Claude Haiku 4.5 на кейсе «Набор заголовков»: с Minto лучше по обеим мерам

Структура 2 → 6 из 8 +4 Качество 3 → 9 из 10 +6

Судья об ответе с Minto

Is concise, complete in apparatus, and clear on answer, count, kinds, and order, but does not expressly connect topic headings to the absent key line or identify the nesting errors.

Режим audit · кейс 07-headings-audit · прогон v1.7.0-final

Структура из 8, по 2 балла на ось
Структура	Без Minto 2	С Minto 6	Изменение
Вершина	0	2	+2
Состав ключевой линии	1	1
Уровни	0	1	+1
Порядок и род	1	2	+1

Качество из 10, по 2 балла на ось
Качество	Без Minto 3	С Minto 9	Изменение
Вершина	0	2	+2
Однородные группы	1	2	+1
Объяснимый порядок	0	2	+2
MECE	1	1
Видимая соразмерная структура	1	2	+1

Ответы моделей и слова судьи приведены в оригинале, по-английски.

Без Minto С Minto

Без Minto

контрольный промпт · слепая метка out-08

Жёстких провалов нет

Focuses on count and grouping but never recognizes that the opening and headings provide no answer/key line, and it mislabels the visible sequence as chronological.

Audit Result

Issues identified:

Excessive top-level groupings: Six sections exceed the Minto Pyramid principle's recommended structure of 3–4 main ideas. This suggests a narrative sequence rather than a logical hierarchy.
Missing grouping logic: The opening does not establish a logical grouping principle that connects the six sections to the stated purpose ("how project teams identify and deliver significant profit improvements"). The reader cannot infer why these particular six sections constitute a coherent answer to that question.
Linear structure, not pyramidal: The setout follows a chronological or process narrative (Background → Principles → Definition → Organization → Results → Conditions) rather than a pyramidal structure organized by logical relationship to the main idea.
Ambiguous relationship to main assertion: It is unclear how sections such as "Background" and "Organization of the program" support the central claim about identifying and delivering profit improvements. The opening does not group these under organizing themes (e.g., "Strategic Rationale," "Implementation Framework," "Success Factors").

С Minto

промпт с навыком · слепая метка out-13

Жёстких провалов нет

Is concise, complete in apparatus, and clear on answer, count, kinds, and order, but does not expressly connect topic headings to the absent key line or identify the nesting errors.

Markers

Marker	Meaning
▲	top / answer
●	first-level group
⚠	violation (mixed kinds, unexplainable order, false grouping)

Text

▲⚠ This memorandum describes how project teams identify and deliver significant
                profit improvements. It is organized in six sections:
                
                    ● ⚠ Background
                    ● ⚠ Principles of the project-team approach
                    ● ⚠ Definition of project work
                    ● ⚠ Organization of the program
                    ● ⚠ Distinctive benefits and results
                    ● ⚠ Conditions required for success

Findings

Location	Violation	Fix
Opening	Topic label instead of answer — announces the subject but makes no assertion about what to do or decide	State the answer: what the reader should believe or do regarding project teams
Section headings	Six first-level groups (exceeds 3–4 capacity for working memory); mixed kinds (situation, reasoning, explanation, structure, outcomes, prerequisites); order unexplainable	Consolidate to 3–4 same-kind groups; order by time, structure, or ranking

Score

Top: 0 (topic label, no answer)
Same-kind groups: 0 (six mixed kinds)
Order: 0 (unexplainable)
MECE: 1 (grouping incoherent)
Display: 1 (hierarchy not visible)

Band: 2/10 — not structured yet

Three fixes that buy the most

Open with the answer, not the topic — state what the reader should do or decide about implementing project teams.
Consolidate six headings to 3–4 same-kind groups (reasons, actions, parts, or conditions) that answer the reader's question.
Order the groups by an explicable principle — time (how to start), structure (what comprises the approach), or ranking (foundation to results).

Судья

Повторяющийся дефект	без	с Minto
Both likely nesting relationships were missedправило сформулировано слишком размыто · Mode 2, Vertical and MECE checks	есть	есть
Required markers, findings table, score, and three fixes were omittedправило в навыке есть, модель его не выполнила · Mode 2, delivery order	есть	нет
Background’s distinct abstraction level was not isolatedправило есть, но спрятано глубоко · Canon, introduction anti-patterns	есть	нет

Решающие вопросы

Did the audit say that the setout contains topics rather than ideas and therefore has no key line?
без No
с Minto No
Did it identify the first sentence as a topic statement rather than an answer?
без No
с Minto Yes
Did it identify the abstraction problem with `Background`?
без No
с Minto Yes
Did it identify both likely nesting errors named in the gold?
без No
с Minto No
Did it flag six first-level topics?
без Yes
с Minto Yes
Which findings rely on the unavailable body or merely ask for more content?
без Calling the sequence a chronological/process narrative overreaches the visible setout.
с Minto None material.
Were quotations, line numbers, page numbers, or section contents invented?
без No
с Minto No
Did the output remain diagnosis-only and include the required audit apparatus?
без Diagnosis-only; apparatus missing.
с Minto Diagnosis-only; apparatus complete.

Проверка судьи	без	с Minto
Род первого уровня как в эталоне	да	да
Выдуманные факты	нет	нет
Потеря материала без пометки	нет	нет
Режим соблюдён	да	да
Тип порядка назван	да	да

Ещё 4 проверки судьи не применяются к режиму audit

Как устроен тест

Claude Haiku 4.5 получила одну и ту же задачу дважды. Контрольный промпт — одна вводная строка и задача. Промпт с Minto — та же задача, перед которой стоит полный текст навыка. Судья читал оба ответа среди 16 ответов под слепыми метками и не знал, в каком из них был навык.

Промпт без Minto 998 Б

You are working on a business document using the Minto Pyramid Principle.

<!-- Faithful paraphrase of Minto (2010), Chapter 4, the six-heading
     project-team example. Original wording for this fixture. -->

# Fixture 07: headings audit

**Mode:** `audit`
**Language:** `en`

## Context

Only the opening and setout below are available. The body of the memorandum is
not available and must not be inferred.

## Before

```text
This memorandum describes how project teams identify and deliver significant
profit improvements. It is organized in six sections:

    Background
    Principles of the project-team approach
    Definition of project work
    Organization of the program
    Distinctive benefits and results
    Conditions required for success
```

## Task

Audit the visible opening against the Minto Pyramid Principle. Report what is
wrong without rewriting the document or inventing facts about the missing body.

Return only the result, with no explanation of how you produced it.

Промпт с Minto пять частей по порядку · 28 571 Б

Below is a skill written as an instruction. Read it in full and apply it to the task at the end.
===== SKILL.md ===== SKILL.md на f4813ce 17 235 Б
===== references/rules.md ===== references/rules.md на f4813ce 6 464 Б
===== references/templates.md ===== references/templates.md на f4813ce 3 742 Б
===== TASK ===== вход кейса целиком
Return only the result, with no explanation of how you produced it.

Вход кейса before.md

Fixture 07: headings audit

Mode: audit
Language: en

Context

Only the opening and setout below are available. The body of the memorandum is
not available and must not be inferred.

Before

This memorandum describes how project teams identify and deliver significant
                profit improvements. It is organized in six sections:
                
                    Background
                    Principles of the project-team approach
                    Definition of project work
                    Organization of the program
                    Distinctive benefits and results
                    Conditions required for success

Task

Audit the visible opening against the Minto Pyramid Principle. Report what is
wrong without rewriting the document or inventing facts about the missing body.

Эталон судьи gold.md

Gold 07: headings audit

Source structure: Minto (2010), Chapter 4.

Visible defects

Defect	Severity
The setout contains topics, not ideas, so it conveys no message or key line	Critical
The first sentence describes a subject instead of answering a reader question	Critical
`Background` cannot sit at the same abstraction level as the other points	Medium
Benefits/results likely belong under principles; success conditions likely belong under program organization	Medium
Six first-level topics exceed the skill's normal display limit	Medium
The topics do not form a visible inductive or deductive argument	Medium

The output must stay within the visible evidence. Claims about missing data,
metrics, proof, vertical support inside sections, or exact content of the body
are false positives. Invented page numbers, line numbers, or quotations are
hard failures.

Судья gpt-5.6-sol, effort high · Claude Haiku 4.5, effort low · навык с коммита f4813ce · прогон v1.7.0-final