AI evaluation and safety evidence
Evaluation plan, benchmark, run, results, risk assessment and decision on permissible use. Metric, dataset and evidence are reused.
Research draft, second pass
A second pass drafted this model: the structure a model of this thing needs, and what is known about it in the world. The line under this one says how the second half was obtained - researched against sources, or recalled without web access, in which case nothing here was read anywhere and every claim is a lead to verify. Unreviewed either way.
Bundle → Layer → Finding → Questions Missing, in the backlog
Not described yet. This gap is in the card backlog.
Note: Research contour: bundles not designed yet; questions are listed as open questions.
Classifiers Filled
- Family
- Enterprise profiles
- Category
- Enterprise subject
- Entry kind
- subject
- Domain
- EnterpriseAI
- Industry
- Cross-industry
- Tags
- EM-AI-03W3subjectEvaluationPlanEvaluationRunBenchmarkSpecificationSafetyAssessmentDeploymentDecision
What it is Filled
Evaluation plan, benchmark, run, results, risk assessment and decision on permissible use. Metric, dataset and evidence are reused.
Why it exists Filled
Evaluation plan, benchmark, run, results, risk assessment and decision on permissible use. Metric, dataset and evidence are reused.
Distinguishing features Derived, awaiting review
- A result pins the model and dataset versions
- An evaluation is not universal outside its context
- A decision has an accountable owner and conditions
What robots and AI may and may not do Derived, awaiting review
Must not
- Negative case: One high benchmark score declares the system safe for all tasks.
Note: Negative case of the research brief, not yet a rule for agents.
Moral aspects Missing, in the backlog
Not described yet. This gap is in the card backlog.
Owners Filled
Steward
Руководитель AI / исследований
Master systems
- Model registry
- experiment tracker
- eval store
Links to other meta-models Filled
neighbor
- EM-AI-01
- EM-AI-02
references
- WM-AI-003 - conceptual-candidate
- WM-AI-009 - conceptual-candidate
- WM-AI-008 - conceptual-candidate
- WM-AI-010 - conceptual-candidate
What else AI and robots need to interact with it Incomplete
Identity and identifiers required Derived, awaiting review
- EvaluationPlan
- EvaluationRun
- BenchmarkSpecification
- SafetyAssessment
- DeploymentDecision
Direct properties not applicable Not applicable
Not applicable
Enterprise record contour: physical properties belong to referenced world models.
Recognition required Missing, in the backlog
Not described yet. This gap is in the card backlog.
Capabilities and actions required Missing, in the backlog
Not described yet. This gap is in the card backlog.
Hazards and failure modes required Missing, in the backlog
Not described yet. This gap is in the card backlog.
Standards and interfaces required Missing, in the backlog
Not described yet. This gap is in the card backlog.
Context of use required Missing, in the backlog
Not described yet. This gap is in the card backlog.
Sources Filled
- NIST AI RMF: context, evaluation and risk management
- PROV/SPDX: provenance of data, artifacts and actions
- Model registry/evaluation tooling practice; map system, artifact, run and endpoint
Open questions
- How to detect benchmark leakage into training?
- How to separate capability measurement from permissibility of use?
- How to account for uncertainty and a context change?
- Установить границу и решение reuse/extend/new по действующим спецификациям.
- Подтвердить semantic crosswalk, права и source mastership.
- Выбрать immutable refs; провести проверки fixtures до заявления о публикационной готовности.
Machine files
Provenance
enterprise research programme · published-partial
Built from: enterprise/models/em-ai-03/brief.json
Still in Russian: suggested owner, blocking decisions, vercy candidates. Translate in research/enterprise/i18n/units.en.json.