# sufficient

Published articles for sufficient.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Necessary, Not Sufficient, and No Longer Available: Grader Non-Determinism After the Withdrawal of Sampling Controls

DevFeed: [Necessary, Not Sufficient, and No Longer Available: Grader Non-Determinism After the Withdrawal of Sampling Controls](<https://devfeed.tech/articles/necessary-not-sufficient-and-no-longer-available-grader-non-determinism-after-the-withdrawal-of-sampling-controls-144911.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.26185>)

Author: Hiroki Tamba

Published: 2026-11-20T05:00:00Z

Content type: opinion

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Temperature settings in AI](<https://devfeed.tech/topics/temperature-settings-in-ai.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [Error Propagation](<https://devfeed.tech/topics/error-propagation.md>)

Tags: [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [entropy](<https://devfeed.tech/tags/entropy.md>), [error](<https://devfeed.tech/tags/error.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [fail](<https://devfeed.tech/tags/fail.md>), [gate](<https://devfeed.tech/tags/gate.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-5-6](<https://devfeed.tech/tags/gpt-5-6.md>), [gpt-5-6-sol](<https://devfeed.tech/tags/gpt-5-6-sol.md>), [gpt-6-1-sol](<https://devfeed.tech/tags/gpt-6-1-sol.md>), [harness](<https://devfeed.tech/tags/harness.md>), [index](<https://devfeed.tech/tags/index.md>), [information](<https://devfeed.tech/tags/information.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-as-judge](<https://devfeed.tech/tags/llm-as-judge.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [openai](<https://devfeed.tech/tags/openai.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>)

### AI overview

The study reports that temperature=0 is no longer a generally available control for LLM grader variability. In October-November 2026 measurements, Anthropic models rejected it; OpenAI chat completions models accepted only temperature 1, while Responses accepted temperature=0 for four of five current models with reasoning off, a configuration the author had not evaluated. The author proposes reporting per-item normalized entropy of grade distributions at the vendor-permitted setting. Across 22 condition runs and 4,760 calls, this measure ranked graders without estimating rates and identified items where the judge retained no information. Borderline items transferred only partly and unpredictably across model generations, so prior calibration sets could not simply be inherited. The author argues grader disagreement should be reported as an error bar on each verdict.

### Source excerpt

arXiv:2606.26185v3 Announce Type: replace Abstract: LLM-as-judge ("grader") components are now standard in evaluation harnesses, including safety evaluations where a pass/fail verdict may gate downstream deployment decisions. Earlier work, my own included, treated temperature=0 as the remedy for grader non-determinism and asked whether it was sufficient. It was necessary and not sufficient. It is now also unavailable. I report a two-vendor measurement taken in October and November 2026. Anthropic's current models reject the setting outright, and under the API version dated 2026-10-21 all fifteen models listed for my key reject it, the older generations included. On the chat completions endpoint OpenAI's current models accept the parameter and refuse every value but one, so a harness grading through that endpoint is obliged to sample its judge at temperature 1. On the Responses endpoint a request carrying temperature=0 is accepted by four of five current models once reasoning is switched off, a configuration I have not graded under, and by gpt-6.1-sol under no setting I tried. I propose the measurement that replaces the earlier protocol: the per-item normalized entropy of the grade distribution, reported at whatever setting the vendor permits. The direct alternative is closed too: gpt-4o returns token log-probabilities, while gpt-5.6-sol refuses the parameter and the Anthropic Messages API does not accept it at all. Across twenty-two condition runs and 4,760 calls the index orders graders without requiring a rate estimate, and identifies items at which a judge retains no information at all. I further show that a borderline item set carries across model generations only in part and not predictably, so a harness cannot inherit its calibration set. I argue that grader disagreement must be reported as an error bar on every verdict, because it is no longer something an evaluator can configure away.

## On the Limits of Sufficient Explanations

DevFeed: [On the Limits of Sufficient Explanations](<https://devfeed.tech/articles/on-the-limits-of-sufficient-explanations-135874.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18163>)

Author: Klaus Weinbauer, Peter F. Stadler, Thomas G\\"artner, Sagar Malhotra

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [explainer](<https://devfeed.tech/tags/explainer.md>), [feature](<https://devfeed.tech/tags/feature.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [images](<https://devfeed.tech/tags/images.md>), [input](<https://devfeed.tech/tags/input.md>), [language](<https://devfeed.tech/tags/language.md>), [limits](<https://devfeed.tech/tags/limits.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [probabilistic](<https://devfeed.tech/tags/probabilistic.md>), [select](<https://devfeed.tech/tags/select.md>), [statistics](<https://devfeed.tech/tags/statistics.md>), [strings](<https://devfeed.tech/tags/strings.md>), [structured](<https://devfeed.tech/tags/structured.md>), [structured-data](<https://devfeed.tech/tags/structured-data.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>)

### AI overview

The paper formalizes when post-hoc explainers can select parts of structured inputs that alone ensure a classifier's predicted label. It shows that whether such sufficient explanations exist depends on both the classifier and the allowed selection relation, and extends the analysis to probabilistic and deletion sufficiency. The authors derive task-level statistics bounding the maximum sufficiency any explainer can achieve and evaluate them on language, protein, and molecular classification datasets. Their results indicate that full sufficiency is unattainable on most evaluated datasets, so the bounds provide a reference for judging explainers' sufficiency.

### Source excerpt

arXiv:2611.18163v1 Announce Type: new Abstract: We formally characterize the conditions under which sufficient explanations exist for classifiers on structured data such as graphs and strings. We focus on post-hoc explainers that select parts of the input as sufficient explanations. An explanation is sufficient if the selected part alone ensures the predicted label. Sufficient explanations have been widely adopted across data modalities, including graphs, strings, and images. However, a unified formal analysis of sufficient explanations remains missing. We bridge this gap with four main contributions: (i) We define a general explanation formalism consisting of an instance space, a classifier, and a select relation. The select relation specifies which potential sub-instances or feature subsets can be selected as explanations from each instance; (ii) We show that the existence of sufficient explainers is fully characterized by the interplay between the classifier and the select relation; (iii) We extend this analysis to practically relevant variants of sufficiency, including probabilistic sufficiency and deletion sufficiency; (iv) Based on the formal analysis, we devise statistics that bound the maximum achievable sufficiency for a given task. We evaluate these statistics on language, protein, and molecular classification datasets and find that full sufficiency is unattainable on most of them. Since these bounds hold for every explainer, they provide a task-level reference against which any explainer's sufficiency can be judged in absolute terms.

## Spectral Ghost in Representation Learning: A Unified View from Component Analysis to Self-Supervised Learning

DevFeed: [Spectral Ghost in Representation Learning: A Unified View from Component Analysis to Self-Supervised Learning](<https://devfeed.tech/articles/spectral-ghost-in-representation-learning-a-unified-view-from-component-analysis-to-self-supervised-learning-132742.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2601.20154>)

Author: Bo Dai, Na Li, Dale Schuurmans

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Self-supervised learning](<https://devfeed.tech/topics/self-supervised-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [algorithms](<https://devfeed.tech/tags/algorithms.md>), [causal-inference](<https://devfeed.tech/tags/causal-inference.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [range](<https://devfeed.tech/tags/range.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [self-supervised-learning](<https://devfeed.tech/tags/self-supervised-learning.md>), [ssl](<https://devfeed.tech/tags/ssl.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>)

### AI overview

The paper proposes a unified spectral framework in which a representation is sufficient for arbitrary downstream prediction with a linear head when it spans the spectral decomposition of pointwise mutual information, which the authors say can be extracted from unlabeled data. It organizes representation methods by the form of the spectral representation and the objective used to fit it, relating a range of self-supervised and classical methods to combinations of those choices. It also argues that batch-size requirements depend on whether an objective is unbiased, a consistent surrogate, or biased, rather than on whether its loss is contrastive. The abstract says the framework motivates scalable algorithms and extensions to causal inference and reinforcement learning; it provides no details about those algorithms or extensions.

### Source excerpt

arXiv:2601.20154v4 Announce Type: replace Abstract: Self-supervised learning (SSL) extracts representations from massive unlabeled data that transfer to a variety of downstream tasks. Its empirical success has produced a dizzying array of objectives and procedures, yet a clear understanding of what representation is desired, and why these seemingly different methods work, is still missing. In this paper, we develop a unified spectral framework for representation learning. We first show that a representation is sufficient for arbitrary downstream prediction with a linear head if it spans the spectral decomposition of the pointwise mutual information, which can be extracted purely from unlabeled data. This view organizes representation learning along two axes, the parametrization of the spectral representation (linear, energy-based, denoising, nonlinear, latent-variable, and multi-modal) and the learning objective for fitting it, under which a broad range of existing methods, including SimCLR, MoCo, BYOL, Barlow Twins, VICReg, DINO, MAE, JEPA, BERT, GPT, and CLIP, as well as classic PCA, CCA, Laplacian eigenmaps, LLE, and SNE, are recovered as particular combinations. The framework also clarifies optimization behaviors: the batch-size requirement is determined by whether the objective is unbiased, a consistent surrogate, or biased, rather than by contrastive vs. non-contrastive losses. Finally, the framework inspires new scalable algorithms and extends spectral representations to causal inference and reinforcement learning.

## Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL

DevFeed: [Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL](<https://devfeed.tech/articles/exploration-via-exploitation-the-blessing-of-reward-diversity-in-personalized-federated-rl-128635.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12964>)

Author: Jiin Woo, Gauri Joshi, Yuejie Chi

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [exploitation](<https://devfeed.tech/tags/exploitation.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [federated](<https://devfeed.tech/tags/federated.md>), [learning](<https://devfeed.tech/tags/learning.md>), [linear](<https://devfeed.tech/tags/linear.md>), [objectives](<https://devfeed.tech/tags/objectives.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [reward](<https://devfeed.tech/tags/reward.md>), [rl](<https://devfeed.tech/tags/rl.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [state](<https://devfeed.tech/tags/state.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [value](<https://devfeed.tech/tags/value.md>)

### AI overview

The paper treats agents' differing rewards as a source of exploration in federated RL. PF-UCBVI separates shared dynamics from personalized objectives and is reported to achieve optimal linear speedup. PF-EFVI is purely greedy, uses reward diversity to provide state-action coverage without explicit exploration bonuses, and is proven to attain logarithmic regret when reward diversity is sufficient. The abstract frames this as shifting the exploration burden from temporal complexity to spatial diversity.

### Source excerpt

arXiv:2611.12964v1 Announce Type: new Abstract: While federated reinforcement learning (RL) has traditionally guaranteed high efficiency in homogeneous environments, collaboration is often hindered when agents possess distinct goals. In this paper, we flip this paradigm, framing reward heterogeneity not as a hurdle to consensus, but as a structural asset that catalyzes exploration. We first propose Personalized Federated Upper Confidence Bound Value Iteration (PF-UCBVI), which achieves optimal linear speedup by decoupling shared dynamics from personalized objectives. To eliminate the risks of explicit exploration, we then introduce Personalized Federated Exploration-Free Value Iteration (PF-EFVI), a purely greedy algorithm that leverages reward diversity to ensure state-action coverage. We prove that PF-EFVI attains logarithmic regret without explicit exploration bonuses under sufficient reward diversity. Our results reveal that agent disagreement shifts the exploration burden from temporal complexity to spatial diversity, enabling efficient collective learning without explicit exploration.

## BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation

DevFeed: [BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation](<https://devfeed.tech/articles/bo-arena-an-evolving-benchmark-for-high-dimensional-bayesian-optimisation-125144.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10198>)

Author: Colin Doumont, Thomas Christie, Henry Moss, Philipp Hennig

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Hyperparameter optimization](<https://devfeed.tech/topics/hyperparameter-optimization.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [bayesian](<https://devfeed.tech/tags/bayesian.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [canonical](<https://devfeed.tech/tags/canonical.md>), [complex](<https://devfeed.tech/tags/complex.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [errors](<https://devfeed.tech/tags/errors.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [insights](<https://devfeed.tech/tags/insights.md>), [optimisation](<https://devfeed.tech/tags/optimisation.md>), [package](<https://devfeed.tech/tags/package.md>), [paper](<https://devfeed.tech/tags/paper.md>), [performance](<https://devfeed.tech/tags/performance.md>), [practices](<https://devfeed.tech/tags/practices.md>), [problems](<https://devfeed.tech/tags/problems.md>), [reference](<https://devfeed.tech/tags/reference.md>), [simple](<https://devfeed.tech/tags/simple.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>)

### AI overview

The paper argues that high-dimensional Bayesian optimisation benchmarks often omit strong baselines or use incorrect implementations, making results hard to assess without shared reference code. It introduces BO-Arena, an actively maintained package of canonical state-of-the-art implementations for rigorous comparisons. Using it, the authors report that simpler factors drive performance and propose an algorithm competitive on problems with many observations without complex Gaussian-process approximations. They also question whether current evidence shows that more complex methods outperform a simple Gaussian process baseline.

### Source excerpt

arXiv:2611.10198v1 Announce Type: new Abstract: High-dimensional Bayesian optimisation (HDBO) is an increasingly crowded field with new methods proposed at every major conference, making it ever harder to answer a deceptively simple question: "Which method is currently state-of-the-art?" In this paper, we question the efficacy of benchmarking practices in the field, and find them to be systematically ineffective: multiple published works fail to benchmark against the strongest available baselines, or even include incorrect implementations of key methods. Without a shared reference implementation, such errors are difficult to detect during peer review. We therefore introduce BO-Arena, an actively maintained and extensible package providing canonical implementations of state-of-the-art algorithms, which allows researchers to develop new methods and benchmark them rigorously. Using BO-Arena, we find that what currently drives performance in HDBO is even simpler than previously thought. We use these insights to propose a new algorithm which is competitive with the state of the art on problems with many observations, without resorting to the complex GP approximations used in recent methods. Finally, we question whether there is currently sufficient evidence that any more complex method outperforms a simple Gaussian process baseline for HDBO.

## Minimum-Sufficient Knowledge and Computation for Wind Energy Predictive Analysis

DevFeed: [Minimum-Sufficient Knowledge and Computation for Wind Energy Predictive Analysis](<https://devfeed.tech/articles/minimum-sufficient-knowledge-and-computation-for-wind-energy-predictive-analysis-123279.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.08558>)

Author: Purbak Sengupta, Aparna S. varde, Emil J{\\o}rgensen Njor

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [Operations research and optimization](<https://devfeed.tech/topics/operations-research-and-optimization.md>), [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [big-data](<https://devfeed.tech/topics/big-data.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [apply](<https://devfeed.tech/tags/apply.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [big-data](<https://devfeed.tech/tags/big-data.md>), [computing](<https://devfeed.tech/tags/computing.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cyber](<https://devfeed.tech/tags/cyber.md>), [data](<https://devfeed.tech/tags/data.md>), [data-analysis](<https://devfeed.tech/tags/data-analysis.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [edge](<https://devfeed.tech/tags/edge.md>), [energy](<https://devfeed.tech/tags/energy.md>), [event](<https://devfeed.tech/tags/event.md>), [external](<https://devfeed.tech/tags/external.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [gate](<https://devfeed.tech/tags/gate.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>)

### AI overview

Minimum-Sufficient Knowledge and Computation (MSKC) routes each decision through the least costly option that meets risk and deployment constraints, escalating when cheaper routes are insufficient. In a wind ramp-event prediction proof of concept using public data from two wind farms, the study applies a state-aware gate to local, relational, and physics-informed routes. At a 35.9% relational-knowledge injection rate, adaptive routing was statistically indistinguishable from always-on injection on the reported metrics while reducing knowledge calls by 64%. The evidence is limited to the reported metrics and this proof-of-concept setting.

### Source excerpt

arXiv:2611.08558v1 Announce Type: new Abstract: Resource-constrained cyber-physical decision systems often apply fixed sensing, knowledge, and computational pipelines despite state-dependent information needs. We introduce Minimum-Sufficient Knowledge and Computation (MSKC), a resource-aware computing principle: select the least-costly route meeting decision-risk and deployment constraints, escalating only when cheaper routes are insufficient. As proof of concept, we isolate adaptive knowledge routing, the decision underlying Knowledge-Guided Machine Learning (KGML), which conventionally injects external knowledge unconditionally rather than only where needed. We instantiate this for wind ramp-event predictive analysis, an edge-oriented decision-support task, evaluating local, relational, and physics-informed routes with a state-aware gate on publicly available real data from two wind farms. We establish conditions for feasibility preservation, cost dominance, and strict expected savings over always-on routing. At a 35.9% relational-knowledge injection rate, adaptive routing is statistically indistinguishable from always-on injection on the reported metrics while reducing knowledge calls by 64%, supporting sustainable, Green-IT-aligned deployment. These results support MSKC's premise that uniformly maximal intelligence is unnecessary. This offers intelligent data analysis for big data streams: the analysis itself decides, per state, how much knowledge and computation the data warrant.

## On the Faithfulness of Visual Thinking: Measurement and Enhancement

DevFeed: [On the Faithfulness of Visual Thinking: Measurement and Enhancement](<https://devfeed.tech/articles/on-the-faithfulness-of-visual-thinking-measurement-and-enhancement-111868.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2510.23482>)

Author: Zujing Liu, Junwen Pan, Qi She, Yuan Gao, Guisong Xia

Published: 2026-11-02T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [vlm](<https://devfeed.tech/topics/vlm.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Chain-of-thought](<https://devfeed.tech/topics/chain-of-thought.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [automated](<https://devfeed.tech/tags/automated.md>), [chain-of-thought](<https://devfeed.tech/tags/chain-of-thought.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [enhancement](<https://devfeed.tech/tags/enhancement.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [learning](<https://devfeed.tech/tags/learning.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [metric](<https://devfeed.tech/tags/metric.md>), [rl](<https://devfeed.tech/tags/rl.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [thinking](<https://devfeed.tech/tags/thinking.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vision-language-models](<https://devfeed.tech/tags/vision-language-models.md>)

### AI overview

The paper finds that visual content in reinforcement fine-tuned multimodal chain-of-thought traces can be inaccurate while answers remain correct: predictions change little when visual thoughts are intervened on, but change significantly when textual thoughts are. The authors attribute this to reward designs that encourage interleaved vision-text formatting without checking visual correctness. They introduce an LVLM-based metric for visual cue relevance and sufficiency, reporting that current traces often fail on both. Their annotation-free, plug-and-play Sufficient-Component Cause Model (SCCM) learning encourages minimal visual components sufficient to support the answer. Experiments across fine-grained perception and reasoning benchmarks report improved visual faithfulness; the abstract does not provide quantitative results.

### Source excerpt

arXiv:2510.23482v2 Announce Type: replace-cross Abstract: Recent large vision-language models (LVLMs) can generate vision-text multimodal chain-of-thought (MCoT) traces after reinforcement fine-tuning (RFT). However, we observe that the visual information in MCoT is often inaccurate even when answers are correct, and task accuracy remains nearly unchanged despite the visual information being corrupted. This indicates a lack of faithfulness in the vision part of MCoT reasoning. We attribute this to the RL reward design in RFT, which solely incentivizes the format of interleaved vision-text cues, encouraging the model to incorporate visual information into its text reasoning steps without considering its correctness. In this paper, we first probe MCoT faithfulness by measuring how much the prediction changes when its visual and textual thoughts are intervened. Surprisingly, the model's predictions remain nearly unchanged under visual intervention but change significantly under textual intervention, indicating that the visual evidence is largely ignored. To further analyze the visual information, we introduce an automated LVLM-based evaluation metric that quantifies the faithfulness of visual cues from two perspectives: relevance and sufficiency. Our evaluation reveals that the visual information in current MCoT traces is simultaneously irrelevant and insufficient. To address this issue, we propose Sufficient-Component Cause Model (SCCM) learning. This approach encourages the MCoT to generate sufficient yet minimal visual components that are independently capable of leading to the correct answer. The proposed SCCM is annotation-free and plug-and-play, compatible with various RFT for MCoT. Empirical results demonstrate that SCCM substantially improves the visual faithfulness across a suite of fine-grained perception and reasoning benchmarks. Code is available at https://github.com/EugeneLiu01/Faithful_Thinking_with_Image.

## GenoBERT: A Language Model for Accurate Genotype Imputation

DevFeed: [GenoBERT: A Language Model for Accurate Genotype Imputation](<https://devfeed.tech/articles/genobert-a-language-model-for-accurate-genotype-imputation-107883.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2604.00058>)

Author: Lei Huang, Chuan Qiu, Kuan-Jui Su, Anqi Liu, Yun Gong, Weiqiang Lin, Lindong Jiang, Chen Zhao, Meng Song, Jeffrey Deng, Qing Tian, Zhe Luo, Ping Gong, Hui Shen, Chaoyang Zhang, Hong-Wen Deng

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [bert](<https://devfeed.tech/topics/bert.md>)

Tags: [attention](<https://devfeed.tech/tags/attention.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [bias](<https://devfeed.tech/tags/bias.md>), [correlation](<https://devfeed.tech/tags/correlation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [genomics](<https://devfeed.tech/tags/genomics.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [panel](<https://devfeed.tech/tags/panel.md>), [performance](<https://devfeed.tech/tags/performance.md>), [q-bio-gn](<https://devfeed.tech/tags/q-bio-gn.md>), [range](<https://devfeed.tech/tags/range.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [sparsity](<https://devfeed.tech/tags/sparsity.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

### AI overview

GenoBERT imputes missing phased genotypes without a reference panel, using a transformer with self-attention to capture short- and long-range linkage disequilibrium. In tests on the Louisiana Osteoporosis Study and 1000 Genomes Project across ancestry groups and 5-50% missingness, it had the highest overall accuracy among the four named baselines: Beagle5.4, SCDA, BiU-Net, and STICI. The abstract reports r² around 0.98 with up to 25% missing and above 0.90 at 50% missing. It also reports consistent gains across ancestries and resilience to small samples and weak LD. LD-decay analyses supported a 128-SNP context window (about 100 Kb) for local correlations. These findings are based on the abstract; it does not provide detailed methods or per-group results.

### Source excerpt

arXiv:2604.00058v2 Announce Type: replace-cross Abstract: Genotype imputation enables dense variant coverage for genome-wide association and risk-prediction studies, yet conventional reference-panel methods remain limited by ancestry bias and reduced rare-variant accuracy. We present Genotype Bidirectional Encoder Representations from Transformers (GenoBERT), a transformer-based, reference-free framework that tokenizes phased genotypes and uses a self-attention mechanism to capture both short- and long-range linkage disequilibrium (LD) dependencies. Benchmarking on two independent datasets including the Louisiana Osteoporosis Study (LOS) and the 1000 Genomes Project (1KGP) across ancestry groups and multiple genotype missingness levels (5-50%) shows that GenoBERT achieves the highest overall accuracy compared to four baseline methods (Beagle5.4, SCDA, BiU-Net, and STICI). At practical sparsity levels (up to 25% missing), GenoBERT attains high overall imputation accuracy ($r^2 approx 0.98$) across datasets, and maintains robust performance ($r^2 > 0.90$) even at 50% missingness. Experimental results across different ancestries confirm consistent gains across datasets, with resilience to small sample sizes and weak LD. A 128-SNP (single-nucleotide polymorphism) context window (approximately 100 Kb) is validated through LD-decay analyses as sufficient to capture local correlation structures. By eliminating reference-panel dependence while preserving high accuracy, GenoBERT provides a scalable and robust solution for genotype imputation and a foundation for downstream genomic modeling.

## Finite-Step Geometry of Marginal-Preserving Velocity Fields in Generative Flows

DevFeed: [Finite-Step Geometry of Marginal-Preserving Velocity Fields in Generative Flows](<https://devfeed.tech/articles/finite-step-geometry-of-marginal-preserving-velocity-fields-in-generative-flows-108613.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.37936>)

Author: Ewsey Obzherin, Valentin Khrulkov

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [World models](<https://devfeed.tech/topics/world-models.md>)

Tags: [continuous](<https://devfeed.tech/tags/continuous.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [distributions](<https://devfeed.tech/tags/distributions.md>), [error](<https://devfeed.tech/tags/error.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [flow](<https://devfeed.tech/tags/flow.md>), [gaussian](<https://devfeed.tech/tags/gaussian.md>), [generative](<https://devfeed.tech/tags/generative.md>), [integration](<https://devfeed.tech/tags/integration.md>), [law](<https://devfeed.tech/tags/law.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [score](<https://devfeed.tech/tags/score.md>), [shape](<https://devfeed.tech/tags/shape.md>), [sharp](<https://devfeed.tech/tags/sharp.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [velocity](<https://devfeed.tech/tags/velocity.md>)

### AI overview

Different velocity fields can follow the same continuous marginal path yet produce different marginal errors after finite-step numerical integration. The paper characterizes this effect using projected modified equations and gives conditions for higher marginal convergence order. For affine distributions with fixed shape, it derives exact finite-step reachability conditions, spectral obstructions, and sharp nearest-reachable Wasserstein errors. For diffusion probability-flow ODEs, skew-score perturbations preserve the exact marginal path when scores are exact, while score error causes measurable leakage. Controlled Gaussian and mixture experiments reproduce the predicted convergence, reachability, and obstruction behavior.

### Source excerpt

arXiv:2610.37936v1 Announce Type: new Abstract: Generative flows can admit different velocity fields that induce the same continuous marginal evolution but behave differently after numerical discretization. We study this finite-step non-equivalence while keeping the marginal path and numerical method fixed. Projected modified equations characterize the component of local integration error that changes the marginal law and give sufficient conditions for higher marginal convergence order. For affine fixed-shape distributions, we characterize exact finite-step reachability and derive spectral obstructions and sharp nearest-reachable Wasserstein errors. For diffusion probability-flow ODEs, we construct skew-score perturbations that preserve the exact marginal path under exact scores and quantify their leakage under score error. Controlled Gaussian and mixture experiments recover the predicted order, reachability, and obstruction phenomena.

## In the Driver's Seat: A Multi-Company Study on the Reality of Autonomous Driving System Testing

DevFeed: [In the Driver's Seat: A Multi-Company Study on the Reality of Autonomous Driving System Testing](<https://devfeed.tech/articles/in-the-driver-s-seat-a-multi-company-study-on-the-reality-of-autonomous-driving-system-testing-101718.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.15820>)

Author: Qunying Song, Yuan Gao, Johannes Betz, Dietmar Pfahl, Mohammad Reza Mousavi, Federica Sarro

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [autonomous vehicles](<https://devfeed.tech/topics/autonomous-vehicles.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [company](<https://devfeed.tech/tags/company.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [environments](<https://devfeed.tech/tags/environments.md>), [framework](<https://devfeed.tech/tags/framework.md>), [interviews](<https://devfeed.tech/tags/interviews.md>), [observability](<https://devfeed.tech/tags/observability.md>), [planning](<https://devfeed.tech/tags/planning.md>), [safety](<https://devfeed.tech/tags/safety.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [study](<https://devfeed.tech/tags/study.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

Interviews with ADS practitioners at nine companies across six countries describe industrial testing as an evidence-building process: teams plan what evidence they need, produce and evaluate it across complementary test environments, then judge whether it is sufficient for progression or release. Confidence is limited by scenario adequacy, simulation and deployment fidelity, test execution and observability, and assurance and decision sufficiency. Practitioners use approaches to address these limits, but gaps remain. The authors propose a closed-loop framework linking testing intent, scenario selection, evidence production, acceptance decisions, and operational feedback.

### Source excerpt

arXiv:2607.15820v2 Announce Type: replace Abstract: Autonomous driving systems (ADS) are increasingly deployed in complex real-world environments, creating strong demands for rigorous testing to establish their functionality and safety. However, ADS testing remains difficult because practitioners must determine not only what and how to test, but also whether the resulting evidence is sufficient to support progression and release decisions. To understand how this is handled in practice, we conducted semi-structured interviews with experts involved in ADS development and testing across nine companies in six countries. Through thematic analysis, we examined how practitioners organize ADS testing to produce and assess evidence, and what limits confidence in that evidence. Our findings show that industrial ADS testing can be understood as an evidence-building process involving three recurring activities: planning what evidence is needed, producing and evaluating evidence across complementary testing environments, and deciding when testing is sufficient. We further identified recurring limitations concerning scenario adequacy, simulation and deployment fidelity, test execution and observability, and assurance and decision sufficiency. Practitioners reported several approaches for addressing these limitations, although important gaps remain. Based on these findings, we propose an evidence-centered closed-loop testing framework that connects testing intent, scenario selection, evidence production, acceptance decisions, and operational feedback. The study provides an industry-grounded account of how ADS testing is organized, where confidence in current testing breaks down, and how testing processes can be structured more systematically.

## Advances in Machine Learning for Directed Evolution: A Five-Year Retrospective

DevFeed: [Advances in Machine Learning for Directed Evolution: A Five-Year Retrospective](<https://devfeed.tech/articles/advances-in-machine-learning-for-directed-evolution-a-five-year-retrospective-96868.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.03046>)

Author: Bruce J. Wittmann

Published: 2026-10-23T04:00:00Z

Content type: opinion

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>)

Tags: [cost](<https://devfeed.tech/tags/cost.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dna](<https://devfeed.tech/tags/dna.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [goals](<https://devfeed.tech/tags/goals.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [ml](<https://devfeed.tech/tags/ml.md>), [objectives](<https://devfeed.tech/tags/objectives.md>), [practical](<https://devfeed.tech/tags/practical.md>), [q-bio-bm](<https://devfeed.tech/tags/q-bio-bm.md>), [resource](<https://devfeed.tech/tags/resource.md>), [retrospective](<https://devfeed.tech/tags/retrospective.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>), [time](<https://devfeed.tech/tags/time.md>)

### AI overview

The retrospective argues that machine learning has had less impact on directed evolution partly because ML-assisted directed evolution (MLDE) often seeks an optimal protein, while practical directed evolution seeks a sufficient protein within time and resource constraints. It highlights DNA synthesis costs as a key omission in nearly all current MLDE methods, limiting practical applicability regardless of model capability. The author notes recent exceptions and argues that the past five years of ML-assisted protein engineering can coexist with reframing MLDE objectives around practical constraints.

### Source excerpt

arXiv:2609.03046v2 Announce Type: replace-cross Abstract: The last five-plus years have seen many protein engineering disciplines transformed by advances in machine learning (ML), but the same cannot be said for directed evolution. Reflecting on a previously co-authored perspective, I discuss why I believe this to be the case, arguing that a disconnect between the goals of machine-learning-assisted directed evolution (MLDE) researchers--"identify an optimal protein"--and the goals of directed evolution more broadly--"identify a sufficient protein given time and resource constraints"--is a principal culprit. As an example, I highlight how nearly all current MLDE methods neglect to account for the cost of DNA synthesis, resulting in strategies that have limited practical applicability regardless of the underlying models' capabilities. I close by discussing recent works that are exceptions to this overarching trend, and emphasize that the last five years of efforts in ML-assisted protein engineering and the prescribed reframe of MLDE objectives need not be mutually exclusive.

## When Reconstruction Is Not Enough: Doubly Robust Counterfactual and Interventional Mediation Analysis with Learned Multimodal Representations

DevFeed: [When Reconstruction Is Not Enough: Doubly Robust Counterfactual and Interventional Mediation Analysis with Learned Multimodal Representations](<https://devfeed.tech/articles/when-reconstruction-is-not-enough-doubly-robust-counterfactual-and-interventional-mediation-analysis-with-learned-multimodal-representations-96911.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.30220>)

Author: Cong Cao

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>)

Tags: [autoencoders](<https://devfeed.tech/tags/autoencoders.md>), [bias](<https://devfeed.tech/tags/bias.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [diagnostics](<https://devfeed.tech/tags/diagnostics.md>), [digital-twins](<https://devfeed.tech/tags/digital-twins.md>), [health](<https://devfeed.tech/tags/health.md>), [linear](<https://devfeed.tech/tags/linear.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [portable](<https://devfeed.tech/tags/portable.md>), [robust](<https://devfeed.tech/tags/robust.md>), [stat-me](<https://devfeed.tech/tags/stat-me.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Learned health-record representations can preserve reconstruction quality while losing confounders needed for causal identification, causing large bias. The abstract distinguishes counterfactual comparisons from interventional mediation, which requires more from a representation, and shows that double robustness and cross-fitting do not remove first-order representation bias; with an insufficient representation, interval coverage can worsen as sample size grows. The proposed workflow combines modality-specific variational autoencoders trained outside the estimation sample with cross-fitted doubly robust estimation, locked phenotypes, select-then-confirm pathway analysis, portable representations, and diagnostics for insufficiency, exposure leakage, and sensitivity. In simulations, omitting a rare, moderately strong confounder yielded only 2% coverage for indirect-effect intervals at n=3,000; reconstruction loss missed the problem, while a predictive diagnostic flagged it in every replicate.

### Source excerpt

arXiv:2610.30220v1 Announce Type: new Abstract: Learned representations of high-dimensional multimodal health records are increasingly used to adjust for confounding, yet they are usually trained to reconstruct the data rather than preserve the information that causal identification requires. We study counterfactual outcomes under alternative treatments, including phenotype-specific effects and patient-level counterfactual risk profiles of the kind digital twins provide, and interventional direct and indirect effects under exposure-induced intermediate confounding. We give conditions under which a representation preserves identification and show that interventional mediation is more demanding than counterfactual comparison. We prove that no covariate-only training objective, whether reconstruction, contrastive, or physics-informed, can certify that a representation is sufficient, and that, in a linear structural model, a representation can lose arbitrarily little reconstruction accuracy yet induce arbitrarily large bias. We decompose the error of cross-fitted doubly robust estimators into a first-order representation bias, which neither double robustness nor cross-fitting removes, and a second-order remainder of nuisance-estimation errors, so coverage worsens as the sample size grows when the representation is insufficient. We propose a workflow combining modality-specific variational autoencoders trained outside the estimation sample, cross-fitted doubly robust estimators, locked phenotypes, select-then-confirm pathway analysis, portable representations, and diagnostics for representation insufficiency, exposure leakage, and sensitivity. In simulations, discarding a rare, moderately strong confounder gave indirect-effect intervals with 2% coverage at n = 3,000; reconstruction loss missed the problem, and a simple predictive diagnostic flagged it in every replicate.

## An Agentic Approach to Metadata Reasoning

DevFeed: [An Agentic Approach to Metadata Reasoning](<https://devfeed.tech/articles/an-agentic-approach-to-metadata-reasoning-96704.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2604.20144>)

Author: Jiani Zhang, Sercan O. Arik, Cosmin Arad, Fatma Ozcan, Alon Halevy

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [data-lake](<https://devfeed.tech/tags/data-lake.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [queries](<https://devfeed.tech/tags/queries.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [robust](<https://devfeed.tech/tags/robust.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [search-engine](<https://devfeed.tech/tags/search-engine.md>), [selection](<https://devfeed.tech/tags/selection.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [table](<https://devfeed.tech/tags/table.md>), [tables](<https://devfeed.tech/tags/tables.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Metadata Reasoner addresses data-source discovery for analytical tasks by using a table-search engine to find candidate tables, then consulting multiple aspects of their metadata to select a sufficient, minimal set. On KramaBench, it achieves 88.63% average F1, 10.73 percentage points above the strongest baseline. On a synthetic BIRD-based benchmark with redundant and low-quality tables, it reaches 93.5% average F1 and reports 100% success in avoiding low-quality data. An extension interleaves table selection with partial-query execution; on runtime-dependent tasks, this improves table-selection F1 by 4.8 points and end-to-end accuracy by 5.3 points versus single-pass selection.

### Source excerpt

arXiv:2604.20144v3 Announce Type: replace Abstract: As autonomous LLM agents evolve to perform complex analytical tasks that require integrating multiple datasets, the problem of discovering relevant data sources becomes a key bottleneck. Beyond the challenge posed by the sheer volume of available data sources, data-source selection is difficult because the semantics of data are nuanced and require considering many aspects of the data. To address this challenge, we introduce Metadata Reasoner, an agentic approach to metadata reasoning that identifies a small set of data sources that are both sufficient and minimal for a given analytical task. Metadata Reasoner leverages a table-search engine to retrieve candidate tables, and then autonomously consults various aspects of the available metadata to determine whether the candidates fit the requirements of the task. We demonstrate the effectiveness of Metadata Reasoner through a series of empirical studies. Evaluated on the real-world KramaBench datasets for data selection, our approach achieves an average F1 score of 88.63%, outperforming the strongest baseline by 10.73 percentage points. Furthermore, evaluations on a newly created synthetic benchmark based on the BIRD dataset reveal that Metadata Reasoner is highly robust against redundant and low-quality tables that are in the data lake. In this noisy environment, Metadata Reasoner maintains a 93.5% average F1 score for selecting the right datasets and demonstrates a 100% success rate in avoiding low-quality data. Finally, we extend Metadata Reasoner to support the interleaving of table selection with the execution of partial queries. Compared with a single pass of table selection, such interleaving improves table-selection F1 score on runtime-dependent tasks by 4.8 percentage points and end-to-end task accuracy by 5.3 points.

## Local and Global Recursive Ridge Regression for Online Residual Correction of Frozen Multivariate Forecasters under Label Delay

DevFeed: [Local and Global Recursive Ridge Regression for Online Residual Correction of Frozen Multivariate Forecasters under Label Delay](<https://devfeed.tech/articles/local-and-global-recursive-ridge-regression-for-online-residual-correction-of-frozen-multivariate-forecasters-under-label-delay-94963.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.29604>)

Author: Takumi Fujimoto, Hiroaki Nishi

Published: 2026-10-22T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [linear-regression](<https://devfeed.tech/topics/linear-regression.md>), [Data Mining & Modeling](<https://devfeed.tech/topics/data-mining-modeling.md>)

Tags: [channel](<https://devfeed.tech/tags/channel.md>), [cosine](<https://devfeed.tech/tags/cosine.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [delay](<https://devfeed.tech/tags/delay.md>), [electricity](<https://devfeed.tech/tags/electricity.md>), [elf](<https://devfeed.tech/tags/elf.md>), [error](<https://devfeed.tech/tags/error.md>), [forecast](<https://devfeed.tech/tags/forecast.md>), [global](<https://devfeed.tech/tags/global.md>), [local](<https://devfeed.tech/tags/local.md>), [online](<https://devfeed.tech/tags/online.md>), [reduction](<https://devfeed.tech/tags/reduction.md>), [regression](<https://devfeed.tech/tags/regression.md>), [state](<https://devfeed.tech/tags/state.md>), [statistics](<https://devfeed.tech/tags/statistics.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [times](<https://devfeed.tech/tags/times.md>), [traffic](<https://devfeed.tech/tags/traffic.md>), [weather](<https://devfeed.tech/tags/weather.md>)

### AI overview

DRiC corrects a frozen multi-horizon forecaster online by recursively fitting ridge regressions on leading DCT coefficients of forecast and input blocks to predict residual blocks, accommodating the delay before each block's labels arrive. DRiC-L keeps a regression per channel; DRiC-G pools channels, so its statistics do not grow with channel count. A guard skips updates for unusually large residual blocks and clips corrections. Across 126 evaluated conditions, DRiC-L8 reduced MSE by 14.55% on average versus 12.98% for ELF, while retaining 15-17 times less state; ELF was more accurate on Traffic. DRiC-G used 14.6 kB on Electricity and 18.9 kB on Traffic and was the most accurate method at or below its state, though 5-7 comparators using at least 10 times more state performed better. On unfilled Weather data, the guard mattered: without it, DRiC-L8's MSE averaged 8 times the frozen forecast's; with it, MSE fell 7.94%.

### Source excerpt

arXiv:2610.29604v1 Announce Type: new Abstract: A frozen multi-horizon forecaster can be corrected online from its own residuals. However, under label delay the target of a block arrives only after the whole horizon has passed, and the corrector's retained state grows with the number of channels. Aiming to combine a small retained state with a large error reduction, we propose DRiC (DCT Ridge Corrector), which fits a ridge regression of the leading discrete cosine transform (DCT) coefficients of the next residual block on those of the frozen forecast and of the latest input block, with sufficient statistics updated recursively. Its local variant, DRiC-L, keeps one such regression per channel; its global variant, DRiC-G, pools all channels into one regression, whose statistics do not depend on the channel count. A guard tracks a running scale of the frozen forecast's residual for each channel; it skips updates on blocks far outside that scale and clips the issued correction. We evaluate on seven datasets (four ETT series, Weather with its missing-value codes filled, Electricity, and Traffic) with DLinear, PatchTST, and iTransformer backbones, against 10 naive, gradient-trained, and closed-form methods. DRiC-L with eight DCT coefficients (DRiC-L8) reduces the mean squared error (MSE) by 14.55% on average over 126 conditions, against 12.98% for ELF, the most accurate comparator, while retaining 15-17 times less state, although ELF is more accurate on Traffic. DRiC-G retains 14.6 kB on the 321-channel Electricity data and 18.9 kB on the 862-channel Traffic data and is the most accurate method at or below its state on both. However, 5 to 7 of the 10 comparators, all with at least 10 times its state, are more accurate there. On the unfilled Weather file, DRiC-L8 without the guard has on average 8.0 times the frozen forecast's MSE, whereas with the guard it reduces the MSE by 7.94%. Code: https://github.com/keiotakmin/dric.

## Looped GNNs Beyond Fixed Depth: Graph Size Generalization and Parameter-Efficient Adaptation

DevFeed: [Looped GNNs Beyond Fixed Depth: Graph Size Generalization and Parameter-Efficient Adaptation](<https://devfeed.tech/articles/looped-gnns-beyond-fixed-depth-graph-size-generalization-and-parameter-efficient-adaptation-93241.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.24112>)

Author: Zhiyang Wang, Zhishang Luo, Yusu Wang

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [peft](<https://devfeed.tech/topics/peft.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [application](<https://devfeed.tech/tags/application.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [effects](<https://devfeed.tech/tags/effects.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [gnn](<https://devfeed.tech/tags/gnn.md>), [graph](<https://devfeed.tech/tags/graph.md>), [information](<https://devfeed.tech/tags/information.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [processor](<https://devfeed.tech/tags/processor.md>), [radius](<https://devfeed.tech/tags/radius.md>), [reuse](<https://devfeed.tech/tags/reuse.md>), [sample](<https://devfeed.tech/tags/sample.md>), [size](<https://devfeed.tech/tags/size.md>), [small](<https://devfeed.tech/tags/small.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>)

### AI overview

Looped GNNs extend information reach to larger graphs by repeatedly applying a GNN processor pretrained on smaller graphs, without retraining. The paper studies tasks with a shared local iterative computation whose effective dependency radius grows with graph size, and categorizes six schemes to distinguish depth extension, fine-tuning, and freeze-and-steer adaptation. Its analysis gives fixed-depth information limits and conditions for accurate iterative reuse. For adaptation, Loop-Freeze-Steer (LFS) freezes the pretrained processor and trains a small controller to guide repeated application, using fewer trainable parameters than full fine-tuning. Finite-sample analysis provides conditions under which adaptation can improve larger-graph performance. Experiments on synthetic tasks and chip placement evaluate these approaches and their accuracy-trainable-parameter trade-off.

### Source excerpt

arXiv:2610.24112v1 Announce Type: new Abstract: Generalizing from small graphs to larger ones can require computation beyond the depth of a neural model used during training. We study target tasks that admit a common local iterative computation and whose effective dependency radius grows with graph size. The central idea is to learn a local update rule through GNN pretraining, then repeatedly apply the same learned processor beyond the training depth to extend information reach on larger graphs without retraining. Calling such parameter-shared architecture a \emph{looped GNN}, we categorize six schemes for looped GNNs to separate the effects of depth extension, fine-tuning, and freeze-and-steer adaptation. Our analysis establishes fixed-depth information limits and sufficient conditions under which accurate iterative reuse overcomes them. To improve beyond unadapted reuse, we introduce \emph{Loop-Freeze-Steer} (LFS), which freezes the pretrained processor and learns a small controller to steer its repeated application, using much fewer trainable parameters than full fine-tuning. Our finite-sample analysis gives sufficient conditions for adaptation to improve performance on larger graphs. Experiments on synthetic tasks and chip placement evaluate depth extension and adaptation, highlighting LFS's accuracy--trainable-parameter trade-off for size generalization.

## Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation

DevFeed: [Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation](<https://devfeed.tech/articles/tokens-per-parameter-coverage-is-critical-for-robust-llm-scaling-law-extrapolation-94123.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.08541>)

Author: Joshua Shay Kricheli, Alexander Lawrence Reid, Soumajyoti Sarkar, Venkata Gandikota, Paulo Shakarian

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [scaling laws](<https://devfeed.tech/topics/scaling-laws.md>), [Chinchilla scaling law](<https://devfeed.tech/topics/chinchilla-scaling-law.md>)

Tags: [3](<https://devfeed.tech/tags/3.md>), [compute](<https://devfeed.tech/tags/compute.md>), [condition](<https://devfeed.tech/tags/condition.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [design](<https://devfeed.tech/tags/design.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [gap](<https://devfeed.tech/tags/gap.md>), [llm](<https://devfeed.tech/tags/llm.md>), [newton](<https://devfeed.tech/tags/newton.md>), [parameter](<https://devfeed.tech/tags/parameter.md>), [point](<https://devfeed.tech/tags/point.md>), [ratio](<https://devfeed.tech/tags/ratio.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [scaling-laws](<https://devfeed.tech/tags/scaling-laws.md>), [square](<https://devfeed.tech/tags/square.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [token](<https://devfeed.tech/tags/token.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

Fitting scaling laws from runs at a single tokens-per-parameter ratio can make parameter and token effects difficult to distinguish, especially when their exponents are nearly equal. The abstract reports that this collinear design makes Gauss-Newton estimation ill-conditioned, inflates coefficient confidence intervals by an order of magnitude or more, and harms extrapolation away from the training ray. The authors prove the result for four scaling-law formalisms and give a necessary-and-sufficient TPP-diversity threshold for well-conditioned estimation. In held-out comparisons, non-collinear designs won 97.3% of the time across four laws, five corpora, and multiple floating-point precision modes. The abstract attributes the issue to Jacobian geometry, extending it to smooth objectives whose curvature involves the Jacobian.

### Source excerpt

arXiv:2605.08541v3 Announce Type: replace Abstract: Neural scaling laws approximate a language model's loss as a power-law function of parameter count $N$ and token count $D$. Following Chinchilla-style compute-optimal training, many studies fit scaling laws from runs performed under a fixed tokens-per-parameter (TPP) ratio $k$ and set $D = kN$. We show that this collinear design, combined with the empirically common near-equality of the exponents governing $N$ and $D$, induces an inherent ill-conditioning in the Gauss-Newton least-squares problem: the condition number of the design grows as the inverse square of the gap between the $N$ and $D$-exponents. The scale coefficients become practically unidentifiable, with confidence intervals inflating by an order of magnitude or more, yielding a ``sloppy'' model whose extrapolations degrade sharply off the training ray. We prove this for four scaling-law formalisms and derive a closed-form TPP-diversity threshold that is necessary and sufficient for well-conditioned estimation. Empirically, non-collinear designs outperform collinear ones on held-out splits with a 97.3\% win rate across four laws, five corpora, multiple floating point precision modes. We further show the degeneracy is rooted in Jacobian geometry and is not an artifact of the loss function: any smooth estimation objective whose curvature involves the Jacobian inherits the same ill-conditioning.

## Evidence Sufficiency and Model Comparisons in MexRegQA: An Item-Level Audit of Mexican-Spanish Regulatory QA

DevFeed: [Evidence Sufficiency and Model Comparisons in MexRegQA: An Item-Level Audit of Mexican-Spanish Regulatory QA](<https://devfeed.tech/articles/evidence-sufficiency-and-model-comparisons-in-mexregqa-an-item-level-audit-of-mexican-spanish-regulatory-qa-93534.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.25710>)

Author: Fred Hu (Huawei Technologies de M\\'exico, Mexico), Yeqi Wang (Huawei Technologies de M\\'exico, Mexico), Xing Zhou (Northeastern University, USA)

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [audit](<https://devfeed.tech/topics/audit.md>)

Tags: [audit](<https://devfeed.tech/tags/audit.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [comparisons](<https://devfeed.tech/tags/comparisons.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [financial](<https://devfeed.tech/tags/financial.md>), [independent](<https://devfeed.tech/tags/independent.md>), [machine](<https://devfeed.tech/tags/machine.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [qa](<https://devfeed.tech/tags/qa.md>), [regulatory](<https://devfeed.tech/tags/regulatory.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>)

### AI overview

Similarity-gated retrieval coverage can miss facts needed to answer regulatory questions: in MexRegQA, 35 of 135 covered items lacked some or all load-bearing facts. On the post-hoc full-evidence slice, eleven prompt-matched models scored 95-98/98 with no significant differences from the anchor, which the authors say does not establish equivalence; excluding evidence-defective items changed the nominal significance status of 14 of 55 pairwise comparisons. Across 56 zero-evidence items, accuracy ranged from 33.9% to 89.3%. Removing evidence under an abstention-permitting prompt reduced accuracy by 63-81 percentage points in all ten tested legs, recovering no items. The authors release MexRegQA v1.0 with provenance and evidence-status labels, while noting the audit was outcome-aware, later comparisons reused the questions, and evaluations lack independent human validation.

### Source excerpt

arXiv:2610.25710v1 Announce Type: new Abstract: Similarity-gated coverage does not establish that retrieved evidence contains the facts needed to answer a question. We audit Mexican-Spanish financial-regulatory QA and find that 35 of 135 covered items lack some or all load-bearing facts. On the post-hoc full-evidence slice (n=98), eleven prompt-matched models score 95-98/98 and none differs significantly from the anchor; this does not establish equivalence. Removing evidence-defective items changes the nominal significance status of 14 of 55 pairwise comparisons. On 56 zero-evidence items, accuracy spans 33.9%-89.3%. Removing evidence from the audited items under an abstention-permitting prompt reduces accuracy by 63-81 percentage points in all ten tested legs, with no recovered items. Building on sufficient-context research, we contribute MexRegQA v1.0: 192 items with provenance and evidence-status labels, frozen retrieval evidence for 191 evaluated items, predictions, judge outputs and offline checks. The audit was outcome-aware, the later model/panel sweep reused the same questions, and all reported scores and labels rely on machine evaluation without independent human validation. We propose releasing evidence-status labels alongside grounded QA benchmarks so that model comparisons can be examined separately from evidence availability.

## ShinyHunters' exploitation of a new PeopleSoft zero-day hole threatens to change enterprise risk dynamics

DevFeed: [ShinyHunters' exploitation of a new PeopleSoft zero-day hole threatens to change enterprise risk dynamics](<https://devfeed.tech/articles/shinyhunters-exploitation-of-a-new-peoplesoft-zero-day-hole-threatens-to-change-enterprise-risk-dynamics-65238.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4230914/shinyhunters-exploitation-of-a-new-peoplesoft-zero-day-hole-threatens-to-change-enterprise-risk-dynamics-2.html>)

Author: Evan Schuman

Published: 2026-10-06T01:10:13Z

Content type: news

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [known exploitable vulnerabilities](<https://devfeed.tech/topics/known-exploitable-vulnerabilities.md>), [Hacking](<https://devfeed.tech/topics/hacking.md>), [distroless](<https://devfeed.tech/topics/distroless.md>)

Tags: [business](<https://devfeed.tech/tags/business.md>), [business-enterprise-enterprise-applications-erp-systems-security-vulnerabilities-zero-day-vuln](<https://devfeed.tech/tags/business-enterprise-enterprise-applications-erp-systems-security-vulnerabilities-zero-day-vuln.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-applications](<https://devfeed.tech/tags/enterprise-applications.md>), [erp-systems](<https://devfeed.tech/tags/erp-systems.md>), [peoplesoft](<https://devfeed.tech/tags/peoplesoft.md>), [security](<https://devfeed.tech/tags/security.md>), [shinyhunters](<https://devfeed.tech/tags/shinyhunters.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [zero-day](<https://devfeed.tech/tags/zero-day.md>), [zero-day-vulnerabilities](<https://devfeed.tech/tags/zero-day-vulnerabilities.md>)

### AI overview

The article reports that ShinyHunters claims to have used a newly discovered PeopleSoft zero-day to breach an FBI system, while the FBI confirmed a breach without details and Oracle has not confirmed the alleged flaw. Analysts recommend patching, limiting public access to exposed PeopleSoft components, and checking for signs of compromise; they stress that the zero-day claim lacks independent confirmation.

### Source excerpt

A recent compromise of PeopleSoft by hacking group ShinyHunters is causing new concerns for enterprise users of the Oracle product, with analysts recommending extreme measures in response. Law enforcement has made some progress in its pursuit of the cyber criminals involved. On Saturday, Reuters reported that a suspected member of ShinyHunters had been arrested by the FBI and has been cooperating with law enforcement to help identify other member of the group. The arrest comes after The Register reported that the group claimed to have discovered a new PeopleSoft zero-day hole and to have leveraged it to break into an FBI system, stealing information on all FBI employees. The FBI has since confirmed the breach without providing details, and PeopleSoft has been silent about the allegedly new flaw. This isn't the first flaw ShinyHunters has found in PeopleSoft. It discovered a PeopleSoft zero-day hole in June that resulted in a flurry of extortion attempts, long after Oracle said it had patched the bugs. Oracle did not respond to a request for comment on the latest vulnerability. Significant risk exposure for enterprises Analysts and consultants played up the risk exposure from the potentially new vulnerability even as they sharply played down the implications of the arrest. Frank Dickson, principal analyst at Dickson Research, recommended that PeopleSoft users take immediate action. "If it is a new flaw, the patch is necessary but not sufficient. PeopleSoft customers should pull the Environment Management Hub and the Integration Broker off the public internet," he said. "Doing so does not break normal user sessions." He also encouraged users to quickly implement many of the recommendations from Google unit Mandiant's report late last month on PeopleSoft security issues, especially "hunting for the web shells and outbound traffic Mandiant describes." "For PeopleSoft shops, the to-do list is short," Dickson said. "Apply Oracle's patch. Disable or remove the Environment

## Ex-Google safety chief warns AI could harm children more than social media did

DevFeed: [Ex-Google safety chief warns AI could harm children more than social media did](<https://devfeed.tech/articles/ex-google-safety-chief-warns-ai-could-harm-children-more-than-social-media-did-58358.md>)

Original publisher: [Read original article](<https://indianexpress.com/article/technology/tech-news-technology/ex-google-safety-chief-warns-ai-could-harm-children-more-than-social-media-did-10890039/>)

Author: Reuters

Published: 2026-09-23T04:13:04Z

Content type: news

Language: en

Sources: [Technology | The Indian Express](<https://devfeed.tech/sources/technology-the-indian-express.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [trust and safety](<https://devfeed.tech/topics/trust-and-safety.md>), [Responsibility & Safety](<https://devfeed.tech/topics/responsibility-safety.md>), [ai safety](<https://devfeed.tech/topics/ai-safety.md>), [Google](<https://devfeed.tech/topics/google.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-age-verification-chatbots](<https://devfeed.tech/tags/ai-age-verification-chatbots.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [ai-harm-to-children-risks](<https://devfeed.tech/tags/ai-harm-to-children-risks.md>), [ai-safety](<https://devfeed.tech/tags/ai-safety.md>), [children](<https://devfeed.tech/tags/children.md>), [cognitive-offloading-ai-kids](<https://devfeed.tech/tags/cognitive-offloading-ai-kids.md>), [development](<https://devfeed.tech/tags/development.md>), [google](<https://devfeed.tech/tags/google.md>), [google-ai-overviews-toggle-kids](<https://devfeed.tech/tags/google-ai-overviews-toggle-kids.md>), [safety](<https://devfeed.tech/tags/safety.md>), [standards](<https://devfeed.tech/tags/standards.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [tech](<https://devfeed.tech/tags/tech.md>), [tech-industry](<https://devfeed.tech/tags/tech-industry.md>), [technology](<https://devfeed.tech/tags/technology.md>), [technology-tech](<https://devfeed.tech/tags/technology-tech.md>), [tom-siegel-ai-safety-warning](<https://devfeed.tech/tags/tom-siegel-ai-safety-warning.md>), [youth-ai-safety-institute-common-sense-media](<https://devfeed.tech/tags/youth-ai-safety-institute-common-sense-media.md>)

### AI overview

A former Google trust and safety leader warns that AI could pose greater risks to children than social media. He calls for a slowdown in AI development, stronger external oversight, and accountability standards, arguing that companies are deploying features for children without sufficient safeguards.

### Source excerpt

Siegel's concerns mirror a growing fear among some tech insiders and academic researchers that AI poses a deeper threat to children than social media did.

## Day 93: the lch() color function

DevFeed: [Day 93: the lch() color function](<https://devfeed.tech/articles/day-93-the-lch-color-function-52289.md>)

Original publisher: [Read original article](<https://www.matuzo.at/blog/2023/100daysof-day93>)

Author: Manuel Matuzović

Published: 2023-02-01T00:00:00Z

Content type: tutorial

Language: en

Sources: [Manuel Matuzović](<https://devfeed.tech/sources/manuel-matuzovic-blog.md>)

Topics: [CSS](<https://devfeed.tech/topics/css.md>), [Web Development](<https://devfeed.tech/topics/web-development.md>), [color](<https://devfeed.tech/topics/color.md>)

Tags: [background](<https://devfeed.tech/tags/background.md>), [color](<https://devfeed.tech/tags/color.md>), [css](<https://devfeed.tech/tags/css.md>), [edge](<https://devfeed.tech/tags/edge.md>), [function](<https://devfeed.tech/tags/function.md>), [lch](<https://devfeed.tech/tags/lch.md>), [modern](<https://devfeed.tech/tags/modern.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [values](<https://devfeed.tech/tags/values.md>)

### AI overview

A tutorial explaining the CSS lch() color function, including its use of the CIELAB color space, lightness, chroma, and hue values, with examples and a note about browser support.

### Source excerpt

The lch() color function allows you to pick colors from the CIELAB color space, which is device-independant and covers the entire gamut (range) of human color perception. Currently, the CSS colors we can define are in the sRGB color space. For the longest time, professional monitors weren't able to display all possible colors in this range. So, using sRGB colors was absolutely sufficient, but that's not true anymore. Nowadays, monitors can display much more colors than exist in the sRGB color space. With lch() we get access to these colors (currently Safari 15+ only). The function takes 3 space-separated values. div { background-color: lch(78% 172.33 248.2); } l - lightness The first value defines the lightness. It's typically a number between 0% (representing black) and 100% (representing white). It's typically a number between 0% and 100% because the value can exceed 100% up to 400% representing extra-bright whites on some systems. It's the same lightness as in the lab() color function. div { background-color: lch(0% 0 0); } c - chroma The second argument is the chroma (roughly representing the "amount of color"). Its a value between 0 and 230. div { background-color: lch(100% 180 0) } h - hue The third argument is the hue angle. 0deg points along the positive "a" axis (toward purplish red). 90deg points along the positive "b" axis (toward mustard yellow), 180deg points along the negative "a" axis (toward greenish cyan), and 270deg points along the negative "b" axis (toward sky blue). div { background-color: lch(100% 180 90); } My blog doesn't support comments yet, but you can reply via blog@matuzo.at.

## Creating a Custom Logger for Craft CMS

DevFeed: [Creating a Custom Logger for Craft CMS](<https://devfeed.tech/articles/creating-a-custom-logger-for-craft-cms-31252.md>)

Original publisher: [Read original article](<https://nystudio107.com/blog/creating-a-custom-logger-for-craft-cms>)

Author: andrew@nystudio107.com (Andrew Welch)

Published: 2019-07-21T17:52:00Z

Content type: tutorial

Language: en

Sources: [nystudio107](<https://devfeed.tech/sources/nystudio107-articles-on-modern-web-development.md>)

Topics: [Content Management System](<https://devfeed.tech/topics/cms.md>), [Logging](<https://devfeed.tech/topics/logging.md>), [configuration](<https://devfeed.tech/topics/configuration.md>), [Dependency injection](<https://devfeed.tech/topics/dependency-injection.md>), [Software as a service](<https://devfeed.tech/topics/saas.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [built-in](<https://devfeed.tech/tags/built-in.md>), [cms](<https://devfeed.tech/tags/cms.md>), [code](<https://devfeed.tech/tags/code.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [craft](<https://devfeed.tech/tags/craft.md>), [custom](<https://devfeed.tech/tags/custom.md>), [dependency-injection](<https://devfeed.tech/tags/dependency-injection.md>), [insights](<https://devfeed.tech/tags/insights.md>), [logger](<https://devfeed.tech/tags/logger.md>), [logging](<https://devfeed.tech/tags/logging.md>), [logs](<https://devfeed.tech/tags/logs.md>), [need](<https://devfeed.tech/tags/need.md>), [needs](<https://devfeed.tech/tags/needs.md>), [saas](<https://devfeed.tech/tags/saas.md>), [send](<https://devfeed.tech/tags/send.md>), [service](<https://devfeed.tech/tags/service.md>), [sufficient](<https://devfeed.tech/tags/sufficient.md>), [third-party](<https://devfeed.tech/tags/third-party.md>), [want](<https://devfeed.tech/tags/want.md>)

### AI overview

A tutorial on customizing Craft CMS logging through Yii-based configuration and code, including changing built-in behavior and sending logs to third-party aggregation services such as PaperTrail or Sentry.

### Source excerpt

The built-in Craft CMS logging system is sufficient for most needs, but what if you need custom logging, or want to send your logs to a third-party service?