explanation."
      },
      {
        "id": "evidence-visibility",
        "label": "Evidence visibility",
        "score": 4,
        "signal": "The case exposes proof rows, values, source handles, and excerpts before the JSON export.",
        "next": "Add openable artifacts, row links, or public excerpts when the proof still feels referenced rather than shown."
      },
      {
        "id": "limitation-clarity",
        "label": "Limitation clarity",
        "score": 5,
        "signal": "The page names what the case proves and what it does not prove.",
        "next": "Add a sharper boundary when a reader could confuse a demonstrator with a benchmark."
      },
      {
        "id": "visual-hierarchy",
        "label": "Visual hierarchy",
        "score": 3,
        "signal": "The route uses visuals, storyboards, or surface frames to break the proof into inspectable layers.",
        "next": "Promote the proof row into a diagram, table, screenshot projection, or openable artifact."
      },
      {
        "id": "purchase-motivation",
        "label": "Purchase motivation",
        "score": 4,
        "signal": "The proof sends the buyer to an evidence room, artifact link, pricing path, or local run.",
        "next": "Tie the proof to local inspection, pricing, account support, or a narrower try/reject decision."
      }
    ],
    "strongest_dimension": {
      "id": "limitation-clarity",
      "label": "Limitation clarity",
      "score": 5,
      "signal": "The page names what the case proves and what it does not prove.",
      "next": "Add a sharper boundary when a reader could confuse a demonstrator with a benchmark."
    },
    "weakest_dimension": {
      "id": "visual-hierarchy",
      "label": "Visual hierarchy",
      "score": 3,
      "signal": "The route uses visuals, storyboards, or surface frames to break the proof into inspectable layers.",
      "next": "Promote the proof row into a diagram, table, screenshot projection, or openable artifact."
    },
    "next_improvement": "Promote the proof row into a diagram, table, screenshot projection, or openable artifact."
  },
  "evidence_room_url": "/proof/substrate-benchmark#evidence-room",
  "evidence_facts": [
    {
      "id": "no-public-lift-number",
      "label": "No public lift number exists",
      "observed": "The benchmark case publishes no numeric lift result and labels the current result as null.",
      "evidence": "Metric row says current public number is none; claim status is null result.",
      "supports": "Supports the claim-discipline argument that no benchmark number ships before the run clears gates.",
      "status": "publicly inspectable",
      "review": {
        "row": 1,
        "public_review_url": "/proof/substrate-benchmark#fact-no-public-lift-number",
        "packet_pointer": "evidence_facts[0]",
        "visible_value_refs": [
          "data-01-current-public-number",
          "data-05-provenance",
          "data-06-reproducibility",
          "data-07-claim-status"
        ],
        "data_refs": [
          "data-01-current-public-number",
          "data-05-provenance",
          "data-06-reproducibility",
          "data-07-claim-status"
        ],
        "source_ids": [
          "source-01-benchmark-design",
          "source-02-run-artifacts"
        ],
        "case_claim_status": "null result",
        "case_visibility": "planned"
      }
    },
    {
      "id": "three-arms-planned",
      "label": "Three benchmark arms are planned",
      "observed": "The planned benchmark compares project system, generic docs, and competent prompt-only baseline arms.",
      "evidence": "Metric row lists three planned arms; after-artifact summary describes separating structured files from generic docs and prompt-only baselines.",
      "supports": "Supports the benchmark design claim without presenting the result as already run.",
      "status": "public projection",
      "review": {
        "row": 2,
        "public_review_url": "/proof/substrate-benchmark#fact-three-arms-planned",
        "packet_pointer": "evidence_facts[1]",
        "visible_value_refs": [
          "data-02-planned-arms",
          "data-05-provenance",
          "data-07-claim-status"
        ],
        "data_refs": [
          "data-02-planned-arms",
          "data-05-provenance",
          "data-07-claim-status"
        ],
        "source_ids": [
          "source-01-benchmark-design",
          "source-02-run-artifacts"
        ],
        "case_claim_status": "null result",
        "case_visibility": "planned"
      }
    },
    {
      "id": "run-artifacts-pending",
      "label": "Run artifacts are pending",
      "observed": "The source artifact list marks run artifacts as pending, and the limitations state no public benchmark result exists yet.",
      "evidence": "Source artifacts include pending run artifacts; limitations explicitly state the result may be narrow or null.",
      "supports": "Supports the status boundary for the benchmark placeholder.",
      "status": "pending",
      "review": {
        "row": 3,
        "public_review_url": "/proof/substrate-benchmark#fact-run-artifacts-pending",
        "packet_pointer": "evidence_facts[2]",
        "visible_value_refs": [
          "data-03-run-date",
          "data-05-provenance",
          "data-07-claim-status"
        ],
        "data_refs": [
          "data-03-run-date",
          "data-05-provenance",
          "data-07-claim-status"
        ],
        "source_ids": [
          "source-01-benchmark-design",
          "source-02-run-artifacts"
        ],
        "case_claim_status": "null result",
        "case_visibility": "planned"
      }
    }
  ],
  "fact_review_table": [
    {
      "row": 1,
      "id": "no-public-lift-number",
      "label": "No public lift number exists",
      "status": "publicly inspectable",
      "observed": "The benchmark case publishes no numeric lift result and labels the current result as null.",
      "evidence": "Metric row says current public number is none; claim status is null result.",
      "supports": "Supports the claim-discipline argument that no benchmark number ships before the run clears gates.",
      "source_ids": [
        "source-01-benchmark-design",
        "source-02-run-artifacts"
      ],
      "visible_value_refs": [
        "data-01-current-public-number",
        "data-05-provenance",
        "data-06-reproducibility",
        "data-07-claim-status"
      ],
      "data_refs": [
        "data-01-current-public-number",
        "data-05-provenance",
        "data-06-reproducibility",
        "data-07-claim-status"
      ],
      "public_review_url": "/proof/substrate-benchmark#fact-no-public-lift-number",
      "packet_pointer": "evidence_facts[0]"
    },
    {
      "row": 2,
      "id": "three-arms-planned",
      "label": "Three benchmark arms are planned",
      "status": "public projection",
      "observed": "The planned benchmark compares project system, generic docs, and competent prompt-only baseline arms.",
      "evidence": "Metric row lists three planned arms; after-artifact summary describes separating structured files from generic docs and prompt-only baselines.",
      "supports": "Supports the benchmark design claim without presenting the result as already run.",
      "source_ids": [
        "source-01-benchmark-design",
        "source-02-run-artifacts"
      ],
      "visible_value_refs": [
        "data-02-planned-arms",
        "data-05-provenance",
        "data-07-claim-status"
      ],
      "data_refs": [
        "data-02-planned-arms",
        "data-05-provenance",
        "data-07-claim-status"
      ],
      "public_review_url": "/proof/substrate-benchmark#fact-three-arms-planned",
      "packet_pointer": "evidence_facts[1]"
    },
    {
      "row": 3,
      "id": "run-artifacts-pending",
      "label": "Run artifacts are pending",
      "status": "pending",
      "observed": "The source artifact list marks run artifacts as pending, and the limitations state no public benchmark result exists yet.",
      "evidence": "Source artifacts include pending run artifacts; limitations explicitly state the result may be narrow or null.",
      "supports": "Supports the status boundary for the benchmark placeholder.",
      "source_ids": [
        "source-01-benchmark-design",
        "source-02-run-artifacts"
      ],
      "visible_value_refs": [
        "data-03-run-date",
        "data-05-provenance",
        "data-07-claim-status"
      ],
      "data_refs": [
        "data-03-run-date",
        "data-05-provenance",
        "data-07-claim-status"
      ],
      "public_review_url": "/proof/substrate-benchmark#fact-run-artifacts-pending",
      "packet_pointer": "evidence_facts[2]"
    }
  ],
  "visible_values": [
    {
      "id": "data-01-current-public-number",
      "kind": "metric",
      "label": "Current public number",
      "value": "none",
      "note": "The site does not claim a measured productivity lift yet.",
      "public_review_url": "/proof/substrate-benchmark#data-01-current-public-number"
    },
    {
      "id": "data-02-planned-arms",
      "kind": "metric",
      "label": "Planned arms",
      "value": "3",
      "note": "Project system, generic docs, and competent prompt-only baseline.",
      "public_review_url": "/proof/substrate-benchmark#data-02-planned-arms"
    },
    {
      "id": "data-03-run-date",
      "kind": "metadata",
      "label": "Run date",
      "value": "Pending",
      "note": "Date label attached to this public proof case.",
      "public_review_url": "/proof/substrate-benchmark#data-03-run-date"
    },
    {
      "id": "data-04-sample",
      "kind": "metadata",
      "label": "Sample",
      "value": "Not run publicly",
      "note": "Sample size or unit under review.",
      "public_review_url": "/proof/substrate-benchmark#data-04-sample"
    },
    {
      "id": "data-05-provenance",
      "kind": "metadata",
      "label": "Provenance",
      "value": "Benchmark design summary",
      "note": "Where the public projection says the evidence came from.",
      "public_review_url": "/proof/substrate-benchmark#data-05-provenance"
    },
    {
      "id": "data-06-reproducibility",
      "kind": "metadata",
      "label": "Reproducibility",
      "value": "The public harness becomes the source once the run clears gates.",
      "note": "What a reviewer can repeat or inspect publicly.",
      "public_review_url": "/proof/substrate-benchmark#data-06-reproducibility"
    },
    {
      "id": "data-07-claim-status",
      "kind": "metadata",
      "label": "Claim status",
      "value": "null result",
      "note": "The maximum strength of the public claim.",
      "public_review_url": "/proof/substrate-benchmark#data-07-claim-status"
    }
  ],
  "source_register": [
    {
      "id": "source-01-benchmark-design",
      "label": "Benchmark design",
      "kind": "measurement plan",
      "status": "public projection",
      "public_review_url": "/proof/substrate-benchmark#source-01-benchmark-design"
    },
    {
      "id": "source-02-run-artifacts",
      "label": "Run artifacts",
      "kind": "benchmark output",
      "status": "pending run",
      "public_review_url": "/proof/substrate-benchmark#source-02-run-artifacts"
    }
  ],
  "metrics": [
    {
      "label": "Current public number",
      "value": "none",
      "note": "The site does not claim a measured productivity lift yet."
    },
    {
      "label": "Planned arms",
      "value": "3",
      "note": "Project system, generic docs, and competent prompt-only baseline."
    }
  ],
  "run_metadata": {
    "date_label": "Pending",
    "sample_size": "Not run publicly",
    "provenance": "Benchmark design summary",
    "reproducibility": "The public harness becomes the source once the run clears gates."
  },
  "source_artifacts": [
    {
      "label": "Benchmark design",
      "kind": "measurement plan",
      "status": "public projection"
    },
    {
      "label": "Run artifacts",
      "kind": "benchmark output",
      "status": "pending run"
    }
  ],
  "public_evidence_excerpts": [],
  "limitations": [
    "No benchmark result exists on the public site yet.",
    "The final claim may be narrow or null.",
    "The result will be published only after the validity gates pass."
  ],
  "visuals": [
    {
      "label": "Benchmark gate",
      "kind": "benchmark gate",
      "alt": "A benchmark gate diagram holds the public numeric claim until design, run, review, and publish gates pass.",
      "caption": "The null result is deliberate: the site shows the measurement gate before it shows a number.",
      "source_status": "planned artifact",
      "component": "benchmark-gate",
      "src": null
    }
  ],
  "cta": {
    "label": "Read the technology page",
    "href": "/technology"
  }
}