# LASKO skill optimization

- **Registry ID:** `lincs-lasko-family`
- **Book:** Machine Learning from Enforcing Compositionality
- **Documentation status:** `public-code-linked`
- **Experimental status:** controlled workflow studies
- **Canonical documentation URL:** https://categorical-ai.sridharmahadevan.com/experiments/lincs-lasko-family

## Purpose

Cheap bracket probes, validation calls, scale experiments, and anchor-chain benchmarks.

## Book location

- Chapter 14: Skills over Lie Algebroids

## Documented studies

- Cheap Lie-bracket probe calibration
- Validation-call economy study
- Skill-library scale experiment
- Anchor-chain benchmark

## Associated code packages

- `lincs-lasko` — [LINCS LASKO package](https://github.com/sridharmahadevan/LINCS/tree/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/lasko); **public**; Apache-2.0. Lie-algebroid skill optimization and validation-economics experiments.

## Start here

These concrete files are selected from the complete resolved source surface. They orient the reader; they are not a claim that every family is independently reproducible.

- **runner · public-pinned** — [`lincs-lasko:scripts/run_anchor_chain_benchmark.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/lasko/scripts/run_anchor_chain_benchmark.py). Open the pinned public source file.
- **runner · public-pinned** — [`lincs-lasko:scripts/run_anchor_chain_scale.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/lasko/scripts/run_anchor_chain_scale.py). Open the pinned public source file.
- **runner · public-pinned** — [`lincs-lasko:scripts/analyze_skillopt_run.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/lasko/scripts/analyze_skillopt_run.py). Open the pinned public source file.

## Entry points

- `scripts/run_anchor_chain_benchmark.py`

## Result artifacts

- `benchmark summaries and workflow traces`

## Resolved code surfaces (3)

- **runner** — [`lincs-lasko:scripts/analyze_skillopt_run.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/lasko/scripts/analyze_skillopt_run.py)
- **runner** — [`lincs-lasko:scripts/run_anchor_chain_benchmark.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/lasko/scripts/run_anchor_chain_benchmark.py)
- **runner** — [`lincs-lasko:scripts/run_anchor_chain_scale.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/lasko/scripts/run_anchor_chain_scale.py)

## Frozen run records (0)

- No frozen run-level record is registered. Consult the result-artifact list and evidence boundary above for the exact surviving evidence; absence of a run record is not evidence that no experiment was run.

## Evidence boundary

Compute savings are relative to the supplied skill language and validation protocol; the system does not invent that language.

A code or artifact link establishes traceability. It does not by itself establish independent reproduction, statistical adequacy, correctness, or support for a claim beyond this boundary.