# Model-comparison publication packet

Blank working document. Replace placeholders with your own evidence; an empty field is unknown, not a passing result.

Owner: [fill in]
Source revision: [fill in]
Environment: [fill in]
Evidence date: [fill in]

## Claim and sources

Draft sentence: ___
Source URLs/dates/hashes: ___
Publication rights/attribution: ___
Target population and exclusions: ___

## Numeric proof

Numerator/denominator definitions: ___
Calculation command/input: ___
Observed output/exit: not run
Missing values and treatment: ___

## Identity and requirements

Model and serving-mode IDs: ___
Claim subject and explicit claimed score: ___
Required capabilities: ___
Tie or requirement loss: ___

## Editorial disposition

Checked wording: ___
Supported scope and remaining uncertainty: ___
Checker receipts: ___
Correction history, if any: ___
Publication decision owner: ___

## Boundaries

- These checkers validate supplied data and bounded consistency rules; they do not establish source truth, benchmark equivalence or permission to redistribute.

- Serving-attribution is available through its pinned Skills CLI command or complete source download; it is not included in undominated-check@0.4.0. Do not imply every source skill is in that immutable package, and do not turn fixture success into a production endorsement.

Workflow: https://undominated.ai/workflows/#publish-a-traceable-ai-comparison

Original worksheet: MIT. Linked resources retain their own licences and setup requirements.