Direct answer
A feature is a pipeline of capture, preprocessing, inference, validation, persistence, and user action. Model output is only one stage.
This page does not publish benchmark or compatibility results. It shows the evidence required to answer on-device AI result provenance without turning an assumption into a product claim.
Evidence to collect
The claim becomes reviewable only when the following evidence is attached to the same artifact and test run:
- Result metadata schema
- Source linkage
- Migration and export test
Task quality needs a versioned corpus and acceptance rules. Fluent sample output is not an accuracy result.
Implementation workflow
- Write the user promise and offline requirement.
- Separate source data from derived output.
- Define typed stage contracts.
- Create privacy-safe fixtures and expected properties.
- Test each stage without hiding partial failure.
- Run the complete task in airplane mode and through lifecycle changes.
Keep each transition observable. A failure should identify the stage, artifact, runtime, and recovery action without logging private user content.
Failure patterns to prevent
- Showing output without model identity
- Embedding raw private input in diagnostics
Also prevent silent fallback, unpinned artifacts, missing cancellation, and conclusions that combine unlike configurations. Store unsuccessful runs alongside successful ones.
Minimum reproducibility record
| Layer | Record |
|---|---|
| Device | Manufacturer, model, chipset, RAM class, operating-system build |
| Software | Application version and git commit |
| Model | Family, variant, revision, format, file length, hash, quantization |
| Runtime | Name, revision, requested backend, observed backend evidence |
| Workload | Fixture revision, input hash, prompt hash, output policy |
| Outcome | Completed, failed, cancelled, fallback, and privacy-safe diagnostics |
Release checklist
- ☐ The primary query is answered without an unsupported number.
- ☐ Every artifact and runtime is pinned.
- ☐ The representative task and failure policy are explicit.
- ☐ Lifecycle, cancellation, cleanup, and fallback are tested.
- ☐ User-content and network boundaries are documented.
- ☐ Result wording applies only to the recorded configuration.
- ☐ The page links to raw method or evidence when results are added.
Sources and related evidence
This page relies on the Cove fact ledger and benchmark policy. Results remain blocked until raw records exist.
Chinese deployment and troubleshooting content is organized in the 奇连 AI 端侧专题.