causal-treatment-models skillA
causal-treatment-models is agent-read markdown (skill) from cuhk-aim-group/neurodiscovery: Use this skill whenever the scientific target is a treatment effect rather than ordinary outcome prediction: propensity weighting, S/T/X learners, doubly robust learning, policy learning, causal forests, TARNet, DragonNet, CATE estimation, heterogeneous treatment effects, and individualized treatment selection. Triggers include 'causal inference', 'treatment effect', 'CATE', 'ATE', 'propensity score', 'IPW', 'doubly robust', 'causal forest', 'TARNet', 'DragonNet', and 'treatment policy'..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Causal Treatment Models Skill ## Overview `causal-treatment-models` estimates average or conditional treatment effects from observational subject-level features. It is for the contrast `Y(1) - Y(0)`, not for predicting the observed outcome alone. **Supported estimators** | Model | Output | |---|---| | `ipw` | propensity-weighted ATE as constant CATE | | `s_learner` | single outcome model treatment contrast | | `t_learner` | separate treated/control outcome models | | `x_learner` | imputed effects blended by propensity | | `doubly_robust` | doubly robust pseudo-outcome CATE | | `policy_learner` | interpretable treatment assignment policy | | `causal_forest` | `econml` CausalForestDML | | `tarnet` | shared representation with two outcome heads | | `dragonnet` | TARNet plus propensity head | The CLI uses cross-fitted held-out predictions. Causal interpretation still requires consistency, positivity, no unmeasured confounding, and a defensible temporal ordering. --- ## Installation ```bash pip install numpy pandas scipy scikit-learn joblib torch ``` For Causal Forest: ```bash pip install econml ``` --- ## Workflows ### 1. Prepare treatment data ```text …
Read the whole file at its exact version.
How to install
mdr add cuhk-aim-group/neurodiscovery/causal-treatment-models@git:20260825.cbd02ffmdr add cuhk-aim-group/neurodiscovery/causal-treatment-models@sha256:b2292cd81f3a35d5Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_pzb4iy35v4yc7fmz)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4362 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
cuhk-aim-group/neurodiscovery · 91 stars · license MIT · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pzb4iy35v4yc7fmz GET https://markdownregistry.com/api/v1/resolve?ref=cuhk-aim-group/neurodiscovery/causal-treatment-models GET https://markdownregistry.com/api/v1/blob/b2292cd81f3a35d55ee9e552cd6c0d7a1554077572257523865831aa3e4bcd2b
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.