Repository files navigation

arXivHuggingFaceGitHubLicensePython

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Causal Discovery Foundation Model (CDFM) is a pretrained foundation model for zero-shot causal discovery. Given purely observational data X (N, D), it predicts the causal graph G (D, D) in a single forward pass.

CDFM reframes causal discovery as a unified, general-purpose framework for zero-shot structural inference. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries.

CDFM benchmark overview

  • State-of-the-art accuracy. Outperforms all baselines across 15 mechanism families and on real-world benchmarks.
  • Zero-shot. One pretrained checkpoint works for any N, any D.
  • Easy to use. pip-installable, single model.predict(data) call.

Installation

pip install cdfm-base

Requirements: torch>=2.0, numpy>=1.20, safetensors, networkx, huggingface_hub.


Usage

1. Causal Discovery

The simplest way to use CDFM is to load the model and pass your observational data directly. By default, CDFM automatically calibrates the threshold for edge prediction.

fromcdfmimportCDFMfromcdfm.utilsimportevaluate_graph, edge_aurocimportnumpyasnp# Load from HuggingFace Hubmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load a simple 4-variable nonlinear example (RFF mechanisms)data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
gt=np.loadtxt("tests/data/simple/adjacency.csv", delimiter=",").astype(np.int32)
# 1. Standard Prediction (Auto-calibrated threshold)result=model.predict(data) # 2. Manual Threshold Controlresult_manual=model.predict(data, threshold=0.5)
print(result.adjacency) # (D, D) binary causal graphmetrics=evaluate_graph(result.adjacency, gt)
auc=edge_auroc(result.logits, gt)
print(f"F1={metrics['f1']:.4f} SHD={metrics['shd']} AUC={auc:.4f}")
# → F1=1.0000 SHD=0 AUC=1.0000

2. Missing value imputation

CDFM has a built-in imputation head trained with quantile loss. Call model.imputation(data) to fill missing values automatically:

fromcdfmimportCDFMimportnumpyasnpmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load data and create missing values (seed for reproducibility)rng=np.random.default_rng(42)
data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
data_with_nan=data.copy()
data_with_nan[rng.random(data.shape) <0.2] =np.nan# CDFM imputation — auto-detects NaNimputed=model.imputation(data_with_nan)
# Compare with mean imputationmean_imp=data_with_nan.copy()
forjinrange(data.shape[1]):
col=data_with_nan[~np.isnan(data_with_nan[:, j]), j]
mean_imp[np.isnan(mean_imp[:, j]), j] =col.mean()
missing=np.isnan(data_with_nan)
mae_cdfm=np.abs(imputed[missing] -data[missing]).mean()
mae_mean=np.abs(mean_imp[missing] -data[missing]).mean()
print(f"CDFM MAE: {mae_cdfm:.4f} | Mean MAE: {mae_mean:.4f}")
# → CDFM MAE: 0.3719 | Mean MAE: 0.7817

API Reference

CDFM Class

classCDFM:
@classmethoddeffrom_pretrained(
cls,
pretrained_model_name_or_path: str="DMIRLAB/CDFM", # HF Hub or local pathdevice: str="auto", # auto / cpu / cuda:Nthreshold: float|None=None, # None = auto-calibrate
) ->"CDFM"defpredict(
self,
data: np.ndarray, # (N, D) float32threshold: float|None=None, # Probability thresholdstandardize: bool=True, # Apply z-score standardizationmissing_mask: np.ndarray|None=None, ) ->CDFMResult

CDFMResult Object

@dataclassclassCDFMResult:
logits: np.ndarray# (D, D) raw edge scoresprobabilities: np.ndarray# (D, D) sigmoid(logits)adjacency: np.ndarray|None# (D, D) binary graphthreshold: float|None# Threshold value usedruntime_sec: float# Wall-clock time

Links

License

This project is licensed under Apache 2.0.

Citation

If you use CDFM in your research, please cite:

@article{qiao2026cdfm,
title = {{CDFM}: Towards a General-Purpose Causal Discovery Foundation Model},
author = {Jie Qiao and Ruichu Cai and Zijian Li and Weilin Chen and Pengfei Hua and Boyan Xu and Zhengming Chen and Zhifeng Hao and Peng Cui},
journal = {arXiv preprint arXiv:2607.11508},
year = {2026},
}

About

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Resources

Stars

57 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
Skip to content

Repository files navigation

arXivHuggingFaceGitHubLicensePython

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Causal Discovery Foundation Model (CDFM) is a pretrained foundation model for zero-shot causal discovery. Given purely observational data X (N, D), it predicts the causal graph G (D, D) in a single forward pass.

CDFM reframes causal discovery as a unified, general-purpose framework for zero-shot structural inference. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries.

CDFM benchmark overview

  • State-of-the-art accuracy. Outperforms all baselines across 15 mechanism families and on real-world benchmarks.
  • Zero-shot. One pretrained checkpoint works for any N, any D.
  • Easy to use. pip-installable, single model.predict(data) call.

Installation

pip install cdfm-base

Requirements: torch>=2.0, numpy>=1.20, safetensors, networkx, huggingface_hub.


Usage

1. Causal Discovery

The simplest way to use CDFM is to load the model and pass your observational data directly. By default, CDFM automatically calibrates the threshold for edge prediction.

fromcdfmimportCDFMfromcdfm.utilsimportevaluate_graph, edge_aurocimportnumpyasnp# Load from HuggingFace Hubmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load a simple 4-variable nonlinear example (RFF mechanisms)data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
gt=np.loadtxt("tests/data/simple/adjacency.csv", delimiter=",").astype(np.int32)
# 1. Standard Prediction (Auto-calibrated threshold)result=model.predict(data) # 2. Manual Threshold Controlresult_manual=model.predict(data, threshold=0.5)
print(result.adjacency) # (D, D) binary causal graphmetrics=evaluate_graph(result.adjacency, gt)
auc=edge_auroc(result.logits, gt)
print(f"F1={metrics['f1']:.4f} SHD={metrics['shd']} AUC={auc:.4f}")
# → F1=1.0000 SHD=0 AUC=1.0000

2. Missing value imputation

CDFM has a built-in imputation head trained with quantile loss. Call model.imputation(data) to fill missing values automatically:

fromcdfmimportCDFMimportnumpyasnpmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load data and create missing values (seed for reproducibility)rng=np.random.default_rng(42)
data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
data_with_nan=data.copy()
data_with_nan[rng.random(data.shape) <0.2] =np.nan# CDFM imputation — auto-detects NaNimputed=model.imputation(data_with_nan)
# Compare with mean imputationmean_imp=data_with_nan.copy()
forjinrange(data.shape[1]):
col=data_with_nan[~np.isnan(data_with_nan[:, j]), j]
mean_imp[np.isnan(mean_imp[:, j]), j] =col.mean()
missing=np.isnan(data_with_nan)
mae_cdfm=np.abs(imputed[missing] -data[missing]).mean()
mae_mean=np.abs(mean_imp[missing] -data[missing]).mean()
print(f"CDFM MAE: {mae_cdfm:.4f} | Mean MAE: {mae_mean:.4f}")
# → CDFM MAE: 0.3719 | Mean MAE: 0.7817

API Reference

CDFM Class

classCDFM:
@classmethoddeffrom_pretrained(
cls,
pretrained_model_name_or_path: str="DMIRLAB/CDFM", # HF Hub or local pathdevice: str="auto", # auto / cpu / cuda:Nthreshold: float|None=None, # None = auto-calibrate
) ->"CDFM"defpredict(
self,
data: np.ndarray, # (N, D) float32threshold: float|None=None, # Probability thresholdstandardize: bool=True, # Apply z-score standardizationmissing_mask: np.ndarray|None=None, ) ->CDFMResult

CDFMResult Object

@dataclassclassCDFMResult:
logits: np.ndarray# (D, D) raw edge scoresprobabilities: np.ndarray# (D, D) sigmoid(logits)adjacency: np.ndarray|None# (D, D) binary graphthreshold: float|None# Threshold value usedruntime_sec: float# Wall-clock time

Links

License

This project is licensed under Apache 2.0.

Citation

If you use CDFM in your research, please cite:

@article{qiao2026cdfm,
title = {{CDFM}: Towards a General-Purpose Causal Discovery Foundation Model},
author = {Jie Qiao and Ruichu Cai and Zijian Li and Weilin Chen and Pengfei Hua and Boyan Xu and Zhengming Chen and Zhifeng Hao and Peng Cui},
journal = {arXiv preprint arXiv:2607.11508},
year = {2026},
}

About

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Resources

Stars

57 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix"); } } catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content

Repository files navigation

arXivHuggingFaceGitHubLicensePython

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Causal Discovery Foundation Model (CDFM) is a pretrained foundation model for zero-shot causal discovery. Given purely observational data X (N, D), it predicts the causal graph G (D, D) in a single forward pass.

CDFM reframes causal discovery as a unified, general-purpose framework for zero-shot structural inference. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries.

CDFM benchmark overview

  • State-of-the-art accuracy. Outperforms all baselines across 15 mechanism families and on real-world benchmarks.
  • Zero-shot. One pretrained checkpoint works for any N, any D.
  • Easy to use. pip-installable, single model.predict(data) call.

Installation

pip install cdfm-base

Requirements: torch>=2.0, numpy>=1.20, safetensors, networkx, huggingface_hub.


Usage

1. Causal Discovery

The simplest way to use CDFM is to load the model and pass your observational data directly. By default, CDFM automatically calibrates the threshold for edge prediction.

fromcdfmimportCDFMfromcdfm.utilsimportevaluate_graph, edge_aurocimportnumpyasnp# Load from HuggingFace Hubmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load a simple 4-variable nonlinear example (RFF mechanisms)data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
gt=np.loadtxt("tests/data/simple/adjacency.csv", delimiter=",").astype(np.int32)
# 1. Standard Prediction (Auto-calibrated threshold)result=model.predict(data) # 2. Manual Threshold Controlresult_manual=model.predict(data, threshold=0.5)
print(result.adjacency) # (D, D) binary causal graphmetrics=evaluate_graph(result.adjacency, gt)
auc=edge_auroc(result.logits, gt)
print(f"F1={metrics['f1']:.4f} SHD={metrics['shd']} AUC={auc:.4f}")
# → F1=1.0000 SHD=0 AUC=1.0000

2. Missing value imputation

CDFM has a built-in imputation head trained with quantile loss. Call model.imputation(data) to fill missing values automatically:

fromcdfmimportCDFMimportnumpyasnpmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load data and create missing values (seed for reproducibility)rng=np.random.default_rng(42)
data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
data_with_nan=data.copy()
data_with_nan[rng.random(data.shape) <0.2] =np.nan# CDFM imputation — auto-detects NaNimputed=model.imputation(data_with_nan)
# Compare with mean imputationmean_imp=data_with_nan.copy()
forjinrange(data.shape[1]):
col=data_with_nan[~np.isnan(data_with_nan[:, j]), j]
mean_imp[np.isnan(mean_imp[:, j]), j] =col.mean()
missing=np.isnan(data_with_nan)
mae_cdfm=np.abs(imputed[missing] -data[missing]).mean()
mae_mean=np.abs(mean_imp[missing] -data[missing]).mean()
print(f"CDFM MAE: {mae_cdfm:.4f} | Mean MAE: {mae_mean:.4f}")
# → CDFM MAE: 0.3719 | Mean MAE: 0.7817

API Reference

CDFM Class

classCDFM:
@classmethoddeffrom_pretrained(
cls,
pretrained_model_name_or_path: str="DMIRLAB/CDFM", # HF Hub or local pathdevice: str="auto", # auto / cpu / cuda:Nthreshold: float|None=None, # None = auto-calibrate
) ->"CDFM"defpredict(
self,
data: np.ndarray, # (N, D) float32threshold: float|None=None, # Probability thresholdstandardize: bool=True, # Apply z-score standardizationmissing_mask: np.ndarray|None=None, ) ->CDFMResult

CDFMResult Object

@dataclassclassCDFMResult:
logits: np.ndarray# (D, D) raw edge scoresprobabilities: np.ndarray# (D, D) sigmoid(logits)adjacency: np.ndarray|None# (D, D) binary graphthreshold: float|None# Threshold value usedruntime_sec: float# Wall-clock time

Links

License

This project is licensed under Apache 2.0.

Citation

If you use CDFM in your research, please cite:

@article{qiao2026cdfm,
title = {{CDFM}: Towards a General-Purpose Causal Discovery Foundation Model},
author = {Jie Qiao and Ruichu Cai and Zijian Li and Weilin Chen and Pengfei Hua and Boyan Xu and Zhengming Chen and Zhifeng Hao and Peng Cui},
journal = {arXiv preprint arXiv:2607.11508},
year = {2026},
}

About

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Resources

Stars

57 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms"); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content

Repository files navigation

arXivHuggingFaceGitHubLicensePython

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Causal Discovery Foundation Model (CDFM) is a pretrained foundation model for zero-shot causal discovery. Given purely observational data X (N, D), it predicts the causal graph G (D, D) in a single forward pass.

CDFM reframes causal discovery as a unified, general-purpose framework for zero-shot structural inference. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries.

CDFM benchmark overview

  • State-of-the-art accuracy. Outperforms all baselines across 15 mechanism families and on real-world benchmarks.
  • Zero-shot. One pretrained checkpoint works for any N, any D.
  • Easy to use. pip-installable, single model.predict(data) call.

Installation

pip install cdfm-base

Requirements: torch>=2.0, numpy>=1.20, safetensors, networkx, huggingface_hub.


Usage

1. Causal Discovery

The simplest way to use CDFM is to load the model and pass your observational data directly. By default, CDFM automatically calibrates the threshold for edge prediction.

fromcdfmimportCDFMfromcdfm.utilsimportevaluate_graph, edge_aurocimportnumpyasnp# Load from HuggingFace Hubmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load a simple 4-variable nonlinear example (RFF mechanisms)data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
gt=np.loadtxt("tests/data/simple/adjacency.csv", delimiter=",").astype(np.int32)
# 1. Standard Prediction (Auto-calibrated threshold)result=model.predict(data) # 2. Manual Threshold Controlresult_manual=model.predict(data, threshold=0.5)
print(result.adjacency) # (D, D) binary causal graphmetrics=evaluate_graph(result.adjacency, gt)
auc=edge_auroc(result.logits, gt)
print(f"F1={metrics['f1']:.4f} SHD={metrics['shd']} AUC={auc:.4f}")
# → F1=1.0000 SHD=0 AUC=1.0000

2. Missing value imputation

CDFM has a built-in imputation head trained with quantile loss. Call model.imputation(data) to fill missing values automatically:

fromcdfmimportCDFMimportnumpyasnpmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load data and create missing values (seed for reproducibility)rng=np.random.default_rng(42)
data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
data_with_nan=data.copy()
data_with_nan[rng.random(data.shape) <0.2] =np.nan# CDFM imputation — auto-detects NaNimputed=model.imputation(data_with_nan)
# Compare with mean imputationmean_imp=data_with_nan.copy()
forjinrange(data.shape[1]):
col=data_with_nan[~np.isnan(data_with_nan[:, j]), j]
mean_imp[np.isnan(mean_imp[:, j]), j] =col.mean()
missing=np.isnan(data_with_nan)
mae_cdfm=np.abs(imputed[missing] -data[missing]).mean()
mae_mean=np.abs(mean_imp[missing] -data[missing]).mean()
print(f"CDFM MAE: {mae_cdfm:.4f} | Mean MAE: {mae_mean:.4f}")
# → CDFM MAE: 0.3719 | Mean MAE: 0.7817

API Reference

CDFM Class

classCDFM:
@classmethoddeffrom_pretrained(
cls,
pretrained_model_name_or_path: str="DMIRLAB/CDFM", # HF Hub or local pathdevice: str="auto", # auto / cpu / cuda:Nthreshold: float|None=None, # None = auto-calibrate
) ->"CDFM"defpredict(
self,
data: np.ndarray, # (N, D) float32threshold: float|None=None, # Probability thresholdstandardize: bool=True, # Apply z-score standardizationmissing_mask: np.ndarray|None=None, ) ->CDFMResult

CDFMResult Object

@dataclassclassCDFMResult:
logits: np.ndarray# (D, D) raw edge scoresprobabilities: np.ndarray# (D, D) sigmoid(logits)adjacency: np.ndarray|None# (D, D) binary graphthreshold: float|None# Threshold value usedruntime_sec: float# Wall-clock time

Links

License

This project is licensed under Apache 2.0.

Citation

If you use CDFM in your research, please cite:

@article{qiao2026cdfm,
title = {{CDFM}: Towards a General-Purpose Causal Discovery Foundation Model},
author = {Jie Qiao and Ruichu Cai and Zijian Li and Weilin Chen and Pengfei Hua and Boyan Xu and Zhengming Chen and Zhifeng Hao and Peng Cui},
journal = {arXiv preprint arXiv:2607.11508},
year = {2026},
}

About

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Resources

Stars

57 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links"); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + '
Skip to content

Repository files navigation

arXivHuggingFaceGitHubLicensePython

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Causal Discovery Foundation Model (CDFM) is a pretrained foundation model for zero-shot causal discovery. Given purely observational data X (N, D), it predicts the causal graph G (D, D) in a single forward pass.

CDFM reframes causal discovery as a unified, general-purpose framework for zero-shot structural inference. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries.

CDFM benchmark overview

  • State-of-the-art accuracy. Outperforms all baselines across 15 mechanism families and on real-world benchmarks.
  • Zero-shot. One pretrained checkpoint works for any N, any D.
  • Easy to use. pip-installable, single model.predict(data) call.

Installation

pip install cdfm-base

Requirements: torch>=2.0, numpy>=1.20, safetensors, networkx, huggingface_hub.


Usage

1. Causal Discovery

The simplest way to use CDFM is to load the model and pass your observational data directly. By default, CDFM automatically calibrates the threshold for edge prediction.

fromcdfmimportCDFMfromcdfm.utilsimportevaluate_graph, edge_aurocimportnumpyasnp# Load from HuggingFace Hubmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load a simple 4-variable nonlinear example (RFF mechanisms)data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
gt=np.loadtxt("tests/data/simple/adjacency.csv", delimiter=",").astype(np.int32)
# 1. Standard Prediction (Auto-calibrated threshold)result=model.predict(data) # 2. Manual Threshold Controlresult_manual=model.predict(data, threshold=0.5)
print(result.adjacency) # (D, D) binary causal graphmetrics=evaluate_graph(result.adjacency, gt)
auc=edge_auroc(result.logits, gt)
print(f"F1={metrics['f1']:.4f} SHD={metrics['shd']} AUC={auc:.4f}")
# → F1=1.0000 SHD=0 AUC=1.0000

2. Missing value imputation

CDFM has a built-in imputation head trained with quantile loss. Call model.imputation(data) to fill missing values automatically:

fromcdfmimportCDFMimportnumpyasnpmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load data and create missing values (seed for reproducibility)rng=np.random.default_rng(42)
data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
data_with_nan=data.copy()
data_with_nan[rng.random(data.shape) <0.2] =np.nan# CDFM imputation — auto-detects NaNimputed=model.imputation(data_with_nan)
# Compare with mean imputationmean_imp=data_with_nan.copy()
forjinrange(data.shape[1]):
col=data_with_nan[~np.isnan(data_with_nan[:, j]), j]
mean_imp[np.isnan(mean_imp[:, j]), j] =col.mean()
missing=np.isnan(data_with_nan)
mae_cdfm=np.abs(imputed[missing] -data[missing]).mean()
mae_mean=np.abs(mean_imp[missing] -data[missing]).mean()
print(f"CDFM MAE: {mae_cdfm:.4f} | Mean MAE: {mae_mean:.4f}")
# → CDFM MAE: 0.3719 | Mean MAE: 0.7817

API Reference

CDFM Class

classCDFM:
@classmethoddeffrom_pretrained(
cls,
pretrained_model_name_or_path: str="DMIRLAB/CDFM", # HF Hub or local pathdevice: str="auto", # auto / cpu / cuda:Nthreshold: float|None=None, # None = auto-calibrate
) ->"CDFM"defpredict(
self,
data: np.ndarray, # (N, D) float32threshold: float|None=None, # Probability thresholdstandardize: bool=True, # Apply z-score standardizationmissing_mask: np.ndarray|None=None, ) ->CDFMResult

CDFMResult Object

@dataclassclassCDFMResult:
logits: np.ndarray# (D, D) raw edge scoresprobabilities: np.ndarray# (D, D) sigmoid(logits)adjacency: np.ndarray|None# (D, D) binary graphthreshold: float|None# Threshold value usedruntime_sec: float# Wall-clock time

Links

License

This project is licensed under Apache 2.0.

Citation

If you use CDFM in your research, please cite:

@article{qiao2026cdfm,
title = {{CDFM}: Towards a General-Purpose Causal Discovery Foundation Model},
author = {Jie Qiao and Ruichu Cai and Zijian Li and Weilin Chen and Pengfei Hua and Boyan Xu and Zhengming Chen and Zhifeng Hao and Peng Cui},
journal = {arXiv preprint arXiv:2607.11508},
year = {2026},
}

About

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Resources

Stars

57 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default"); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content

Repository files navigation

arXivHuggingFaceGitHubLicensePython

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Causal Discovery Foundation Model (CDFM) is a pretrained foundation model for zero-shot causal discovery. Given purely observational data X (N, D), it predicts the causal graph G (D, D) in a single forward pass.

CDFM reframes causal discovery as a unified, general-purpose framework for zero-shot structural inference. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries.

CDFM benchmark overview

  • State-of-the-art accuracy. Outperforms all baselines across 15 mechanism families and on real-world benchmarks.
  • Zero-shot. One pretrained checkpoint works for any N, any D.
  • Easy to use. pip-installable, single model.predict(data) call.

Installation

pip install cdfm-base

Requirements: torch>=2.0, numpy>=1.20, safetensors, networkx, huggingface_hub.


Usage

1. Causal Discovery

The simplest way to use CDFM is to load the model and pass your observational data directly. By default, CDFM automatically calibrates the threshold for edge prediction.

fromcdfmimportCDFMfromcdfm.utilsimportevaluate_graph, edge_aurocimportnumpyasnp# Load from HuggingFace Hubmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load a simple 4-variable nonlinear example (RFF mechanisms)data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
gt=np.loadtxt("tests/data/simple/adjacency.csv", delimiter=",").astype(np.int32)
# 1. Standard Prediction (Auto-calibrated threshold)result=model.predict(data) # 2. Manual Threshold Controlresult_manual=model.predict(data, threshold=0.5)
print(result.adjacency) # (D, D) binary causal graphmetrics=evaluate_graph(result.adjacency, gt)
auc=edge_auroc(result.logits, gt)
print(f"F1={metrics['f1']:.4f} SHD={metrics['shd']} AUC={auc:.4f}")
# → F1=1.0000 SHD=0 AUC=1.0000

2. Missing value imputation

CDFM has a built-in imputation head trained with quantile loss. Call model.imputation(data) to fill missing values automatically:

fromcdfmimportCDFMimportnumpyasnpmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load data and create missing values (seed for reproducibility)rng=np.random.default_rng(42)
data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
data_with_nan=data.copy()
data_with_nan[rng.random(data.shape) <0.2] =np.nan# CDFM imputation — auto-detects NaNimputed=model.imputation(data_with_nan)
# Compare with mean imputationmean_imp=data_with_nan.copy()
forjinrange(data.shape[1]):
col=data_with_nan[~np.isnan(data_with_nan[:, j]), j]
mean_imp[np.isnan(mean_imp[:, j]), j] =col.mean()
missing=np.isnan(data_with_nan)
mae_cdfm=np.abs(imputed[missing] -data[missing]).mean()
mae_mean=np.abs(mean_imp[missing] -data[missing]).mean()
print(f"CDFM MAE: {mae_cdfm:.4f} | Mean MAE: {mae_mean:.4f}")
# → CDFM MAE: 0.3719 | Mean MAE: 0.7817

API Reference

CDFM Class

classCDFM:
@classmethoddeffrom_pretrained(
cls,
pretrained_model_name_or_path: str="DMIRLAB/CDFM", # HF Hub or local pathdevice: str="auto", # auto / cpu / cuda:Nthreshold: float|None=None, # None = auto-calibrate
) ->"CDFM"defpredict(
self,
data: np.ndarray, # (N, D) float32threshold: float|None=None, # Probability thresholdstandardize: bool=True, # Apply z-score standardizationmissing_mask: np.ndarray|None=None, ) ->CDFMResult

CDFMResult Object

@dataclassclassCDFMResult:
logits: np.ndarray# (D, D) raw edge scoresprobabilities: np.ndarray# (D, D) sigmoid(logits)adjacency: np.ndarray|None# (D, D) binary graphthreshold: float|None# Threshold value usedruntime_sec: float# Wall-clock time

Links

License

This project is licensed under Apache 2.0.

Citation

If you use CDFM in your research, please cite:

@article{qiao2026cdfm,
title = {{CDFM}: Towards a General-Purpose Causal Discovery Foundation Model},
author = {Jie Qiao and Ruichu Cai and Zijian Li and Weilin Chen and Pengfei Hua and Boyan Xu and Zhengming Chen and Zhifeng Hao and Peng Cui},
journal = {arXiv preprint arXiv:2607.11508},
year = {2026},
}

About

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Resources

Stars

57 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers"); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content

Repository files navigation

arXivHuggingFaceGitHubLicensePython

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Causal Discovery Foundation Model (CDFM) is a pretrained foundation model for zero-shot causal discovery. Given purely observational data X (N, D), it predicts the causal graph G (D, D) in a single forward pass.

CDFM reframes causal discovery as a unified, general-purpose framework for zero-shot structural inference. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries.

CDFM benchmark overview

  • State-of-the-art accuracy. Outperforms all baselines across 15 mechanism families and on real-world benchmarks.
  • Zero-shot. One pretrained checkpoint works for any N, any D.
  • Easy to use. pip-installable, single model.predict(data) call.

Installation

pip install cdfm-base

Requirements: torch>=2.0, numpy>=1.20, safetensors, networkx, huggingface_hub.


Usage

1. Causal Discovery

The simplest way to use CDFM is to load the model and pass your observational data directly. By default, CDFM automatically calibrates the threshold for edge prediction.

fromcdfmimportCDFMfromcdfm.utilsimportevaluate_graph, edge_aurocimportnumpyasnp# Load from HuggingFace Hubmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load a simple 4-variable nonlinear example (RFF mechanisms)data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
gt=np.loadtxt("tests/data/simple/adjacency.csv", delimiter=",").astype(np.int32)
# 1. Standard Prediction (Auto-calibrated threshold)result=model.predict(data) # 2. Manual Threshold Controlresult_manual=model.predict(data, threshold=0.5)
print(result.adjacency) # (D, D) binary causal graphmetrics=evaluate_graph(result.adjacency, gt)
auc=edge_auroc(result.logits, gt)
print(f"F1={metrics['f1']:.4f} SHD={metrics['shd']} AUC={auc:.4f}")
# → F1=1.0000 SHD=0 AUC=1.0000

2. Missing value imputation

CDFM has a built-in imputation head trained with quantile loss. Call model.imputation(data) to fill missing values automatically:

fromcdfmimportCDFMimportnumpyasnpmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load data and create missing values (seed for reproducibility)rng=np.random.default_rng(42)
data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
data_with_nan=data.copy()
data_with_nan[rng.random(data.shape) <0.2] =np.nan# CDFM imputation — auto-detects NaNimputed=model.imputation(data_with_nan)
# Compare with mean imputationmean_imp=data_with_nan.copy()
forjinrange(data.shape[1]):
col=data_with_nan[~np.isnan(data_with_nan[:, j]), j]
mean_imp[np.isnan(mean_imp[:, j]), j] =col.mean()
missing=np.isnan(data_with_nan)
mae_cdfm=np.abs(imputed[missing] -data[missing]).mean()
mae_mean=np.abs(mean_imp[missing] -data[missing]).mean()
print(f"CDFM MAE: {mae_cdfm:.4f} | Mean MAE: {mae_mean:.4f}")
# → CDFM MAE: 0.3719 | Mean MAE: 0.7817

API Reference

CDFM Class

classCDFM:
@classmethoddeffrom_pretrained(
cls,
pretrained_model_name_or_path: str="DMIRLAB/CDFM", # HF Hub or local pathdevice: str="auto", # auto / cpu / cuda:Nthreshold: float|None=None, # None = auto-calibrate
) ->"CDFM"defpredict(
self,
data: np.ndarray, # (N, D) float32threshold: float|None=None, # Probability thresholdstandardize: bool=True, # Apply z-score standardizationmissing_mask: np.ndarray|None=None, ) ->CDFMResult

CDFMResult Object

@dataclassclassCDFMResult:
logits: np.ndarray# (D, D) raw edge scoresprobabilities: np.ndarray# (D, D) sigmoid(logits)adjacency: np.ndarray|None# (D, D) binary graphthreshold: float|None# Threshold value usedruntime_sec: float# Wall-clock time

Links

License

This project is licensed under Apache 2.0.

Citation

If you use CDFM in your research, please cite:

@article{qiao2026cdfm,
title = {{CDFM}: Towards a General-Purpose Causal Discovery Foundation Model},
author = {Jie Qiao and Ruichu Cai and Zijian Li and Weilin Chen and Pengfei Hua and Boyan Xu and Zhengming Chen and Zhifeng Hao and Peng Cui},
journal = {arXiv preprint arXiv:2607.11508},
year = {2026},
}

About

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Resources

Stars

57 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode"); } } catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); } })(); })();
Skip to content

Repository files navigation

arXivHuggingFaceGitHubLicensePython

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Causal Discovery Foundation Model (CDFM) is a pretrained foundation model for zero-shot causal discovery. Given purely observational data X (N, D), it predicts the causal graph G (D, D) in a single forward pass.

CDFM reframes causal discovery as a unified, general-purpose framework for zero-shot structural inference. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries.

CDFM benchmark overview

  • State-of-the-art accuracy. Outperforms all baselines across 15 mechanism families and on real-world benchmarks.
  • Zero-shot. One pretrained checkpoint works for any N, any D.
  • Easy to use. pip-installable, single model.predict(data) call.

Installation

pip install cdfm-base

Requirements: torch>=2.0, numpy>=1.20, safetensors, networkx, huggingface_hub.


Usage

1. Causal Discovery

The simplest way to use CDFM is to load the model and pass your observational data directly. By default, CDFM automatically calibrates the threshold for edge prediction.

fromcdfmimportCDFMfromcdfm.utilsimportevaluate_graph, edge_aurocimportnumpyasnp# Load from HuggingFace Hubmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load a simple 4-variable nonlinear example (RFF mechanisms)data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
gt=np.loadtxt("tests/data/simple/adjacency.csv", delimiter=",").astype(np.int32)
# 1. Standard Prediction (Auto-calibrated threshold)result=model.predict(data) # 2. Manual Threshold Controlresult_manual=model.predict(data, threshold=0.5)
print(result.adjacency) # (D, D) binary causal graphmetrics=evaluate_graph(result.adjacency, gt)
auc=edge_auroc(result.logits, gt)
print(f"F1={metrics['f1']:.4f} SHD={metrics['shd']} AUC={auc:.4f}")
# → F1=1.0000 SHD=0 AUC=1.0000

2. Missing value imputation

CDFM has a built-in imputation head trained with quantile loss. Call model.imputation(data) to fill missing values automatically:

fromcdfmimportCDFMimportnumpyasnpmodel=CDFM.from_pretrained("DMIRLAB/CDFM")
# Load data and create missing values (seed for reproducibility)rng=np.random.default_rng(42)
data=np.loadtxt("tests/data/simple/data.csv", delimiter=",")
data_with_nan=data.copy()
data_with_nan[rng.random(data.shape) <0.2] =np.nan# CDFM imputation — auto-detects NaNimputed=model.imputation(data_with_nan)
# Compare with mean imputationmean_imp=data_with_nan.copy()
forjinrange(data.shape[1]):
col=data_with_nan[~np.isnan(data_with_nan[:, j]), j]
mean_imp[np.isnan(mean_imp[:, j]), j] =col.mean()
missing=np.isnan(data_with_nan)
mae_cdfm=np.abs(imputed[missing] -data[missing]).mean()
mae_mean=np.abs(mean_imp[missing] -data[missing]).mean()
print(f"CDFM MAE: {mae_cdfm:.4f} | Mean MAE: {mae_mean:.4f}")
# → CDFM MAE: 0.3719 | Mean MAE: 0.7817

API Reference

CDFM Class

classCDFM:
@classmethoddeffrom_pretrained(
cls,
pretrained_model_name_or_path: str="DMIRLAB/CDFM", # HF Hub or local pathdevice: str="auto", # auto / cpu / cuda:Nthreshold: float|None=None, # None = auto-calibrate
) ->"CDFM"defpredict(
self,
data: np.ndarray, # (N, D) float32threshold: float|None=None, # Probability thresholdstandardize: bool=True, # Apply z-score standardizationmissing_mask: np.ndarray|None=None, ) ->CDFMResult

CDFMResult Object

@dataclassclassCDFMResult:
logits: np.ndarray# (D, D) raw edge scoresprobabilities: np.ndarray# (D, D) sigmoid(logits)adjacency: np.ndarray|None# (D, D) binary graphthreshold: float|None# Threshold value usedruntime_sec: float# Wall-clock time

Links

License

This project is licensed under Apache 2.0.

Citation

If you use CDFM in your research, please cite:

@article{qiao2026cdfm,
title = {{CDFM}: Towards a General-Purpose Causal Discovery Foundation Model},
author = {Jie Qiao and Ruichu Cai and Zijian Li and Weilin Chen and Pengfei Hua and Boyan Xu and Zhengming Chen and Zhifeng Hao and Peng Cui},
journal = {arXiv preprint arXiv:2607.11508},
year = {2026},
}

About

CDFM: Towards a General-Purpose Causal Discovery Foundation Model

Resources

Stars

57 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages