Theory Intermediate 2 minute read Updated 2026-06-26 UTC

Inheritance and variation

A precise artifact-level interpretation of parentage, inherited traits, mutation operators, and descendant records.

Research statusImplementation-oriented synthesis Publication statePublished Reviewed byMichael Kappel Source reports3

The engineering meaning of inheritance

In model breeding, inheritance is not a mystical transfer of essence. It is the preservation of traceable properties from parent artifacts to descendant artifacts. Those properties may include base architecture, tokenizer, adapters, training data lineage, evaluation history, safety restrictions, runtime requirements, and known failure modes.

Inheritance channels

ChannelInherited propertyExample
Parameter lineageweights, adapters, quantization statea LoRA descendant from a shared base
Data lineageexamples, teacher outputs, labels, filtersa distilled specialist from a larger teacher
Contract lineageinput and output schemasa replacement summarizer that preserves JSON output
Evaluation lineagebenchmark suites and thresholdsa candidate compared against the same release gate
Operational lineageowners, rollback, deployment tiera canary descendant with the same rollback target

Variation operators

Variation should be declared before execution. This makes the candidate reproducible and keeps selection honest.

pseudocode
RECORD VariationOperator
    name
    operator_version
    allowed_parent_types
    allowed_parameter_budget
    allowed_data_sources
    sandbox_profile
    expected_outputs
    risk_tier
END RECORD

Parentage depth

A descendant can have one parent, multiple parents, or a non-model seed origin. The more parents it has, the more provenance and compatibility checks it needs. Multi-parent merging and adapter fusion can be valuable, but they also increase the chance of license conflicts, tokenizer mismatch, and destructive interference.

Trait records

Borrow the biological word trait only when it maps to a measurable property. A trait can be latency class, calibration quality, reasoning style, language coverage, refusal behavior, memory footprint, or tool-use permission. Each trait should have evidence.

pseudocode
RECORD DescendantTrait
    trait_name
    measured_value
    measurement_suite
    measured_at_utc
    confidence
    inherited_from_parent_id OPTIONAL
    changed_by_operator_id OPTIONAL
END RECORD

Why rejected descendants matter

Rejected candidates teach the ecology where the search failed. Record why they failed: hard gate, insufficient gain, excessive cost, evaluator regression, unsafe behavior, compatibility failure, or duplicate niche. Rejected lineage records prevent repeated expensive mistakes.

Source reports used for this guide

These reports are preserved verbatim in the site archive. The guide above is an editorial synthesis and may narrow, qualify, or reorganize claims from the source material.