Durable experiment record · Public core code · curated results

BRIDGE/SKFM geometric causal discovery

Random-DAG, injected-confounding, Sachs, screening, graph extraction, and runtime experiments.

30 code surfaces0 frozen runs1 code packageslincs-bridge-skfm-family

Experimental contract

What this family tests

controlled synthetic and benchmark studies

  • Random-DAG closure calibration
  • Injected latent-confounding recovery
  • Sachs benchmark study
  • Lie-bracket screening and graph extraction
  • Runtime and robustness comparison

Book-to-code crosswalk

The highlighted Experiment cards covered here

Implementation map

From entry point to source surface

Start here

These concrete files are selected from the complete registered source surface to orient the reader.

Author-declared entry points

  • kan_do_dcdi/experiments/

Resolved code

runner · 30

Evidence record

Artifacts and frozen runs

Result artifacts

  • package reports and benchmark summaries

Run records

No run-level packet is registered. The family retains code-level provenance, but public run reproduction still requires curation.

Evidence boundary

Lie-bracket nonclosure is a diagnostic under registered semantics, not unique identification of a latent confounder.

This registry links the experiments reported by the three books to their executable or archived code surfaces. A code link establishes traceability, not independent reproduction, correctness, or support for a claim beyond the experiment's stated boundary.