Upload README.md with huggingface_hub

README.md

@@ -32,16 +32,44 @@ A causal reasoning foundation model — predicts effects, judges trustworthiness
 - Curriculum: Phase 1 CATE-only → Phase 2 +Null → Phase 3 Full judgment
 
 ## Usage
+
+### CLI (recommended)
+```bash
+# Full analysis + root cause analysis in one shot
+tcpfn infer sensor_data.csv \
+  --target "temperature_sensor" \
+  --event-time "2025-11-15 14:15" \
+  -o results.json
+
+# Discovery only (no specific event)
+tcpfn analyze sensor_data.csv -o analysis.json
+
+# RCA only (reuse previous analysis)
+tcpfn explain sensor_data.csv \
+  --target "temperature_sensor" \
+  --event-time "2025-11-15 14:15" \
+  --analysis analysis.json
+```
+
+### Python SDK
 ```python
 from tcpfn import TemporalCausalAnalyzer
 
 analyzer = TemporalCausalAnalyzer(
     temporal_model="models/temporal/final.pt",
 )
+
+# Causal discovery + effects
 report = analyzer.run("sensor_data.csv")
 print(report.edges)          # causal graph
-print(report.judgments)      # null prob, regime, identifiability per edge
-print(report.root_causes)   # ranked root causes
+
+# Root cause analysis
+result = analyzer.explain_event(
+    data_path="sensor_data.csv",
+    target_var="temperature_sensor",
+    event_time="2025-11-15 14:15",
+)
+print(result.summary())      # ranked root causes + causal chains
 ```
 
 ## Training Metrics (mean over steps 150K-200K)