Wave 10 — rigor & sharing: CLI — lawsynth backtest (rolling-origin/walk-forward: N origins x horizon, per-state RMSE/MAE/R2 + skill-vs-horizon decay + verdict, --html report); lawsynth workspace export/import (portable .lsworkspace archive: world bytes + provenance + runs, per-entry SHA-256 integrity, non-destructive import). SDK — Study.backtest -> Backtest (skill-vs-horizon decay, deterministic); lawsynth.Project workspace persisting in the CLI library.tsv format (verified bidirectional CLI<->SDK interop) with export/import archives. Docs — a real cookbook (10 task recipes, CLI + SDK each) + 3 end-to-end tutorials, verified against the shipped source (two-intervention-semantics and preset-vs-recipe differences called out). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
20 lines
1014 B
Markdown
20 lines
1014 B
Markdown
# Tutorials
|
||
|
||
Longer, narrative walkthroughs that chain many LawSynth features into one story.
|
||
Each is runnable end to end and deterministic/offline. For short, single-task
|
||
recipes, see the [cookbook](../cookbook/README.md).
|
||
|
||
1. [From a messy sensor CSV to a trusted, shareable model](messy-sensor-to-trusted-model.md)
|
||
— profile → prep → discover → explain → validate → backtest → ensemble →
|
||
report → export → register.
|
||
2. [A predator–prey ecology walkthrough](predator-prey-ecology.md)
|
||
— generate data, discover with the ecology recipe, read the laws, run
|
||
what-ifs and scenario boards, and export.
|
||
3. [Monitoring a running system](monitoring-a-running-system.md)
|
||
— discover a model of "normal", score fresh batches for drift, and decide.
|
||
|
||
Prerequisites: a built `lawsynth` CLI and the `lawsynth` Python SDK (see
|
||
[installation](../getting-started/installation.md)); optionally the
|
||
`lawsynth-notebook` package for interactive views. Verify your setup with
|
||
`lawsynth doctor`.
|