In the supplementary material, we first introduce the pseudo algorithm of DA W . Then we clarify the Then, we provide a more detailed explanation of Figures 1, 2, 4, and 5, which are slightly abbreviated due to the limited space of the main paper. In the naive pseudo-labeling method, all pseudo labels are enrolled into training, i.e., E 1 + E 2, which is guaranteed by theoretical functional analysis in the next section. Inequality 45 holds true at all times. In this section, we provide more qualitative results between ours and other competitors.

The critical challenge of semi-supervised semantic segmentation lies in how to fully exploit a large volume of unlabeled data to improve the model's generalization performance for robust segmentation. Existing methods tend to employ certain criteria (weighting function) to select pixel-level pseudo labels. However, the trade-off exists between inaccurate yet utilized pseudo-labels, and correct yet discarded pseudo-labels in these methods when handling pseudo-labels without thoughtful consideration of the weighting function, hindering the generalization ability of the model. In this paper, we systematically analyze the trade-off in previous methods when dealing with pseudo-labels. We formally define the trade-off between inaccurate yet utilized pseudo-labels, and correct yet discarded pseudo-labels by explicitly modeling the confidence distribution of correct and inaccurate pseudo-labels, equipped with a unified weighting function. To this end, we propose Distribution-Aware Weighting (DAW) to strive to minimize the negative equivalence impact raised by the trade-off. We find an interesting fact that the optimal solution for the weighting function is a hard step function, with the jump point located at the intersection of the two confidence distributions. Besides, we devise distribution alignment to mitigate the issue of the discrepancy between the prediction distributions of labeled and unlabeled data. Extensive experimental results on multiple benchmarks including mitochondria segmentation demonstrate that DAW performs favorably against state-of-the-art methods.

Uncertain knowledge graphs (UKGs) associate each triple with a confidence score to provide more precise knowledge representations. Recently, since real-world UKGs suffer from the incompleteness, uncertain knowledge graph (UKG) completion attracts more attention, aiming to complete missing triples and confidences. Current studies attempt to learn UKG embeddings to solve this problem, but they neglect the extremely imbalanced distributions of triple confidences. This causes that the learnt embeddings are insufficient to high-quality UKG completion. Thus, in this paper, to address the above issue, we propose a new semi-supervised Confidence Distribution Learning (ssCDL) method for UKG completion, where each triple confidence is transformed into a confidence distribution to introduce more supervision information of different confidences to reinforce the embedding learning process. ssCDL iteratively learns UKG embedding by relational learning on labeled data (i.e., existing triples with confidences) and unlabeled data with pseudo labels (i.e., unseen triples with the generated confidences), which are predicted by meta-learning to augment the training data and rebalance the distribution of triple confidences. Experiments on two UKG datasets demonstrate that ssCDL consistently outperforms state-of-the-art baselines in different evaluation metrics.

Recent papers show LLMs achieve near-random accuracy in causal relation classification, raising questions about whether such failures arise from limited pretraining exposure or deeper representational gaps. We investigate this under uncertainty-based evaluation, testing whether pretraining exposure to causal examples improves causal understanding >18K PubMed sentences -- half from The Pile corpus, half post-2024 -- across seven models (Pythia-1.4B/7B/12B, GPT-J-6B, Dolly-7B/12B, Qwen-7B). We analyze model behavior through: (i) causal classification, where the model identifies causal relationships in text, and (ii) verbatim memorization probing, where we assess whether the model prefers previously seen causal statements over their paraphrases. Models perform four-way classification (direct/conditional/correlational/no-relationship) and select between originals and their generated paraphrases. Results show almost identical accuracy on seen/unseen sentences (p > 0.05), no memorization bias (24.8% original selection), and output distribution over the possible options is almost flat, with entropic values near the maximum (1.35/1.39), confirming random guessing. Instruction-tuned models show severe miscalibration (Qwen: > 95% confidence, 32.8% accuracy, ECE=0.49). Conditional relations induce highest entropy (+11% vs. direct). These findings suggest that failures in causal understanding arise from the lack of structured causal representation, rather than insufficient exposure to causal examples during pretraining.

We prove a fundamental impossibility theorem: neural networks cannot simultaneously learn well-calibrated confidence estimates with meaningful diversity when trained using binary correct/incorrect supervision. Through rigorous mathematical analysis and comprehensive empirical evaluation spanning negative reward training, symmetric loss functions, and post-hoc calibration methods, we demonstrate this is an information-theoretic constraint, not a methodological failure. Our experiments reveal universal failure patterns: negative rewards produce extreme underconfidence (ECE greater than 0.8) while destroying confidence diversity (std less than 0.05), symmetric losses fail to escape binary signal averaging, and post-hoc methods achieve calibration (ECE less than 0.02) only by compressing the confidence distribution. We formalize this as an underspecified mapping problem where binary signals cannot distinguish between different confidence levels for correct predictions: a 60 percent confident correct answer receives identical supervision to a 90 percent confident one. Crucially, our real-world validation shows 100 percent failure rate for all training methods across MNIST, Fashion-MNIST, and CIFAR-10, while post-hoc calibration's 33 percent success rate paradoxically confirms our theorem by achieving calibration through transformation rather than learning. This impossibility directly explains neural network hallucinations and establishes why post-hoc calibration is mathematically necessary, not merely convenient. We propose novel supervision paradigms using ensemble disagreement and adaptive multi-agent learning that could overcome these fundamental limitations without requiring human confidence annotations.