Product depth across all three surfaces (PRODUCT.md captures the vision): CLI — new lawsynth-report crate (self-contained HTML reports with inline SVG trajectory + phase-portrait charts) and five product commands: report, explain (plain-language laws), compare (world diff), forecast (what-if interventions), library (local world index). Demonstrated end-to-end on a damped oscillator. SDK — high-level Study workflow (from_csv -> discover -> explain -> simulate/ forecast -> report -> save/load), stdlib HTML report generator, and notebook rich _repr_html_ display. Quickstart example recovers the oscillator exactly (R2=1.0) and writes a 30KB report. Studio — 5 interactive screens (discovery canvas, equation explorer, regime timeline, uncertainty lens, world lab) composing the shared TS packages through a reactive state-store; typecheck-clean. Also: benchmark execution deepened 9 -> 18 real cases (causal + regime families now scored against ground truth); cross-service integration tests (gateway-> artifact proxy, scheduler<->worker lifecycle over real sockets). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
causal/interventional executed family case
This benchmark generates a deterministic causal dataset and runs the real
LawSynth discover --causal pipeline through the compiled CLI. The CLI emits a
dependency_edges signal (dependency-hypothesis edges), which is scored against a ground-truth-derived
minimum declared in benchmark.toml's [expect] table.
Run python3 run.py to execute and score the case, python3 score.py for
the same scored result, and python3 generate.py to write the reproducible
observation CSV. The signal is a real (partial) structural measurement from the
engine, never a fabricated identification, segmentation, or coverage number.