arXiv subjects

Yegor Denisov-Blanch

Publications and source records attributed to Yegor Denisov-Blanch.

8 recordsLinked to original sources

arXiv2026

A Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-Agent Adoption

Coding agents increase development velocity but also technical debt. Prior work reports only average effects across adopters, hiding wide differences between teams. We introduce RAMP (Repository AI Maturity Profile), a four-level cumulative maturity model grounded in version-controlled artifacts that teams commit to configure AI tools. RAMP runs from behavioral rules and coding standards through named agent definitions to multi-agent orchestration, with observed practice concentrated in the first three levels. Across 441 repositories the levels behave as a cumulative scale, and independent human annotation reproduces RAMP's repository-level labels on 97% of a held-out sample. Adoption is cumulative, forward-only, and set-and-forget: 73.8% of artifacts are committed once and never modified. Re-estimating an existing agent-adoption panel within each stratum, agents accelerate development regardless of maturity (28-38% more commits), but quality diverges: among agent-first repositories, where the contrast is identified, those without committed AI configuration show roughly twice the increase in cognitive complexity (+53% versus +27%) and 1.7x the increase in static-analysis warnings. Because maturity is observational, correlated engineering discipline or model capability may explain part of the gap; we present these findings as hypothesis-generating and release RAMP as a reusable instrument.

cs.SE↗

arXiv2026

AI Writes Faster Than Humans Can Review: A Longitudinal Study of an Enterprise 2x Mandate

Enterprises increasingly mandate AI coding tools and report large productivity gains, yet longitudinal evidence on how such a mandate unfolds is scarce. In this paper, we present a quantitative case study of a documented enterprise "2x" mandate at a mid-sized, AI-forward company that has been committed to doubling merged pull requests per engineer since mid-2025. In a panel of 802 developers and 196,212 pull requests (January 2024-April 2026), per-capita throughput eventually doubled, reaching 2.09x the pre-mandate baseline in April 2026, among the largest gains reported from a field deployment of AI coding tools to our knowledge. A staggered difference-in-differences design links the within-developer share of this gain to AI adoption and to a further gain that grows with accumulated use, with the mandate acting as a catalyst rather than a direct driver. Because adoption and usage intensity were not randomly assigned, we read this evidence as strongly implicating an adoption-and-use channel rather than as exact causal attribution. The gain is broadly shared across seniority yet concentrated in newer code and not separable across model generations. Adoption also restructured code review around automation: per-reviewer load roughly doubled and automated review overtook human review, while merge and revert rates held steady.

cs.SE↗

arXiv2026

Internal Data Repetition Destroys Language Models

Language models are running out of high-quality training data, and even aggressively deduplicated corpora retain some amount of repetition. Earlier controlled studies predated Chinchilla-style scaling laws and could only measure the cost of repetition indirectly. We revisit repetition in the Chinchilla era, using a fitted no-repetition scaling law to report Compute-Equivalent Gain and Compute-Equivalent Loss. We show that under this modernized paradigm, repetition damage is systematic in three ways. First, holding compute allocated to repeated data constant, eval loss peaks at an intermediate repeat count $\Rep$; repeating a moderately sized subset a moderate number of times damages performance more than repeating a large subset a few times or a small subset many times. Second, the location of this peak is well-fit by a power law in model size; this scaling law reveals that the most damaging number of repeated data grows more quickly than compute. Finally, when repeated documents consume 10\% of the FLOPs budget in a controlled exact-document repetition setting, the compute-equivalent loss can be large: on FineWeb-Edu-Dedup, the most damaging repeat count for a Qwen3-style 344M-parameter model at $\OT=1$ matches the loss of a no-repetition run using 67% of the FLOPs. We demonstrate that these phenomena are not language-model-specific, and can be analytically understood in a simple statistical model: a misspecified linear regression with verbatim duplicates reproduces the same qualitative loss peak, quantifying how such peaks can arise from a statistical tradeoff between memorization and generalization. Our findings add precision to the study of duplication in language models, allowing practitioners to quantify the wasted compute incurred by the presence and repeat structure of duplicates in pretraining corpora.

cs.LG↗

arXiv2026

Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness

Pass@k and other methods of scaling inference compute can improve language model performance in domains with external verifiers, including mathematics and code, where incorrect candidates can be filtered reliably. This raises a natural question: can we similarly scale compute to elicit gains in truthfulness for domains without convenient verification? We show that across five benchmarks and models, surprisingly, it cannot. Even at 25x the inference cost of naive sampling, polling-style aggregation yields no consistent accuracy gains over single-sample baselines and often amplifies shared misconceptions. We find that under uncertainty, models are better at predicting what other models will say within model ensembles than at identifying what is true, revealing a separation between social prediction and truth verification. Across models and benchmarks, aggregation fails to provide a robust truth signal because language model errors are strongly correlated. The source of correlation goes beyond any individual benchmark: we show that even when conditioned on out of distribution random strings and asked to produce pseudo-random outputs, different models produce correlated outputs. Confidence-based weighting provides no benefit because self-reported confidence fails to reliably distinguish correct from incorrect answers. These results delineate a boundary for inference-time scaling: in verified domains, additional samples provide more candidates for a verifier to filter; in unverified domains, additional samples merely reinforce shared misconceptions.

cs.LG↗

arXiv2025

Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track

Science progresses by iteratively advancing and correcting humanity's understanding of the world. In machine learning (ML) research, rapid advancements have led to an explosion of publications, but have also led to misleading, incorrect, flawed or perhaps even fraudulent studies being accepted and sometimes highlighted at ML conferences due to the fallibility of peer review. While such mistakes are understandable, ML conferences do not offer robust processes to help the field systematically correct when such errors are made. This position paper argues that ML conferences should establish a dedicated "Refutations and Critiques" (R&C) Track. This R&C Track would provide a high-profile, reputable platform to support vital research that critically challenges prior research, thereby fostering a dynamic self-correcting research ecosystem. We discuss key considerations including track design, review principles, potential pitfalls, and provide an illustrative example submission concerning a recent ICLR 2025 Oral. We conclude that ML conferences should create official, reputable mechanisms to help ML research self-correct.

cs.LG↗

arXiv2025

Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models

Sampling from language models impacts the quality and diversity of outputs, affecting both research and real-world applications. Recently, Nguyen et al. 2024's "Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs" introduced a new sampler called min-p, claiming it achieves superior quality and diversity over established samplers such as basic, top-k, and top-p sampling. The significance of these claims was underscored by the paper's recognition as the 18th highest-scoring submission to ICLR 2025 and selection for an Oral presentation. This paper conducts a comprehensive re-examination of the evidence supporting min-p and reaches different conclusions from the original paper's four lines of evidence. First, the original paper's human evaluations omitted data, conducted statistical tests incorrectly, and described qualitative feedback inaccurately; our reanalysis demonstrates min-p did not outperform baselines in quality, diversity, or a trade-off between quality and diversity; in response to our findings, the authors of the original paper conducted a new human evaluation using a different implementation, task, and rubric that nevertheless provides further evidence min-p does not improve over baselines. Second, comprehensively sweeping the original paper's NLP benchmarks reveals min-p does not surpass baselines when controlling for the number of hyperparameters. Third, the original paper's LLM-as-a-Judge evaluations lack methodological clarity and appear inconsistently reported. Fourth, community adoption claims (49k GitHub repositories, 1.1M GitHub stars) were found to be unsubstantiated, leading to their removal; the revised adoption claim remains misleading. We conclude that evidence presented in the original paper fails to support claims that min-p improves quality, diversity, or a trade-off between quality and diversity.

cs.CL↗

arXiv2025

Measuring Determinism in Large Language Models for Software Code Review

Large Language Models (LLMs) promise to streamline software code reviews, but their ability to produce consistent assessments remains an open question. In this study, we tested four leading LLMs -- GPT-4o mini, GPT-4o, Claude 3.5 Sonnet, and LLaMA 3.2 90B Vision -- on 70 Java commits from both private and public repositories. By setting each model's temperature to zero, clearing context, and repeating the exact same prompts five times, we measured how consistently each model generated code-review assessments. Our results reveal that even with temperature minimized, LLM responses varied to different degrees. These findings highlight a consideration about the inherently limited consistency (test-retest reliability) of LLMs -- even when the temperature is set to zero -- and the need for caution when using LLM-generated code reviews to make real-world decisions.

cs.SE↗

arXiv2024

Predicting Expert Evaluations in Software Code Reviews

Manual code reviews are an essential but time-consuming part of software development, often leading reviewers to prioritize technical issues while skipping valuable assessments. This paper presents an algorithmic model that automates aspects of code review typically avoided due to their complexity or subjectivity, such as assessing coding time, implementation time, and code complexity. Instead of replacing manual reviews, our model adds insights that help reviewers focus on more impactful tasks. Calibrated using expert evaluations, the model predicts key metrics from code commits with strong correlations to human judgments (r = 0.82 for coding time, r = 0.86 for implementation time). By automating these assessments, we reduce the burden on human reviewers and ensure consistent analysis of time-consuming areas, offering a scalable solution alongside manual reviews. This research shows how automated tools can enhance code reviews by addressing overlooked tasks, supporting data-driven decisions and improving the review process.

cs.SE↗