When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection
This paper proposes a neural rule evaluator that compiles logical constraints into directed acyclic graphs and introduces chimera training to address the scarcity of real anomaly examples. Experiments on CLEVRER, OpenImages, and VidOR show improved rule-level anomaly detection AUROC, especially for compositional and relational rules.
Article intelligence
Key points
- The neural rule evaluator compiles constraints into DAGs and learns feature-aware subtree MLP gates.
- Chimera training constructs counterfactual examples by concatenating subtree features from different samples at the feature level.
- The method outperforms baselines and provides both scalar anomaly scores and rule-level attributions.
Why it matters
This matters because the neural rule evaluator compiles constraints into DAGs and learns feature-aware subtree MLP gates.
Technical impact
May affect research directions, evaluation methods, open-source reproduction, and productization paths.
[2605.26171] When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection
[Submitted on 25 May 2026]
Title:When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection
View a PDF of the paper titled When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection, by Alejandro Ascarate and 4 other authors
View PDF HTML (experimental)
Abstract:Many practical anomalies are not merely rare inputs, but violations of semantic constraints: objects co-occur in structured ways, actions imply preconditions, and events satisfy temporal or relational regularities. We study anomaly detection in this setting, where constraints are given as logical rules over learned visual concepts, but real rule violations are rare or absent during training. We propose a neural rule evaluator that compiles each constraint into a directed acyclic graph and learns feature-aware subtree MLP gates for its internal logical operators. Each gate maps child features and edge-level negations to a parent representation and a rule-satisfaction probability, with intermediate supervision obtained from exact Boolean propagation over ground-truth concept labels. The key difficulty is that same-image training data often provide insufficient coverage of informative truth configurations and also allow shortcut solutions. To address this, we introduce chimera training: an operand-level counterfactual construction at the feature level. Instead of mixing input images, we concatenate subtree features from different samples; each operand keeps the hard truth label of the sample it came from, and the chimera target is obtained by applying the node's logical operator to those inherited labels. This supplies supervised logical counterexamples without requiring real anomalous images. Across CLEVRER, OpenImages, and VidOR, the resulting evaluator improves rule-level anomaly AUROC over independent-events and same-image semantic-training baselines, especially for compositional and relational rules. The method yields both scalar anomaly scores and rule-level attributions.
Comments: 9+30 pages, 4+4 figures, under review
Subjects:
Machine Learning (cs.LG)
Cite as: arXiv:2605.26171 [cs.LG]
(or arXiv:2605.26171v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.26171
arXiv-issued DOI via DataCite
Submission history
From: Alejandro Ascárate [view email] [v1] Mon, 25 May 2026 02:52:36 UTC (3,459 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection, by Alejandro Ascarate and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)