The paper audits the confidence outputs of seven feed‑forward 3D reconstruction backbones across 13 datasets, evaluating four properties: error ranking, average error‑to‑uncertainty ratio, slope of this ratio, and coverage of the implied error distribution. While confidence ranks errors well, the decoded uncertainty is consistently too small—off by at least 2.4× on median cases—and worsens with higher confidence. A post‑hoc power‑law fit per backbone‑dataset pair improves all four metrics at the dataset level, reducing the median error by 1.35×, but fails to correct coverage for many held‑out scenes, indicating the models lack the correct error scale and distribution shape.
arXiv:2608.29705v1 Announce Type: cross Abstract: Feed-forward 3D reconstruction models emit a per-pixel confidence that downstream systems read as a reliability signal. It is trained as a loss weigh...
The paper argues that internal self-consistency checks cannot guarantee the accuracy of photogrammetric reconstructions, a limitation that is structural rather than a tuning issue. It introduces a track‑leakage‑free hold‑out protocol that withholds a deterministic subset of images and tests each against only 3D points supported by at least two retained images, ensuring no view is evaluated against the structure it helped create. Experiments on diverse datasets show that while the protocol is well‑posed, it saturates at a confidence score of 1.00 and fails to detect coherent distortion, missing large errors that can reach over 100 m. whyItMatters":"The study highlights that hold‑out self‑validation scores, increasingly used as quality evidence for metric deliverables, may be misleading and cannot replace external survey validation."
arXiv:2607. 13682v2 Announce Type: cross Abstract: Radiative Gaussian splatting reconstructs sparse-view CT fast and accurately, and recent work attaches per-Gaussian posteriors to yield per-voxel uncertainty maps.
arXiv:2608. 12652v1 Announce Type: cross Abstract: Benchmark contamination is diagnosed today with n-gram overlap, with likelihood-based membership inference, or with canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at dataset release.
arXiv:2607. 21721v1 Announce Type: cross Abstract: Learned generative priors are increasingly used for ill-posed Bayesian inverse problems, their posterior uncertainty treated as earned from data.
arXiv:2609.18465v1 Announce Type: new Abstract: Feed-forward 3D foundation models such as VGGT predict cameras, depth, and point maps in a single pass, but can fail silently under low overlap, low pa...
arXiv:2606. 15910v2 Announce Type: replace Abstract: A vision-language model can answer a question about a chest radiograph or a pathology slide fluently and confidently while barely using the image, relying instead on language priors.
arXiv:2608. 09768v1 Announce Type: new Abstract: A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken.
Feed-forward 3D foundation models such as VGGT predict cameras, depth, and point maps in a single pass, but can fail silently under low overlap, low parallax, and extreme relative rotation. Stratified...
arXiv:2606. 04857v1 Announce Type: new Abstract: Standard IMVC evaluation retrains separate models for different missing-data configurations.
arXiv:2606. 03305v1 Announce Type: new Abstract: Benchmark contamination, where evaluation examples appear in a model's training data, threatens the validity of LLM assessment.
The study evaluates the reliability of deep‑ensemble uncertainty for brain tumour segmentation on the BraTS‑GoAT dataset. A 5‑fold cross‑validated nnU‑Net baseline and a 3‑seed deep ensemble were compared for calibration and error detection; the ensemble showed modest gains in calibration on in‑distribution data but the single model’s confidence remained flat while accuracy degraded under synthetic corruptions. Disagreement among ensemble members rose sharply with corruption severity, proving to be a more sensitive indicator of acquisition shift than single‑model confidence.