# Role Support in Knowledge-Graph Error Ranking: Predictor Regimes and Evaluation Policies

arXiv: https://arxiv.org/abs/2512.22318 · HTML: https://mlsanity.com/paper/2512.22318/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 26 Dec 2025.

## Builds on (most cited first, 15 of 15)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Canonical Tensor Decomposition for Knowledge Base Completion](https://mlsanity.com/paper/1806.07297/) (2018)
- [CoDEx: A Comprehensive Knowledge Graph Completion Benchmark](https://mlsanity.com/paper/2009.07810/) (2020)
- [Type-Constrained Representation Learning in Knowledge Graphs](https://mlsanity.com/paper/1508.02593/) (2015)
- [Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2110.13522/) (2021)
- [Embedding Uncertain Knowledge Graphs](https://mlsanity.com/paper/1811.10667/) (2018)
- [Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning](https://mlsanity.com/paper/2104.04597/) (2021)
- [Toward Degree Bias in Embedding-Based Knowledge Graph Completion](https://mlsanity.com/paper/2302.05044/) (2023)
- [Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings](https://mlsanity.com/paper/2505.16877/) (2025)
- [Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration](https://mlsanity.com/paper/2503.18025/) (2025)
- [Selective Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2404.01695/) (2024)

## Built on by (most cited first, 1 of 1)

- [When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG](https://mlsanity.com/paper/2606.22728/) (2026)

## Abstract (arXiv)

When do role-specific training counts improve knowledge-graph error ranking? We evaluate fifteen from-scratch predictors, nine development-selected continuation stages, and six fixed ensembles across three static graphs. A positive penalty for missing training support has no stable error-ranking orientation: stronger ComplEx training reverses its pooled error AUROC from 0.689 to 0.364 on FB15k-237, and from 0.729 to 0.430 in a prospectively specified CoDEx-S check. Pair decomposition shows that reversal also survives pair-weighted within-relation evaluation, but not equal-relation averaging. The statement depends on which relations and query pairs receive weight. Learned continuous counts remain useful: they improve AURC and Brier beyond explicit ensemble disagreement in twelve original ensemble/head comparisons and satisfy all four predefined external-dataset AURC contrasts. Binary indicators add no information beyond their defining counts and have less stable fitting effects. Candidate, target, population and acceptance policies change the comparisons; fixed development thresholds do not preserve a common test answer rate. The external study was fixed before inspection of its test outcomes, whereas subsequent explanations and reused-graph controls are explicitly exploratory. These measurements support relation-aware count baselines and policy-specific support diagnostics, not a new uncertainty decomposition, causal training mechanism, calibrated factual truth, or graph-population guarantee. Saved checkpoints, ledgers and separately authored numerical implementation replays make the scoped findings inspectable.