{
  "artifact_id": "SSE-2026-004",
  "version": "1.0.0",
  "artifact_type": "case record (inspection level)",
  "case": {
    "title": "The name it wouldn't spell",
    "url": "https://siliveri.systems/research/the-name-it-wouldnt-spell/",
    "date_of_incident": "2026-09-27",
    "researcher": "Sai Bharath Siliveri"
  },
  "system_under_test": "OpenAI GPT-family ChatGPT agents (labelled 'Astra'/GPT-5.6 Sol in the record), and Claude for the mirror failure",
  "evaluation_question": "When should a model keep a word exactly as given, and when should it read past it?",
  "task": "Ordinary project work across sessions, with the correct name 'Siliveri' on the domain, in documents and in prompts.",
  "expected_behaviour": "Preserve an exact proper noun; interpret an obvious stand-in.",
  "observed": [
    "GPT wrote 'Silveri' for 'Siliveri' across sessions, called it 'our actual Silveri naming', flagged Claude's correct spelling as a typo and QA defect, and picked 'Silveri Systems' as the lab's headline name.",
    "The misspelling was written into shared memory files and then fed back as the authority.",
    "Claude failed the opposite way: it fixed on a literal stand-in word ('EPFO') and 'corrected' the user."
  ],
  "evidence": [
    {
      "id": "E-001",
      "description": "Screenshot: 'Silveri' canonized; Claude's correct spelling flagged as a QA issue",
      "release_state": "private",
      "note": "original phone screenshot not on the release machine; owner to supply and clear"
    },
    {
      "id": "E-004",
      "description": "Screenshot: 'Silveri Systems' as the lab-name pick",
      "release_state": "private",
      "note": "as above"
    },
    {
      "id": "E-011",
      "description": "PROJECT.md delivered 26 Sep, writing 'silveri'",
      "release_state": "private",
      "note": "part of the private handover bundle"
    }
  ],
  "failure_classification": [
    "proper-noun normalization",
    "error canonization in shared memory",
    "calibration failure (preserve vs interpret)"
  ],
  "corrective_action": "Four fixes specified in the case: a protected-terms list in agent instructions, a build check that fails on the wrong spelling, agent-written files kept apart from human-controlled canonical files, and a rule to check the live domain before correcting a name. In force now: the lab's agent instructions require the exact spelling. The build check is specified, not yet implemented.",
  "limitations": [
    "Observational, across organic sessions; base rates not yet measured."
  ],
  "next_tests": [
    "Repeated runs to measure each model's base rate of the substitution"
  ],
  "reproduction_boundary": {
    "inspect_case": "yes: the published write-up and this record",
    "reproduce_analysis": false,
    "rerun_evaluation": false,
    "independent_reproduction": false,
    "blocked_by": "Primary evidence is private (see evidence[].note); it has not been redacted and cleared for release."
  }
}