List your company

Circuit Recovery on ARC-E

1.06CPR Faithfulness ScoreNAP-IG-Inputs
0.21760.43630.6550.8737Apr 27, 2026

Evaluation results

MethodLinks
NAP-IG-InputsMethod Category=NAP-IG-Inputs, Transfer Setting=Gold (Upper Bound)2026.041.06
NAP-IG-ActivationsMethod Category=NAP-IG-Activations, Transfer Setting=Gold (Upper Bound)2026.040.9
NAPMethod Category=NAP, Transfer Setting=Gold (Upper Bound)2026.040.89
NAP-IG-InputsTransfer Setting=DFA (Near-Distribution), Model Pair=Llama-3 (1B -> 3B)2026.040.54
NAP-IG-InputsTransfer Setting=Gold (Upper Bound), Model Pair=Llama-3 (1B -> 3B)2026.040.52
NAP-IG-InputsTransfer Setting=DFA (Far/Zero-Shot), Model Pair=Llama-3 (1B -> 3B)2026.040.47
NAP-IG-InputsTransfer Setting=DFA (In-Distribution), Model Pair=Llama-3 (1B -> 3B)2026.040.41
NAPMethod Category=NAP, Transfer Setting=DFA (Far/Zero-Shot)2026.040.4
NAP-IG-ActivationsMethod Category=NAP-IG-Activations, Transfer Setting=DFA (Far/Zero-Shot)2026.040.35
NAP-IG-InputsMethod Category=NAP-IG-Inputs, Transfer Setting=DFA (Near-Distribution)2026.040.31
NAP-IG-InputsMethod Category=NAP-IG-Inputs, Transfer Setting=DFA (In-Distribution)2026.040.29
NAP-IG-InputsMethod Category=NAP-IG-Inputs, Transfer Setting=DFA (Far/Zero-Shot)2026.040.29
NAPMethod Category=NAP, Transfer Setting=DFA (Near-Distribution)2026.040.29
NAP-IG-ActivationsMethod Category=NAP-IG-Activations, Transfer Setting=DFA (Near-Distribution)2026.040.29
BaselineMethod Category=Baseline, Transfer Setting=Random Alignment2026.040.27
NAPMethod Category=NAP, Transfer Setting=DFA (In-Distribution)2026.040.27
NAP-IG-ActivationsMethod Category=NAP-IG-Activations, Transfer Setting=DFA (In-Distribution)2026.040.27
BaselineTransfer Setting=Random Alignment, Model Pair=Llama-3 (1B -> 3B)2026.040.25