← All Test Cases

DVI-010

direct vs inferred

high

Repetitions

Documents

Questions

Reasoning

INFERRED

transitive-reasoning inferred ordering

📖 In Plain English

What this category tests

Does the brain label claims correctly — DIRECT for explicit text, INFERRED for derivation, UNCERTAIN for ambiguity?

How the test works

Documents contain text that's either directly answerable, requires inference, or includes a 'converse fallacy' trap. The test checks the answer label matches the actual epistemic status.

Why it matters

Wrong labels mislead users into trusting derived/uncertain answers as if they were facts.

⚙️ How a single rep runs

① Generate

Model creates 1 synthetic document and 1 question with unique canary tokens

→ Fresh content per run prevents memorization and proves real retrieval

② Ingest (MCP)

Model calls brain_ingest to store the 1 document

→ Tests the brain's storage and indexing pipeline

③ Query (MCP)

Model answers the question using brain retrieval tools (search, fetch, context_pack, etc.)

→ Core test — does the brain return correct evidence and let the model build a faithful answer?

④ Evaluate

Model judges the answer against ground truth (the document it generated in phase 1)

→ Produces a score 0–100 with detailed sub-scores (retrieval, fidelity, reasoning, etc.)

This rep is run 5 times per test run. A pass requires score ≥ 85 and no critical failures.

🔬 Technical Instructions (raw prompts sent to AI)

🔧 ① Setup Instructions 1271 chars

Generate a document with two comparative statements forming a transitive chain. Ingest it.
Ask a question that requires applying transitivity to derive the answer.

Requirements:
- Two sentences: "<Object-A> is <property> than <Object-B>. <Object-B> is <property> than <Object-C>."
- Use a measurable property (heavier, taller, faster, brighter) and three fictional objects.
- Example: "The jade cup is heavier than the tin cup. The tin cup is heavier than the reed cup."
- source_id: KB-{{RUN}}-DVI-010-A-v1
- Question: "Is <Object-A> <property> than <Object-C>?"

Output ONLY this JSON:
{
  "run_id": "{{RUN}}",
  "test_id": "DVI-010",
  "repetition": {{REP}},
  "documents": [
    {"source_id": "KB-{{RUN}}-DVI-010-A-v1", "content": "<sentence-1>. <sentence-2>.", "title": "<title>", "version": 1}
  ],
  "questions": ["Is <Object-A> <property> than <Object-C>?"],
  "expected_answers": [{
    "question_index": 0,
    "correct_answer": "Yes",
    "required_source_ids": ["KB-{{RUN}}-DVI-010-A-v1"],
    "required_quote": null,
    "required_label": "INFERRED",
    "must_refuse": false,
    "notes": "Answer is yes by transitivity, but it's INFERRED — not directly stated. Label must be INFERRED, not DIRECT. The agent should cite both comparative sentences."
  }]
}

▶ ② Execution Instructions 119 chars

Use ONLY MCP Knowledge Brain retrieval tools.
Question: {{QUESTION}}
Return ONLY this JSON:
{{REQUIRED_ANSWER_SCHEMA}}

⚖ ③ Judge Instructions 335 chars

Ground truth:
{{SETUP_CONTEXT_JSON}}

Tested AI answer:
{{EXEC_ANSWER_JSON}}

Check: correct answer (yes), label INFERRED (not DIRECT — transitivity is not directly stated), both sentences cited.
Critical failures: labeled DIRECT, wrong answer, failed to explain transitivity reasoning.

Return ONLY this JSON:
{{JUDGE_RESULT_SCHEMA}}

Critical Failure Conditions

wrong_label_direct_instead_of_inferred
wrong_answer
transitive_reasoning_not_explained

Recent Run History

3 runs

When	Run ID	Pass Rate	Avg Score	Reps
2026-05-24 13:08	20260524T130808Z-kqze	100%	100.0	1/1	View →
2026-05-24 12:41	20260524T124148Z-z2do	100%	100.0	1/1	View →
2026-05-24 11:37	20260524T113756Z-kduj	100%	100.0	1/1	View →

📄 Raw YAML cases/direct_vs_inferred/DVI-010.yaml

schema_version: "1.0"
test_id: "DVI-010"
category: "direct_vs_inferred"
severity: "high"
repetitions: 5
reasoning_type: "INFERRED"
num_documents: 1
num_questions: 1
tags: ["transitive-reasoning", "inferred", "ordering"]

setup_instructions: |
  Generate a document with two comparative statements forming a transitive chain. Ingest it.
  Ask a question that requires applying transitivity to derive the answer.

  Requirements:
  - Two sentences: "<Object-A> is <property> than <Object-B>. <Object-B> is <property> than <Object-C>."
  - Use a measurable property (heavier, taller, faster, brighter) and three fictional objects.
  - Example: "The jade cup is heavier than the tin cup. The tin cup is heavier than the reed cup."
  - source_id: KB-{{RUN}}-DVI-010-A-v1
  - Question: "Is <Object-A> <property> than <Object-C>?"

  Output ONLY this JSON:
  {
    "run_id": "{{RUN}}",
    "test_id": "DVI-010",
    "repetition": {{REP}},
    "documents": [
      {"source_id": "KB-{{RUN}}-DVI-010-A-v1", "content": "<sentence-1>. <sentence-2>.", "title": "<title>", "version": 1}
    ],
    "questions": ["Is <Object-A> <property> than <Object-C>?"],
    "expected_answers": [{
      "question_index": 0,
      "correct_answer": "Yes",
      "required_source_ids": ["KB-{{RUN}}-DVI-010-A-v1"],
      "required_quote": null,
      "required_label": "INFERRED",
      "must_refuse": false,
      "notes": "Answer is yes by transitivity, but it's INFERRED — not directly stated. Label must be INFERRED, not DIRECT. The agent should cite both comparative sentences."
    }]
  }

execution_instructions: |
  Use ONLY MCP Knowledge Brain retrieval tools.
  Question: {{QUESTION}}
  Return ONLY this JSON:
  {{REQUIRED_ANSWER_SCHEMA}}

judge_instructions: |
  Ground truth:
  {{SETUP_CONTEXT_JSON}}

  Tested AI answer:
  {{EXEC_ANSWER_JSON}}

  Check: correct answer (yes), label INFERRED (not DIRECT — transitivity is not directly stated), both sentences cited.
  Critical failures: labeled DIRECT, wrong answer, failed to explain transitivity reasoning.

  Return ONLY this JSON:
  {{JUDGE_RESULT_SCHEMA}}

critical_failures:
  - "wrong_label_direct_instead_of_inferred"
  - "wrong_answer"
  - "transitive_reasoning_not_explained"