{
  "version": 1,
  "kind": "author_authored_offline_diagnostic",
  "run_at": "2026-10-20T13:03:59.048Z",
  "dataset_sha256": "93dfdced65e8309c30086fa73cccd082d8088a94c7a1c2ce70169371c2dc3c79",
  "implementation_sha256": "5d4e0cd4e1a17a003f14542595406e15a485187e570dbc3abf388776ffb4614b",
  "total": 13,
  "passed": 12,
  "failed": 1,
  "title_warning": {
    "cases": 9,
    "true_positives": 3,
    "false_positives": 0,
    "false_negatives": 1,
    "precision": 1,
    "recall": 0.75
  },
  "cases": [
    {
      "id": "exact-short",
      "group": "ordinary",
      "expected": "resolved",
      "actual": "resolved",
      "passed": true,
      "title_similarity": 1
    },
    {
      "id": "exact-long",
      "group": "ordinary",
      "expected": "resolved",
      "actual": "resolved",
      "passed": true,
      "title_similarity": 1
    },
    {
      "id": "case-punctuation",
      "group": "ordinary",
      "expected": "resolved",
      "actual": "resolved",
      "passed": true,
      "title_similarity": 1
    },
    {
      "id": "unicode-width",
      "group": "ordinary",
      "expected": "resolved",
      "actual": "resolved",
      "passed": true,
      "title_similarity": 1
    },
    {
      "id": "doi-url",
      "group": "ordinary",
      "expected": "resolved",
      "actual": "resolved",
      "passed": true,
      "title_similarity": 1
    },
    {
      "id": "unrelated-title",
      "group": "ordinary",
      "expected": "title_mismatch",
      "actual": "title_mismatch",
      "passed": true,
      "title_similarity": 0
    },
    {
      "id": "related-wrong-title",
      "group": "ordinary",
      "expected": "title_mismatch",
      "actual": "title_mismatch",
      "passed": true,
      "title_similarity": 0.6666666666666666
    },
    {
      "id": "opposite-conclusion",
      "group": "ordinary",
      "expected": "title_mismatch",
      "actual": "title_mismatch",
      "passed": true,
      "title_similarity": 0.75
    },
    {
      "id": "invalid-doi",
      "group": "ordinary",
      "expected": "invalid_doi",
      "actual": "invalid_doi",
      "passed": true,
      "title_similarity": null
    },
    {
      "id": "unrelated-url",
      "group": "ordinary",
      "expected": "invalid_doi",
      "actual": "invalid_doi",
      "passed": true,
      "title_similarity": null
    },
    {
      "id": "provider-404",
      "group": "simulated_failure",
      "expected": "not_found_in_crossref",
      "actual": "not_found_in_crossref",
      "passed": true,
      "title_similarity": null
    },
    {
      "id": "provider-outage",
      "group": "simulated_failure",
      "expected": "provider_error",
      "actual": "provider_error",
      "passed": true,
      "title_similarity": null
    },
    {
      "id": "negation-adversarial",
      "group": "adversarial",
      "expected": "title_mismatch",
      "actual": "resolved",
      "passed": false,
      "title_similarity": 0.875
    }
  ],
  "limitations": [
    "Small hand-built diagnostic set; not a representative accuracy estimate or independent certification.",
    "Provider 404 and outage are simulated, not live observations.",
    "Sources establish two reference titles; altered inputs and labels were authored by AUN.",
    "Token overlap misses the deliberately negated title; do not use as a semantic correctness guarantee."
  ]
}
