diff --git a/image_analysis/bragg_integration/BraggIntegrationEngineCPU.cpp b/image_analysis/bragg_integration/BraggIntegrationEngineCPU.cpp
index c5f6f346..d4371d71 100644
--- a/image_analysis/bragg_integration/BraggIntegrationEngineCPU.cpp
+++ b/image_analysis/bragg_integration/BraggIntegrationEngineCPU.cpp
@@ -345,8 +345,11 @@ std::vector<Reflection> BraggIntegrationEngineCPU::RunImpl(const Sampler &img,
             I = rh.I;
             sigma = rh.sigma;
         }
+        // Carry the Pass-A box-sum intensity-weighted centroid (observed spot position) through the
+        // profile path too - post-refinement uses it as the observed position (beam-centre / distance).
         results[i] = {static_cast<float>(I), static_cast<float>(sigma),
-                      static_cast<float>(rh.bkg), 0.0f, 0.0f, true, false};
+                      static_cast<float>(rh.bkg),
+                      static_cast<float>(rh.obs_x), static_cast<float>(rh.obs_y), true, rh.has_obs};
     }
 
     return Finalize(predicted, npredicted, results, image_number);
diff --git a/image_analysis/bragg_integration/BraggIntegrationEngineGPU.cu b/image_analysis/bragg_integration/BraggIntegrationEngineGPU.cu
index 36a62773..b0a3d6a5 100644
--- a/image_analysis/bragg_integration/BraggIntegrationEngineGPU.cu
+++ b/image_analysis/bragg_integration/BraggIntegrationEngineGPU.cu
@@ -518,12 +518,11 @@ std::vector<Reflection> BraggIntegrationEngineGPU::Run(const ImagePreprocessorBu
     cuda_err(cudaMemcpyAsync(h_sigma.data(), d_sigma, sizeof(float) * npredicted, cudaMemcpyDeviceToHost, *stream));
     cuda_err(cudaMemcpyAsync(h_bkg.data(), d_bkg, sizeof(float) * npredicted, cudaMemcpyDeviceToHost, *stream));
     cuda_err(cudaMemcpyAsync(h_ok.data(), d_ok, sizeof(uint8_t) * npredicted, cudaMemcpyDeviceToHost, *stream));
-    const bool boxsum_mode = mode == IntegratorMode::BoxSum;
-    if (boxsum_mode) {
-        cuda_err(cudaMemcpyAsync(h_obs_x.data(), d_obs_x, sizeof(float) * npredicted, cudaMemcpyDeviceToHost, *stream));
-        cuda_err(cudaMemcpyAsync(h_obs_y.data(), d_obs_y, sizeof(float) * npredicted, cudaMemcpyDeviceToHost, *stream));
-        cuda_err(cudaMemcpyAsync(h_has_obs.data(), d_has_obs, sizeof(uint8_t) * npredicted, cudaMemcpyDeviceToHost, *stream));
-    }
+    // Pass A always fills the box-sum centroid (observed spot position), so copy it back in all modes -
+    // post-refinement uses it as the observed position (beam-centre / distance).
+    cuda_err(cudaMemcpyAsync(h_obs_x.data(), d_obs_x, sizeof(float) * npredicted, cudaMemcpyDeviceToHost, *stream));
+    cuda_err(cudaMemcpyAsync(h_obs_y.data(), d_obs_y, sizeof(float) * npredicted, cudaMemcpyDeviceToHost, *stream));
+    cuda_err(cudaMemcpyAsync(h_has_obs.data(), d_has_obs, sizeof(uint8_t) * npredicted, cudaMemcpyDeviceToHost, *stream));
     cuda_err(cudaStreamSynchronize(*stream));
 
     for (size_t i = 0; i < npredicted; ++i) {
@@ -532,7 +531,7 @@ std::vector<Reflection> BraggIntegrationEngineGPU::Run(const ImagePreprocessorBu
         results[i].sigma = h_sigma[i];
         results[i].bkg = h_bkg[i];
         results[i].ok = true;
-        if (boxsum_mode && h_has_obs[i]) {
+        if (h_has_obs[i]) {
             results[i].observed_x = h_obs_x[i];
             results[i].observed_y = h_obs_y[i];
             results[i].has_observed = true;