Research

• Databases11+175.0%
• DevOps & cloud16+100.0%
• Linear bandits119+56.6%
• Federated learning44+41.9%
• Speech emotion17+41.7%
• Diffusion priors25+38.9%
• Small LLMs53+29.3%
• Algorithmic trading27+28.6%

• Dynamic model and policy routing for general-purpose AI1 paper raises it · 1 addresses it

  Balancing performance and computational cost across diverse tasks and modalities is critical for scalable AI systems.

  • Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systemsraises · addresses
• Cross-repository consistency in coding agents1 paper raises it · 1 addresses it

  Real-world software development often requires coordinated changes across interdependent repositories, which current agents struggle to handle.

  • CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agentsraises · addresses
• Efficient long-video generation with consistent quality1 paper raises it · 1 addresses it

  Real-time long-video generation demands continuous output without quality degradation or camera drift, which current methods fail to achieve efficiently.

  • Wave Forcing: Towards Speed-of-Light Streaming Video Generationraises · addresses
• Local decision-making for reasoning compression1 paper raises it · 1 addresses it

  Reducing inference costs without sacrificing accuracy requires models to know when to stop reasoning, not just how to shorten outputs.

  • Think Less, Locally: Local Preference Learning for Reasoning Compressionraises · addresses
• Unified taxonomy and coordination for agentic systems1 paper raises it · 1 addresses it

  Fragmented terminology and rapid growth in agentic systems hinder systematic understanding and coordination across tasks.

  • Advances in Agentic Computer Graphicsraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.CLOct 3

  Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents

  Peigui Qi, Kunsheng Tang, Yide Song, Weiming Zhang, Nenghai Yu

  Large language models (LLMs) increasingly serve as autonomous agents that invoke external tools. However, this capability introduces tool hallucination, selecting incorrect tools or generating invalid calls. Existing mitigation methods report substantial improvements, yet we identify a previously overlooked failure mode that we term Hallucination Escape. These methods reduce hallucination on the tool configuration they are tuned on but increase it on other configurations, canceling out the gain. We further investigate this phenomenon and find that hallucination rises sharply when a model's intrinsic tool-use tendencies conflict with the current tool configuration, and that existing methods reinforce rather than suppress these tendencies, which in turn contributes to hallucination escape. Building on these findings, we propose EscapeGuard, a training-free inference-time method that combines conflict-aware gating with configuration-derived attention enhancement to mitigate tool hallucination while preventing hallucination escape. Across six benchmarks on various models, EscapeGuard reduces tool-selection hallucination by 9.0 pp and suppresses hallucination escape, lowering the…

  PDF

  Summarize this
• arXiv cs.AIOct 3

  TimeNet: An Extensible Unified Data Infrastructure for Next-Generation Temporal Foundation Models

  Martin Maritsch, Timo Stoffregen, Thomas Kaar, Behsad Riemer, Maxwell A. Xu +34

  Temporal Foundation Models (TFMs) aim to generalize across domains, datasets, and tasks. Yet, their development remains constrained by fragmented, task-specific data formats, annotations, and processing pipelines. We introduce TimeNet, an open-source data standard and scalable infrastructure that decouples temporal data from task definitions and represents signals, metadata, annotations, and supervision in a shared, extensible data model. TimeNet supports multimodal signals with regular, irregular, or ordinal time axes and expresses different task families (including classification, forecasting, temporal localization, question answering, generation, and editing) as reusable views over the same recordings. This shared representation enables heterogeneous time-series datasets to be combined for large-scale model training across domains, modalities, and tasks. We demonstrate TimeNet by transcoding datasets with 1.5M task instances spanning diverse domains, modalities, temporal scales, and forms of supervision, while retaining practical I/O performance relative to native formats. TimeNet enables an existing TFN training pipeline to support joint training on a configurable number of…

  PDF

  Summarize this
• arXiv cs.LGOct 3

  CEENs: Causality-enforced evolutional networks for solving time-dependent partial differential equations

  Jeahan Jung, Heechang Kim, Hyomin Shin, Minseok Choi

  Despite the growing popularity of physics-informed neural networks (PINNs), their applicability in the long-time integration of partial differential equations (PDEs) remains constrained. We argue that this problem stems from the lack of consideration of temporal causality in the original PINN formulation, resulting in a bias towards satisfying governing equations at later times before learning the initial condition and hence leading to erroneous solutions. To this end, we propose a novel method that seamlessly integrates temporal causality into the training process. Drawing inspiration from classical numerical methods where the temporal causality is reflected, we divide the time domain into nonoverlapping subintervals, assign a unique neural network to each subinterval, and construct a loss function founded on the integral form of PDEs within these subintervals. The proposed networks undergo sequential training, beginning with the initial time step. Our method demonstrates significant improvement in accuracy for long-time simulations of various PDE problems where the original PINN method fails while it requires less computational cost and memory compared to the PINN method. A…

  PDF

  Summarize this
• arXiv cs.CLOct 3

  Saying, Not Knowing: Aggressively GGUF-Quantized Small Language Models Still Write Rare Words They Can No Longer Define

  Saurabh Kumar Singh, Yogeshwar Singh Dadwhal, Malhar Vedak

  Post-training quantization to the GGUF format's mixed-precision K-quants is commonly how open-weight language models reach consumer hardware, yet its effect on fine-grained lexical competence is uncharacterized. We audit 27 quantized artifacts across 13 families and four architecture backbones, 0.35B-14B parameters, evaluated down their published ladder to Q2_K (about 2.6 bits per weight), on 429 frequency-validated rare English words under two probes: surface inclusion of a prompt-supplied word and its one-sentence definition, scored by a tiered multi-synonym matcher, its error measured by a blind LLM-judge census of every definition, with human verification. Three regimes emerge at Q2: total collapse into unusable builds, severe semantic dissociation in sub-2B models, and mostly robust preservation above about 3B. In every sub-2B artifact, definitions fall 20-67% below the artifact's baseline, typically several times the inclusion loss. Two controls separate rarity from task difficulty: within the rare set, loss rises with rarity in six of seven sub-2B artifacts, and on a 100-word common-word set rare words lose more than common words in all eight, significantly in six.…

  PDF

  Summarize this
• arXiv cs.CLOct 3

  Ideological Stance Detection in a Low-Resource Language: Polarization in Bangladeshi Public vs Private University Discourse on Social Media

  Safaruzzaman Shovo, Monowar Islam, Asif Hossain, Sameya Akhter, Md. Shamsul Islam

  Public vs. private universities is a debatable issue, and it creates polarization on social media in Bangladesh. Debate on quality, jobs, and prestige is passionate among the students, parents, and graduates, the majority of whom speak Bengali, a low-resource language. To measure this polarization, this paper introduces a manually annotated dataset of 4,060 Bengali comments labeled as Pro-Public, Pro-Private, or Neutral. We evaluated the quality of our annotations by Fleiss's Kappa agreement that was 0.89, corresponding to a high agreement among annotators. The classical ML (SVM, Random Forest, XGBoost), BiLSTM network, hybrid BanglaBERT+XGBoost models and the state-of-the-art zero-shot LLMs (Claude Sonnet 4, DeepSeek-V3.1, Llama 4 Maverick, Kimi K2 Thinking, Qwen3-235B Thinking) models are evaluated. The accuracy of BanglaBERT+XGBoost is 91.81% and macro F1 score is 91.70%, which is higher than all the supervised baselines. The zero-shot Llama 4 Maverick Thinking achieves a macro F1 of 0.931 (overall accuracy of 93.31%) without any fine-tuning. All machine learning (ML), deep machine learning (DL) and transformer models were outperformed by the zero-shot Llama 4 Maverick model.…

  PDF

  Summarize this
• arXiv cs.CLOct 3

  XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions

  Zhanxun Liu, Yifan Duan, Hengtao Wu, Chen Yang, Qinyuan Cheng +5

  General turn-taking behavior in real-time dialogue systems requires deciding whether to keep listening or start responding while listening, and whether to continue or stop while speaking. Existing turn detectors use heterogeneous, task-specific label spaces and are often trained on limited annotations or evaluated on isolated utterances, making them difficult to use as a unified causal controller with comprehensive context. We propose XTurnix, a compact text-based model that formulates turn control as two binary decisions conditioned on the AI's current listening or speaking state and predicts a single control token from the complete dialogue history. XTurnix is pretrained on 5.5 million causal action examples automatically derived from timestamped two-speaker transcripts, then fine-tuned on synthetic multi-turn examples with a flatter distribution across the four state-action labels. We evaluate XTurnix on four public benchmarks and a balanced self-curated benchmark. Across the public benchmarks, XTurnix achieves the best results on all SemanticVAD and LiveKit splits, ties the native Smart-Turn model on Smart-Turn Bench, and achieves the highest incomplete-turn accuracy on…

  PDF

  Summarize this
• arXiv cs.CLOct 3

  GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization

  Kunsheng Tang, Peigui Qi, Yide Song, Peijun Huang, Weiming Zhang +1

  Glitch tokens are anomalous vocabulary entries that can cause large language models (LLMs) to produce outputs inconsistent with their inputs. Existing repair methods require access to model internals, making them impractical for frozen checkpoints. We investigate whether glitch tokens can be repaired outside the model by optimizing the input tokenization. An empirical study on BPE merge-rule deletion reveals that (1)deleting a glitch token's merge rule can fix a substantial fraction of failures, yet disrupting normal tokens sharing intermediate merge nodes causes the overall glitch rate to rise, and (2)different decomposition granularities yield non-monotonic fix rates while collateral damage on normal tokens grows monotonically. Motivated by these findings, we propose GlitchPatch, a repair framework for frozen language models based on local retokenization, consisting of two stages: the offline stage uses Behavioral Path Optimization (BPO) to find the behaviorally optimal replacement token sequence for each glitch token and compiles validated replacements into a rule table; the online stage substitutes only the IDs of matched glitch tokens in the canonical token sequence, with no…

  PDF

  Summarize this
• arXiv cs.CROct 3

  JASPER: Special Session on Joint Reliability And Security Assessment of SPlit Computing for Edge Robustness

  Enrico Magliano, Giuseppe Esposito, Amir Hossein Shahdadian, Rama Mounika Kodamanchili, Juan David Guerrero Balaguera +11

  Split Computing (SC) enables efficient deployment of Deep Neural Networks (DNNs) by partitioning inference between edge devices and cloud servers. However, intermediate feature representations are simultaneously exposed to hardware faults and adversarial attacks, which are traditionally evaluated independently. This paper presents a unified framework for the joint assessment of reliability and security in Split Computing. First, reliability is characterized through neuron-level fault injection using the Mean Relative Accuracy Degradation (MRAD) while security through feature-map-aware adversarial attacks simulations using the Attack Success Rate (ASR). Based on these complementary analyses, the Joint Vulnerability Score (JVS) is introduced, along with a confidence-aware extension that jointly captures prediction errors and confidence degradation. The framework is evaluated on ten Split Computing configurations based on ResNet-50 trained on ILSVRC-2012. Experimental results show substantial differences across compression strategies, with MRAD ranging from 44.3% to 61.2% under fault injection, while adversarial attacks achieve up to 98.8% ASR. Furthermore, the proposed joint…

  AI20PDF

  Summarize this
• arXiv cs.CVOct 3

  Detecting Defects that Matter: An Application-Driven Benchmark for Anomaly Detection in Manufacturing and Retail Logistics (VAND 4.0 Challenge)

  Lars Heckler-Kram, Dorian Henning, Ashwin Vaidya, Jan-Hendrik Neudeck, Ulla Scheler +4

  Existing Anomaly Detection benchmarks are saturated and often unrealistic. As part of the VAND 4.0 Challenge, we introduce a hidden-test, application-driven benchmark across two deployment-critical domains: industrial manufacturing and retail logistics. In the Industrial Track (MVTec AD 2), the results reveal that unsupervised anomaly segmentation remains challenging: the best regular-setting method achieves only ~57\% pixel-level $SegF_1$, indicating substantial room for improvement. Zero-shot approaches trail by ~15 $SegF_1$ points, confirming that task-specific training on normal data remains essential for precise defect localization. Robustness to distribution shifts remains a key open challenge and DINOv3-backbones clearly dominate this track. In the Retail Track (Kaputt 2), the results reveal that (1) supervised defect detection is approaching saturation for common defect types; (2) the best off-the-shelf VLM approach trails specialized models by ~28 AP, confirming that currently VLMs cannot replace fine-tuned detectors, (3) reference images did not prove helpful for top-performing approaches. Performance collapses on rare defects (spillage ~53 AP, missing units ~27 AP),…

  PDF

  Summarize this
• arXiv stat.MLOct 3

  Gaussian Flow Dynamics: Simulation-Free Neural SDE Learning Beyond One-Time Marginals

  Grigory Bartosh, Christian A. Naesseth

  Simulation-free training of latent Stochastic Differential Equations (SDEs) relies on a variational posterior process whose one-time marginals are tractable, typically Gaussian. Such marginals, however, do not determine the underlying dynamics: many processes share the same marginals while differing in their temporal structure, and existing parameterizations fix this structure implicitly, which restricts the posterior family and biases the learned model. We introduce Gaussian flow dynamics, which construct stochastic processes directly from smoothly evolving Gaussian marginals while making the marginal-preserving, or gauge, degrees of freedom explicit and parameterizable. The construction admits state-dependent diffusion coefficients and recovers every linear SDE with additive noise and a non-degenerate Gaussian initial distribution. Building on it, we propose Gauge Matching, a simulation-free method for latent SDE learning that combines Gaussian flow dynamics with the SDE Matching objective. Gauge Matching costs at most quadratically in the latent dimension per step, like SDE Matching, but learns the temporal structure of the posterior beyond its one-time marginals. It comes…

  PDF

  Summarize this
• arXiv cs.LGOct 3

  Learning to Remember: Distilling Memory Retention for Compact Recurrent Neural Networks

  Nilushika Udayangania, Kishor Nandakishora, Marimuthu Palaniswami

  Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series analysis. These models capture complex, sequential patterns in time series, enabling real-time assessments. However, their high computational complexity and large model sizes pose challenges for deployment in resource-constrained environments, such as wearable devices and edge computing platforms. Knowledge Distillation (KD) offers a solution by transferring knowledge from a large, complex model (teacher) to a smaller, more efficient model (student), thereby retaining high performance while reducing computational demands. Current KD methods, originally designed for computer vision tasks, neglect the unique temporal dependencies and memory retention characteristics of time series models. To bridge this gap, we propose a novel KD framework termed Memory-Discrepancy Knowledge Distillation (MemKD). MemKD leverages a specialized loss function to capture memory retention discrepancies between the teacher and student models across subsequences within time series data, ensuring that the student model effectively mimics the teacher's…

  PDF

  Summarize this
• arXiv cs.AIOct 3

  TrustMed-RL: Long-Horizon Reinforcement Learning for Evidence-Grounded Clinical Diagnosis

  Wenxin Zhan, Yizheng Jiao, Haifeng Song, Shuai Xu, Chencheng Pan +2

  Medical language models can produce correct diagnoses despite incomplete investigations and unsupported reasoning. To support long-horizon, evidence-grounded diagnosis, we introduce \textbf{TrustMed-RL}. Built from PubMed rare-disease cases and over 24,000 manually annotated image panels, it integrates interviews, examinations, testing, specialist consultation, and literature search through state-dependent actions. Our 8B vision--language policy, trained with clinically adapted GiGPO and coverage-adjusted diagnostic rewards, achieves 37.1\% diagnostic accuracy on 2,500 evaluation cases, outperforming all evaluated open-weight baselines and improving over supervised fine-tuning by 12.4 percentage points.. When success additionally requires acquiring at least 50\% of supporting test evidence, TrustMed-RL achieves 32.5\%, exceeding GPT-4o by 6.8 percentage points. Furthermore, it surpasses all evaluated baselines on MTMedDialog and multiple larger 27--32B models on AgentClinic. In physician review of 200 diagnostically accepted test-set trajectories, 83.0\% receive evidential-grounding scores of 4--5 out of 5. Physicians' assessments suggest that these diagnostic trajectories are…

  PDF

  Summarize this
• arXiv math.OCOct 3

  Largest Rashomon sets of decision trees for robust contextual optimization

  Lorenzo Bonasera, David Pisinger

  Many decision trees fit the same data almost equally well, yet they can route a query point to different leaves and induce different local empirical distributions. We study decisions that meet prescribed cost, shortage or risk targets despite this predictive multiplicity. We propose the joint Rashomon and robustness optimization framework for optimal decision trees. It jointly selects an operational decision and the largest Rashomon set of trees, so that the targets hold under the local empirical distribution that every tree in this set induces at the query point. We specialize the framework to the regression setting, and we show that a tree affects the decision only through the training observations sharing the query leaf, which we call its query neighborhood. As a result, the robust problem involves only finitely many distinct constraints, which can be examined in order of increasing estimation loss. We develop a constraint generation algorithm that combines query-path pricing with dynamic programming to identify violating neighborhoods without enumerating trees. On synthetic newsvendor instances, the algorithm typically needs few neighborhoods and runs substantially faster…

  PDF

  Summarize this
• arXiv cs.CVOct 3

  Beyond Plausibility: Verifiable Fine-Grained Image Editing on Structured Assets

  Muyao Wang, Chen Zhu, Shiqi Yang, DongHyun Hwan, Hideki Nakayama

  Fine-grained image editing requires more than producing a visually plausible result: an editor must execute the requested attribute change precisely while leaving everything else intact. However, existing benchmarks leave a critical gap between realism and verifiability: benchmarks built on realistic images typically rely on human or vision--language model judgments, while deterministic evaluation has largely focused on synthetic shape canvases, with application-oriented extensions primarily limited to charts. This makes it difficult to determine precisely how much of a requested edit was executed, where unintended changes occurred, and whether small differences between models reflect genuine editing capability or evaluator uncertainty. To bridge this gap, we present VeriEdit-Bench, a benchmark for fine-grained, instruction-faithful image editing across realistic structured assets with deterministic, four-axis evaluation. Its 1,740 cases are compiled from the source code of 153 Scalable Vector Graphics (SVG) graphics, charts, web interfaces, and presentation slides. Controlled source-code edits preserve the original visual context while yielding exact target images, pixel-level…

  PDF

  Summarize this
• arXiv cs.AIOct 3

  AgentPersonaBench: Benchmarking Persona-Driven User Simulation

  Jintao Huang, Yifan Wang, Hongyu Shen, Yi Daniel Lu, Shirley Huang +41

  We introduce AgentPersonaBench (APB), a benchmark evaluating whether persona conditioning faithfully steers downstream agent behavior. While language models are increasingly deployed for persona-driven user simulation, existing benchmarks primarily evaluate conversational styling or self-reports rather than authentic behavioral fidelity. APB evaluates latent persona adherence one trait at a time, embedding each target trait within a complete synthetic profile without explicitly naming the trait or disclosing the test. Ground-truth adherence is verified strictly from observable actions across four interaction surfaces of increasing realism: survey, chat, web (interactive web environments), and app (desktop software environments). APB comprises 2,460 tasks spanning 867 traits, verified through automated audits and expert review. Our evaluation of 20 frontier model arms demonstrates that high-fidelity user simulation is already attainable: leading models achieve up to 84.7% full-pass adherence under unprompted conditions. At the same time, APB identifies clear behavioral boundaries: adherence drops across interaction modalities (only 37.9-64.3% pass all four surfaces),…

  PDF

  Summarize this
• arXiv cs.CROct 3

  COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol Layers

  Nahom Birhan, Mehrdad Rostamzadeh, Sidhant Narula, Mahmoud Nazzal, Mohammad Ghasemigol +1

  Large language models increasingly mediate tool use in Model Context Protocol (MCP) systems, where adversarial influence may enter through user instructions, tool schemas, tool outputs, or protocol messages. Existing benchmarks often evaluate deployed agents, conflating model susceptibility with guardrails, orchestration, and general task capability. We introduce COPEX (COntext Provider EXploitation), a controlled benchmark that isolates the model as an MCP client by fixing the surrounding agent stack and varying only the tool-selecting model. COPEX covers 25 attack types instantiated as 125 scenarios across four entry surfaces: model/agent, client, server/tool, and transport. Across nine models and 3,375 trials, the mean attack success rate is 64.4%, with surface-level means ranging from 58.3% to 71.4%. Some client- and transport-level attacks succeed partly outside the model's observation or control, separating system exposure from model susceptibility. Combined input and context scanning reduces mean attack success by 49.6% on an eight-attack defense subset relative to the undefended setting. The benchmark is available at https://github.com/inspire-center/copex.

  PDF

  Summarize this
• arXiv cs.AIOct 3

  Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents

  Boyang Yang, Zhenhao Li, Ziyao Yang, Kanghui Jia, Xin Yin +2

  Agents built on large language models (LLMs) build and run software through tool calls. A call reaches its program through several hops, and any hop can change the call without notice. When the changed call fails, the agent retries a correct call, which costs users time and money. Benchmarks and failure analyses do not see the change, because they read the call and its result but not what a hop received. We define intent-execution correspondence (IEC) as the property that the executed action matches the action the emitted call denotes under the tool contract. Our protocol observes what each hop received without executing the call, and names the first hop that changed it by the receiver's own parser. IntAct then delivers the call in a form that this hop cannot alter, or refuses the call. We build IEC-Bench from the changes observed in real-world use, with chains of dependent calls under the execution paths of 4 widely-used harnesses. In 47,828 shell calls within production sessions, Claude Code's Bash tool changes 12.0% of the calls that carry code, escape sequences, or long text. For 80.7% of the calls whose backslashes are changed, the wrong action runs without any reported…

  PDF

  Summarize this
• arXiv cs.ROOct 3

  Frame-Level Temporal Alignment for Human-to-Robot Visual Adaptation

  Xizhe Zhang, Jingfeng Zhang, Zirun Zhou, Hong Jia

  Transferring visual representations pretrained on human videos to robot manipulation requires learning reliable correspondences between human and robot demonstrations. However, paired demonstrations can differ in execution rate and in the proportion of non-key frames that do not directly reflect task progress. Frames at the same relative timestamp may therefore represent different task stages, which can cause correspondence learning to fail. To address these issues, we propose Frame-Level Temporal Alignment (FLTA), a framework that uses two temporal priors to adapt visual encoders pretrained on human videos for robot manipulation. It learns shared task-progress representations without frame-level correspondence annotations, allowing frames at different relative temporal positions to match. A global progress prior combines normalized temporal positions with visual similarity to construct a soft correspondence target. A local temporal order prior penalizes backward transitions while allowing stays and varying forward rates to accommodate execution-rate differences. With ResNet-50 and ViT encoders, our method achieves relative improvements of 46.93% and 65.96%, respectively, over…

  PDF

  Summarize this
• arXiv cs.AIOct 3

  Functionally Equivalent or Not? Graph-Grounded Differential Surrogate Execution for Code Equivalence

  Amit Kachroo, Like Hui, Haitao Mao, Yuhao Zhang, Nguyen Vo

  Determining whether two programs are functionally equivalent is central to code modernization, patch validation, refactoring, and code-generation evaluation. Yet the usual signals are incomplete: tests cover only finite inputs, textual similarity confuses implementation with behavior, and unconstrained LLM judgments are difficult to audit. Direct execution is often impossible when a program depends on an obsolete, licensed, unavailable, or unsafe environment. We introduce FEAgent, a selective equivalence assessor agent that combines typed program-graph evidence with differential surrogate execution. FEAgent first aligns public interfaces and behaviorally relevant graph anchors, then issues bounded queries over call-flow, control-flow, data-flow, type, import, and effect relations. Next, a branch-aware generator agent proposes discriminating inputs, and two blinded LLM surrogates independently predict source and target observables. Every claim and predicted divergence is recorded in an evidence ledger. A deterministic reconciler then returns EQUIVALENT, INEQUIVALENT, or UNCLEAR rather than forcing a verdict when paths are uncovered or evidence conflicts. We evaluate FEAgent on…

  PDF

  Summarize this
• arXiv cs.CLOct 3

  Boundaries Agree, Labels Do Not: Intra-Annotator Dynamics as a Kind of Training Data

  Marharyta Shvets

  Data quality now matters as much as compute for training language models. Much training data comes from human annotation of text, and interpretive annotation has no ground truth that could settle what is "accurate". Two lines of work respond to this. One combines annotators into a "ground truth" and measures how well they agree with each other; the other treats their disagreement as a signal. Both compare different people at one point in time. We measure something else: how well one reader reproduces their own reading of the same text over time. One expert human reader and three LLM families segmented three Sumerian myths and labelled the causal function of each segment with one of seven states. Across runs months apart, the human cut the text in much the same places but named the segments differently, in every myth. The models show no such consistent pattern: their gap between the two layers is positive in some myths and negative in others, and its size varies. The human's label changes are not random: the runs go through much the same functions but start them one step apart, while model runs start them at the same places. We argue that this pattern is a usable measure of data…

  PDF

  Summarize this