Causal Discovery on CausalMan Medium
27.4F1 ScoreCAST
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| CASTLLM Backbone=Qw.3 14B, HITL=true, RAG=true2026.07 | 27.4 | 65.6 | 558 | |
| CASTLLM Backbone=Qw.3 14B, HITL=true, RAG=false2026.07 | 26.6 | 50.8 | 610.8 | |
| CASTLLM Backbone=Qw.3 14B, HITL=false, RAG=true2026.07 | 21.1 | 48.5 | 568.4 | |
| CausalStewardLLM Backbone=o3-mini, HITL=false, RAG=true2026.07 | 20.9 | 51.8 | 571.6 | |
| CausalStewardLLM Backbone=o3-mini, HITL=true, RAG=false2026.07 | 17.5 | 49.9 | 558.8 | |
| CausalStewardLLM Backbone=o3-mini, HITL=true, RAG=true2026.07 | 14.1 | 35.7 | 579.6 | |
| CASTLLM Backbone=o4-mini, HITL=false, RAG=true2026.07 | 11.3 | 29.6 | 594.2 | |
| CASTLLM Backbone=o4-mini, HITL=true, RAG=false2026.07 | 10.3 | 39.2 | 547 | |
| CASTLLM Backbone=o4-mini, HITL=true, RAG=true2026.07 | 8.6 | 27.1 | 568.2 | |
| BOSS2026.07 | 5.7 | 3 | 1,817.4 | |
| XGES2026.07 | 1.4 | 21.1 | 547 | |
| CausalCopilot2026.07 | 1.4 | 21.1 | 547 | |
| GranDAG2026.07 | 0 | 0 | 544.4 |