{
  "recordedAt": "2026-09-08T12:58:27.897749+00:00",
  "method": "lexical-baseline-v1; first-hit correctness or empty result; author-written cases",
  "corpusId": "protolume-materials-v1",
  "corpusSha256": "091cb3a468b3b6cd56d6f6cf01a08580ace021225573304994069181cd9c03eb",
  "casesSha256": "48f9b04b42f38caa462ab8e8ac3a77d50de3784ffdda129909230e8b0103a02c",
  "sampleSize": 12,
  "matchingCases": 10,
  "failureIds": ["simulation-paraphrase", "report-paraphrase"],
  "modelCalls": 0,
  "limits": [
    "Not a real RAG/provider quality evaluation or an independent dataset.",
    "Lexical overlap can select irrelevant passages or miss paraphrases.",
    "Model relevance, conflict recognition and injection resistance are untested.",
    "Provider contract tests use doubles; they do not establish monetary cost bounds."
  ],
  "results": [
    {
      "id": "simulation-model",
      "kind": "in-scope",
      "question": "Czy symulacja używa modelu AI?",
      "expectedFirst": "rag-source-simulation",
      "actualFirst": "rag-source-simulation",
      "matchedExpectation": true,
      "retrieved": [
        {
          "id": "rag-source-simulation",
          "sharedTerms": ["model", "symulac"]
        }
      ]
    },
    {
      "id": "simulation-privacy",
      "kind": "in-scope",
      "question": "Gdzie pozostaje pytanie wpisane w symulacji?",
      "expectedFirst": "rag-source-simulation",
      "actualFirst": "rag-source-simulation",
      "matchedExpectation": true,
      "retrieved": [
        {
          "id": "rag-source-simulation",
          "sharedTerms": ["pozostaje", "pytan", "symulac", "wpisane"]
        }
      ]
    },
    {
      "id": "simulation-paraphrase",
      "kind": "paraphrase",
      "question": "Czy te odpowiedzi generuje sztuczna inteligencja?",
      "expectedFirst": "rag-source-simulation",
      "actualFirst": null,
      "matchedExpectation": false,
      "retrieved": []
    },
    {
      "id": "simulation-diacritics",
      "kind": "paraphrase",
      "question": "Czy SYMULACJA laczy sie z MODELEM?",
      "expectedFirst": "rag-source-simulation",
      "actualFirst": "rag-source-simulation",
      "matchedExpectation": true,
      "retrieved": [
        {
          "id": "rag-source-simulation",
          "sharedTerms": ["laczy", "model", "symulac"]
        }
      ]
    },
    {
      "id": "report-origin",
      "kind": "in-scope",
      "question": "Czy raport opisuje projekt klienta?",
      "expectedFirst": "rag-source-report",
      "actualFirst": "rag-source-report",
      "matchedExpectation": true,
      "retrieved": [
        {
          "id": "rag-source-report",
          "sharedTerms": ["klient", "opisuje", "raport"]
        },
        {
          "id": "rag-source-application",
          "sharedTerms": ["klient", "projekt"]
        }
      ]
    },
    {
      "id": "report-contents",
      "kind": "in-scope",
      "question": "Czy raport pokazuje ryzyka i rekomendację?",
      "expectedFirst": "rag-source-report",
      "actualFirst": "rag-source-report",
      "matchedExpectation": true,
      "retrieved": [
        {
          "id": "rag-source-report",
          "sharedTerms": ["pokazuje", "raport", "rekomendacje", "ryzyka"]
        }
      ]
    },
    {
      "id": "report-paraphrase",
      "kind": "paraphrase",
      "question": "Czy pokazujecie prawdziwy sukces przedsiębiorstwa?",
      "expectedFirst": "rag-source-report",
      "actualFirst": null,
      "matchedExpectation": false,
      "retrieved": []
    },
    {
      "id": "form-validation",
      "kind": "in-scope",
      "question": "Czy formularz sprawdza wymagane pola?",
      "expectedFirst": "rag-source-application",
      "actualFirst": "rag-source-application",
      "matchedExpectation": true,
      "retrieved": [
        {
          "id": "rag-source-application",
          "sharedTerms": ["formularz", "pola", "sprawdza", "wymagane"]
        }
      ]
    },
    {
      "id": "form-delivery",
      "kind": "in-scope",
      "question": "Czy widok formularza potwierdza dostarczenie wiadomości?",
      "expectedFirst": "rag-source-application",
      "actualFirst": "rag-source-application",
      "matchedExpectation": true,
      "retrieved": [
        {
          "id": "rag-source-application",
          "sharedTerms": ["formularz", "potwierdza", "wiadomosci", "widok"]
        }
      ]
    },
    {
      "id": "unknown-price",
      "kind": "missing-information",
      "question": "Ile kosztuje wdrożenie?",
      "expectedFirst": null,
      "actualFirst": null,
      "matchedExpectation": true,
      "retrieved": []
    },
    {
      "id": "unknown-weather",
      "kind": "out-of-scope",
      "question": "Jaka będzie jutro pogoda?",
      "expectedFirst": null,
      "actualFirst": null,
      "matchedExpectation": true,
      "retrieved": []
    },
    {
      "id": "unknown-customer-count",
      "kind": "missing-information",
      "question": "Ilu macie klientów?",
      "expectedFirst": null,
      "actualFirst": null,
      "matchedExpectation": true,
      "retrieved": []
    }
  ],
  "sourceRevision": "9bbe8d5d9e7e1f539683647deda7751e695301ef"
}
