Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Wednesday 12 August

Artificial Intelligence

A Hybrid AI Framework for Academic Advising: Integrating Ensemble-Based Grade Prediction and a Rule-Based Expert System

The rapidly increasing student population has posed serious challenges to the traditional academic advising process. This study designs and implements a multi-purpose intelligent system to support students' academic progress, based on a two-part hybrid framework: (1) an advanced model for grade prediction and (2) a rule-based recommendation engine. Using a dataset containing 416,558 educational records from the University of Birjand, students were first divided into homogeneous clusters using the Gaussian Mixture Model (GMM). Subsequently, a Stacking Ensemble model combining Random Forest, Gradient Boosting, and MLP was trained specifically for each cluster. Evaluation results demonstrated that the Stacking model outperformed base models across all clusters, achieving a final aggregated RMSE of 2.35. The second component is an expert system that provides intelligent recommendations by synergizing educational regulations with the grades predicted by the first component. This system has been implemented as a practical tool on the University of Birjand portal, offering students real-time feedback such as semester GPA prediction, probation risk warnings, and course suggestions for GPA improvement.
Read the full abstract

All authors Hamid Saadatfar, Rohollah Hedayati-Nasab, AmirHossein Eshghi, Arash Hajihashemi

Computation and Language

Damage Predicts Recovery: When Calibration Data Matters in Compressing Financial LLMs

Post-training quantization and pruning rely on a small calibration corpus. Whether specialized domains such as finance require domain-matched calibration data remains unsettled. We argue that the answer depends on the task-level damage caused by compression rather than on domain mismatch. If compression preserves the target capability, changing the calibration corpus has little effect. If compression causes large losses, task-formatted calibration can recover part of the loss. We test this hypothesis across two model families, six compression configurations, three token-matched calibration corpora, and ten financial classification and numerical question-answering tasks. The results support this hypothesis. Quantization largely preserves task performance, and calibration choice has little effect in this case. Pruning reduces numerical QA accuracy by over 40 points. In these damaged settings, another generic corpus does not help, while FinMix, a mixture of financial task examples, recovers a large part of the loss. The link between damage and recovery holds across model families and scales. These findings support a practical rule. Measure task-specific compression damage first, and construct specialized calibration data only when the damage is large.
Read the full abstract

All authors Junyi Ye, Mengjia Yu, Debapriya Hazra, Guiling Wang

Information Retrieval

ABAI at COLIEE 2026 Task 1: Multi-Stage Retrieval with GraphRAG-Enhanced Meta-Learning, and a Post-Hoc Study of the Cross-Validation-to-Test Gap

We present the ABAI submission to COLIEE 2026 Task 1, case law retrieval, together with a controlled study of why it underperformed. The task suppresses the cited passages themselves, which removes much of the lexical overlap a retriever would rely on. Our pipeline answers this with four independently trained stages: multi-view BM25 over citation-context windows with reciprocal rank fusion, neural reranking, graph-based features from entity communities and a graph attention network, and a LightGBM meta-learner over 34 features. Our best run reached F1=0.177 on the official test set, against a cross-validated 0.311, and we attributed that gap to a recall ceiling, temporal distribution shift, and threshold miscalibration. We then tested all three. Under leakage-free protocols threshold transfer costs 0.007 F1, decision quality is flat across chronological quartiles, and the official test queries are not measurably farther from the training manifold than training queries are from each other, in two independent embedding spaces. Decomposing the misses instead splits them exactly evenly between candidates never retrieved and candidates retrieved but ranked below the cut. Measuring the remedies for each half, BM25 length-normalisation tuning, an event-triple view, and full-content dense fusion lift top-200 recall by three to seven points, and citation-graph features add 0.014 F1 over eight seeds once own-citation leakage is removed, while per-query cutoff rules, a zero-shot reranker swap, and a date filter do not help. We also document four evaluation artifacts, each of which reversed a result once the protocol was corrected.
Read the full abstract

All authors Minhan Cho, Soyoung Park, Daejin Choi, Jinyoung Han

Cryptography and Security

Towards Effective Black-Box Adversarial Attacks on Deep Code Models via Structural and Identifier Perturbations

Deep code models (DCMs) are increasingly embedded in code intelligence tasks. However, their robustness under adversarial attacks remains insufficiently understood. Prior black-box attacks mainly rely on identifier- only substitutions or structural edits transferred from reference samples, yielding perturbation spaces defined largely independently of the attacked input. We introduce Strike, an input-conditioned black-box adversarial robustness-testing framework that constructs and searches a hierarchical perturbation space for each input. Strike first partitions code into blocks and uses an LLM to generate context-specific structural candidates, filtered for syntactic validity, ranked by similarity, and adaptively combined. It then refines the best structural variant through similarity-guided identifier substitutions drawn from dynamically constructed candidate pools. Evaluations across representative code intelligence tasks, including clone detection, vulnerability detection, and code summarization, demonstrate that Strike achieves higher attack success rates with competitive target- model query overhead. Strategy-specific static checks across all three tasks and execution-based validation on the executable Juliet vulnerability-detection subset provide complementary, task-bounded evidence regarding the validity of the generated variants. Representation similarity and human evaluation further indicate that the variants remain highly similar to the original code and contextually natural. Fine-tuning with Strike- generated samples improves cross-attack performance on fixed perturbed evaluation sets while preserving clean performance.
Read the full abstract

All authors Bin Duan, Jintao Lin, Dan Dongseong Kim, Guowei Yang

Machine Learning

High-Order Liquid Evidence Modeling for Continuous and Subtle GNSS Spoofing Detection in Autonomous Driving

Continuous and subtle GNSS spoofing poses a serious threat to autonomous vehicles because forged positions may remain locally plausible while gradually becoming inconsistent with vehicle motion observed by non-GNSS onboard sensors. Existing AV-oriented detectors commonly rely on residual thresholds or feature-level classification and provide limited modeling of how weak GNSS–motion inconsistency develops and persists over time. This paper formulates subtle GNSS spoofing detection as a causal sequential evidence-modeling problem and proposes a high-order liquid evidence detector. The method first compares the displacement implied by consecutive GNSS positions with that inferred from independent onboard motion observations and converts their difference into uncertainty-normalized residual evidence. It then represents the current inconsistency, its local evolution, excess above the normal level, accumulated persistence, and displacement validity as causal weak evidence. These cues are mapped into instantaneous, evolutionary, and persistent latent states, aligned through a bounded Kirchhoff-inspired symmetric exchange, and combined through an explicit third-order interaction to capture their coordinated support for spoofing. To model how this coordinated evidence develops over time, second-order liquid dynamics track its memory and evolution to estimate causal spoofing probabilities, which are converted into confirmed alarms using validation-selected threshold and persistence parameters. Experiments on the AV–GPS dataset family demonstrate strong controlled and external generalization, together with clear sequential alarm behavior. On Dataset-1, the proposed detector achieves an AUROC of 0.9932 and an AUPRC of 0.9843, while obtaining the lowest false-positive rate among the learning-based baselines. Code: https://github.com/pangjunbiao/HO-LLN-Spoofing.
Read the full abstract

Software Engineering

Reducing Hallucinations in Large Language Models Through Integrated Self-Verification and Retrieval-Augmented Generation

Large Language Models (LLMs) are progressively used for advanced engineering tasks, includes Computer-Aided Design (CAD) documentation, standards compliance verification, and knowledge retrieval. Still, they are prone to produce hallucinations, outputs that seem convincing but aren't based on context that limit their trustworthiness in high-end engineering applications where precision and compliance are crucial. The paper introduces CoVe-RAG+, a unified framework that integrates Chain-of-Verification (CoVe) with Retrieval-Augmented Generation (RAG) to mitigate hallucinations in the results generated by large language models (LLMs). CoVe-RAG+ supports LLM verification in external sources of authority, such as engineering standards, CAD information, and simulation reports, while applying an iterative self-verification process to validate important claims. CoVe-RAG+ is assessed on engineering activities such as CAD model documentation, standards compliance verification, and the reutilization of historical design data. Experimental findings indicate a 28% improvement in factual accuracy relative to baseline CoVe and RAG methodologies. Moreover, CoVe-RAG+ strengthens user confidence by providing elucidative verification reports and source traceability. The findings indicate that CoVe-RAG+ provides a scalable and reliable option for implementing LLMs in engineering design processes where factual accuracy is critical.
Read the full abstract

Computation and Language

Same Chart, Different Story: Bias in Vision-Language Chart Interpretation

Vision-language models (VLMs) are increasingly used to interpret charts and generate natural-language explanations for socially consequential data. However, they may produce different narratives for the same chart when only the referenced social group changes, reinforcing stereotypes and misleading decisions. Despite these risks, no benchmark exists for systematically evaluating bias in chart interpretation across social dimensions. We introduce ChartBias, the first benchmark for auditing bias in VLM-based chart interpretation. ChartBias contains 820 manually curated real-world charts spanning six attributes: race, income, age, religion, immigration status, and gender, yielding 4,319 valid chart, attribute instances and 8,638 paired generations where the chart is fixed and only the group term is swapped. Across 12 proprietary and open-source VLMs, totaling 155,484 model responses, we find three widespread failure modes: narrative shift (same chart, different narratives), group hallucination (assigning a chart to a group without evidence), and preference polarity (favourable trends often linked to one group). We further propose a multi-agent mitigation framework that serves as a strong baseline by separating chart-grounded evidence extraction from group-conditioned generation and using a counterfactual judge to verify that group-driven differences are supported by the chart. The framework substantially reduces narrative shift while preserving chart-grounded reasoning. Our findings show that evaluating chart understanding requires measuring not only accuracy, but also fairness and consistency across social groups. We release ChartBias at https://github.com/vis-nlp/ChartBiasBench.
Read the full abstract

All authors Mizanur Rahman, Huan Wu, Arash Asgari, Enamul Hoque Prince, Laleh Seyyed-Kalantari

Databases

Generating Query Context for Relational Databases

Relational databases are the systems of record for business applications, and there is growing demand to query them through natural language interfaces. A key challenge is that AI models need appropriate query context, i.e., sample questions paired with their corresponding data-model fragments, to generate accurate SQL. Today, creating this context is a manual, time-consuming process that requires expertise in both SQL and the database schema, leading to a cold start problem for new databases and an ongoing maintenance burden as schemas and query patterns evolve. We present an automated approach for generating query context for relational databases. Our method defines query flows that capture common patterns of data retrieval and analysis questions, systematically generates data models by traversing these flows, and instantiates them with specific values sampled from the database using weighted strategies that maximize diversity and coverage. The resulting question–data-model pairs can be used to guide natural language interfaces in accurately querying relational databases. We report on our experience deploying this approach across more than 50 real-world databases connected to Tursio.
Read the full abstract

All authors Alekh Jindal, Jyoti Pandey, Christina Pavlopoulou, Ronith PR, Sharath Prakash, Shi Qiao, Shivani Tripathi, Wangda Zhang

Cryptography and Security

Unread or Unenforced? Separating Representation from Enforcement Failure in Content Guards

When an encoded attack passes a content guard, the guard either never represented the payload's harmful content or represented it and failed to act. End-to-end attack success rate reports one number for both, yet the two have opposite remedies: one is a representational limit that more verdict-level safety training cannot reach, the other is a decision rule that it can. We separate them by reading a guard's own residual stream, using a content probe fitted on plaintext and transferred without refitting to the encoded condition, alongside the verdict logits from the same pass. Licensing that read honestly is most of the problem and is our main contribution. A conventional permutation test admits the decode measurement on most of a 19-condition encoding ladder for each of two open guards. A length-matched null and a floor calibrated on conditions the guard's base model decodes at rate zero reduce it to four conditions each; holding out the items the probe was fitted on removes one more. A further screen constrains the block axis by running plaintext content inside each condition's own wrapper. It removes the largest surviving cell. What remains is a policy failure that survives an item-level holdout on the zero-width encoding for both guards, at 8 and 7 per 100 prompts, against 17 and 23 when the probe is allowed to have seen the prompt it is scoring. It is also confined to one family of surface encodings: where an encoding leaves content linearly recoverable we can separate the two failures, and on genuine ciphers we report the cells as unmeasured rather than as evidence that nothing was decoded. Across every guard and condition pair except two, both unmeasured on the decode axis, blocked without decoding is near zero, so we find little evidence for a pure encoding-format detector under the conditions we test. That cell is the one read we do not repeat under the holdout.
Read the full abstract

All authors Haoyu Zhang, Yi Feng, Shibo Zheng, Hanwen Liu, Haowen Xu, Xiao Luo, Zhuoxi Wang, Mohammad Zandsalimy, Shanu Sushmita

Cryptography and Security

Refusing Everything Looks Safe: Restoring the Benign Arm to Encoded-Prompt Evaluation

Encoded-prompt attacks are evaluated almost entirely on their harmful arm: a benchmark sends obfuscated harmful requests and reports how often the model complied. A high refusal rate there is reported as safety, and it is equally consistent with a model that has stopped telling the request apart from anything else in the same format. We run the benign arm through the same transformation, and the two cases are far apart. Across four 7-8B models spanning three base families and four post-training recipes, refusal of harmful homoglyph-encoded prompts spans 0.08 while the same four span 0.57 on the identical requests in plaintext. What the encoding destroys is not refusal but the harm gap: on one model the gap between harmful and benign refusal falls from +0.82 in plaintext to exactly 0.00 under the encoding, and a benchmark reading only the harmful arm scores that model and one retaining a +0.61 gap identically. Running the cell such benchmarks leave out (plaintext content wearing the attack template, with nothing obfuscated) shows that on two of the four models the loss is caused by the protocol rather than by the character transformation, and on a third by the characters. Across a full SFT -> DPO -> RLVR pipeline the harm gap rises by +0.26 with a paired interval excluding zero while the standard harmful-arm metric registers no resolved change at all. We report twelve instrument defects, each with the control that caught it, including a binary jailbreak judge that fires on 0.61-0.70 of responses to plaintext benign prompts; six of the twelve inflate apparent safety, which is the direction a broken safety evaluation fails in by default.
Read the full abstract

All authors Haoyu Zhang, Haowen Xu, Xiao Luo, Hanwen Liu, Yang Chen, Zijian Xiao, Yi Feng, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita

Cryptography and Security

The Uncontrolled Variable: Vision-Language Refusal Is Conditioned on the Image-Attachment Interface, and Not Robust to Irrelevant Image Properties

We show that aligned vision-language models also condition refusal on a property of a request's form: whether an image is attached, holding everything the request asks fixed. Attaching a blank canvas, an image that cannot be read, cannot relate to the request, and is byte-identical across every prompt in its condition, shifts benign refusal by tens of points. The shift is not blanket caution but a threshold shift: genuinely neutral instructions are almost unaffected (<=2 percentage points on three of four hosted models) while borderline-benign prompts move +23 to +51 points, so the cost falls on sensitivity-adjacent traffic, meaning benign questions about privacy, self-harm, violence and illegal activity. There is a benign reading of such a threshold, namely that attachment correlates with risk in real traffic, and we take it seriously; a black-box study cannot measure that correlation and we do not claim to. What it can test is whether the response to attachment is robust to variation carrying no information about the request, and on four independent measurements it is not. It varies with canvas colour and pixel count. Its sign inverts across checkpoints. It survives an explicit instruction to disregard the image. And on one model it fires on a bare assertion that an attachment exists, with nothing attached and the modality word contributing none of it. Finally we price it. On a matched harmful set the same canvas does lower attack success, so the cue buys something. But the charge is decoupled from the purchase: the checkpoint with the least harmful headroom we measure, completing only 2% of plain harmful requests, still pays the benign cost in full, and across our models the harmful-side denominator falls as alignment improves while the benign cost does not track it down. Image presence is not a conservative default that a deployer chose and priced. It is an uncontrolled variable.
Read the full abstract

All authors Haoyu Zhang, Yi Feng, Hanwen Liu, Shibo Zheng, Zhuoxi Wang, Yang Chen, Haowen Xu, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita

Information Theory

Fronthaul-Efficient Cell-Free Massive MIMO via Stream-Adaptive Resolution Control

We consider the uplink of a fronthaul-constrained cell-free massive MIMO system with a single multi-antenna user equipment (UE) transmitting multiple spatial streams to distributed access points (APs). Due to heterogeneous channel conditions and limited fronthaul capacity, uniform-resolution quantization across APs and streams is highly inefficient. To address this, we propose a stream- and AP-adaptive resolution control framework that jointly optimizes the transmit power and per-AP per-stream quantization resolutions. By leveraging a distributed implementation of singular-value decomposition (SVD)-based processing, the data streams are decoupled at the APs, enabling flexible fronthaul compression across both spatial streams and APs. The resulting non-convex optimization problem is tackled using a weighted minimum mean-squared error (WMMSE)-based block coordinate descent algorithm with semi-closed-form updates.
Read the full abstract

Information Theory

Joint Quantized Precoding and Bit Allocation for Fronthaul-Constrained Cell-Free Massive MIMO

We study quantization-aware precoding for the downlink of cell-free massive MIMO systems with limited-resolution fronthaul. In such systems, the centrally designed precoder must be quantized before being conveyed to distributed access points (APs), creating a strong coupling between precoder design and fronthaul compression. To capture this effect, we develop an end-to-end signal model based on Bussgang decomposition, where the quantization distortion depends explicitly on the precoder coefficients. Building on this model, we formulate a joint precoding and bit allocation problem under per-AP power constraints and a total fronthaul bit budget. We propose an efficient block coordinate descent algorithm that iteratively updates the precoder, receive scaling, and distortion levels. Numerical results demonstrate that the proposed method significantly outperforms uniform bit allocation and quantization-unaware precoding schemes, particularly in fronthaul-limited regimes.
Read the full abstract

Hardware Architecture

NPLSD: Accelerating Line-Segment Detection on NPU Microcontrollers

Line-segment detection is fundamental to robotics, autonomous navigation, and industrial inspection. While transformer-based detectors achieve the highest accuracy, their deployment on microcontrollers remains impractical due to resource constraints. The STM32N6, with its Neural-ART NPU, promises to enable deep vision at the extreme edge. However, existing detectors rely on attention, grid-sampling, and normalization, operators that are unsupported by the convolution-oriented NPU. This architectural mismatch is characterized operator by operator: attention, grid-sampling, and normalization lack accelerator primitives, and the decoder's self-attention alone materializes a 39 MB score tensor that exceeds on-chip memory. To address this limitation, NPLSD is introduced as a pair of NPU-compatible line-segment detectors built from one design methodology. NPLSD-H retains the convolutional HGNetv2 backbone of LINEA and replaces the transformer head with a fully-convolutional feature pyramid and an F-Clip dense head. NPLSD-M adapts the M-LSD-tiny trunk to the supported operator set. Warm-started from ImageNet and trained on ShanghaiTech Wireframe, the 2.63M-parameter NPLSD-H reaches sAP^10=37.9 (35.9 int8); the 0.62M-parameter NPLSD-M reaches 41.9 (41.1 int8). A controlled ablation isolates the trunk as the only variable, and initialization alone accounts for 4.6 points.
Read the full abstract

Software Engineering

When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation

Large Language Models (LLMs) are widely used as programming assistants, yet it remains unclear whether and how user's demographic information impacts the technical quality of generated code. We conduct a large-scale empirical study of persona-induced bias in LLM-based code generation, focusing a proprietary model (Gemini 2.5 Pro) and an open-weight model (GPT-OSS-120B). Using 18 demographic personas spanning nationality, gender, and experience level, we compare persona-induced prompts against a neutral baseline. Across 35,000+ generated programs, we analyze demographic marker leakage in reasoning and responses, as well as differences in functional correctness, maintainability, code style, and security. Our results show that demographic cues are frequently reflected in LLM reasoning and outputs. Demographic markers appear in up to 65% of responses and 70% of reasoning traces, despite being semantically irrelevant to the tasks. On LiveCodeBench, persona prompting were associated with lower correctness scores of the Gemini model by an average of 1.54 percentage points, with one persona exhibiting a decrease of 3.6% (odds ratio = 0.51). In contrast, the accuracy of the GPT-OSS model improved by 3.4 - 5.7% across all personas (odds ratios = 1.8 - 3.0). Maintainability and code style metrics show statistically significant but negligible effect sizes (all Cliff's {\delta} < 0.15), and security vulnerabilities exhibit no systematic persona-specific patterns. Overall, our results show that the presence of demographic information about users is associated with measurable variation in LLM reasoning and code quality even in purely technical tasks, and that these effects hold across models. Our work highlights an under-examined risk in LLM-assisted software development.
Read the full abstract

All authors Anubhav Gupta, Mayara Costa Figueiredo, Leticia Santos Machado, Tanner Wright, Ivan Beschastnikh, Cleidson R. B. de Souza, Gema Rodríguez-Pérez

Computation and Language

Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models

Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusable context is added. We formulate this phenomenon, which we call context poisoning, as extreme-value interference in attention: the decisive-evidence score is upper-bounded, while the maximum score among effective distractors grows with their number. Under a softmax retrieval abstraction, we derive a finite-sample upper bound showing that maintaining a fixed accuracy target above base rate requires the evidence margin to scale as $\Omega(\sqrt{\log N})$, where N denotes the effective distractor count rather than necessarily the raw context length. The analysis connects long-context degradation to score aliasing, positional aliasing, and softmax dilution. Controlled experiments show that retrieval accuracy decreases as total context grows in the presence of embedded hard negatives, that the same-format condition produces the largest observed accuracy drop among the tested distractor constructions at fixed context length, and that retrieval gating can improve evidence use while its net benefit depends on preserving evidence recall. These results motivate evidence bottlenecks, alias-resistant representations, retrieve-then-reason architectures, verifier-mediated memory, and contrastive anti-poison training.
Read the full abstract

All authors Meysam Ghaffari, Nina Fatehi, Bhaskar Sen, Nasim Sabetpour, Carlos Morato

Computation and Language

AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) improves language models with retrieved evidence, but processing many long passages is costly and can introduce distracting information. Soft compression addresses this challenge by encoding passages as compact sequences of continuous memory embeddings before generation. However, existing methods typically assign each retained passage an identical number of memory embeddings, irrespective of its query-specific relevance. To address this, we propose AdaMem, a relevance-guided soft-compression framework that maps learned passage-relevance estimates to a query-dependent allocation of a fixed memory-token budget. A shared query-conditioned compressor produces both continuous passage memories and relevance scores in a single pass; a deterministic allocation rule assigns more memory tokens to higher-scoring passages and can omit low-scoring ones. Across six open-domain QA benchmarks, AdaMem consistently outperforms OSCAR (the closely matched soft-compression baseline that uses uniform allocation) as well as other soft-compression methods at matched memory budgets. Under standard 16$\times$ compression, AdaMem improves sub-string match by up to 3.2 points (5.5%) over uniform allocation baseline, with an average relative gain of 3.4%; under aggressive 64$\times$ compression the average relative gain grows to 14.6%, with a maximum of 9.8 points (19.7%) on PopQA. AdaMem matches the answer quality of the uncompressed at up to 4$\times$ lower inference latency than full context baseline. AdaMem retains an efficiency profile comparable to the uniform-compression baseline, while achieving up to $4\times$ lower inference latency than full-context inference. Thus, relevance-guided memory allocation is particularly effective when retrieval pools are large and the available memory budget is tight.
Read the full abstract

All authors Artem Sakhno, Grigorii Davydenko, Omar Zoloev, Julia Belikova, Andrey Savchenko, Maksim Makarenko

Computation and Language

A framework for recipe data structure with applications for culinary and nutritional insights

Cooking is a complex process that transforms raw ingredients into delicious and nutritious dishes, yet the recipes that encode this process remain largely free text; readable by people but not directly computable. Existing recipe collections capture fragments of this information, but no shared representation links a recipe's structured ingredient composition, its geo-cultural provenance, and its nutritional profile within a single queryable schema. We address this representation gap by formalizing a framework for recipe data structure that decomposes each recipe into typed ingredient entities, grounds those entities in a reference nutritional database, and annotates them with geo-cultural and dietary context. We present RecipeDB2, a structured compilation of 128,942 recipes with 35,474 ingredients from 32 regions and 99 countries. Ingredient phrases are parsed into seven culinary attributes using a transformer-based named-entity model; ingredients are linked to the USDA reference tables through a BERT embedding strategy (F1 = 87.90 on a manually adjudicated set of the 200 most frequent ingredients), yielding 148 nutritional parameters per mapped ingredient; a Random Forest classifier propagates 34 ingredient categories across the full vocabulary; and a deterministic, conservative rule set assigns each recipe a dietary style. Through RecipeDB2 (https://cosylab.iiitd.edu.in/recipedb2/), we demonstrate a scalable framework for making recipes computable, turning culinary heritage (long treated as an artistic rather than a quantitative object) into a data-driven analysis.
Read the full abstract

All authors Mansi Goel, Sumit Bhagat, Saloni Srivastava, Malav Patel, Shlok Vinodkumar Mehroliya, Ganesh Bagler

Computation and Language

TreeSpark: Calibrated, Load-Adaptive Draft Trees for Semi-Autoregressive Speculative Decoding

Speculative decoding accelerates language-model inference by letting a cheap drafter propose tokens that the target model verifies in parallel. Recent block drafters make drafting nearly free: a single backbone pass emits an entire block of draft tokens. Draft trees promise a further gain – several alternative continuations verified in one target forward – but existing constructions rank candidates by per-position marginals that ignore which parent a candidate extends, so on semi-autoregressive drafters wider trees mostly add mis-ranked nodes; and a tree of fixed size ignores how much speculation each decoding round, and each serving load, can support. We introduce TreeSpark, which reads a parent-conditioned distribution from the drafter's existing Markov head at negligible cost, calibrates it into an edge-acceptance estimate, and lets path survival govern everything else: best-first expansion, per-round stopping, and a load-adaptive serving policy. Sampling siblings without replacement, with matching residuals in recursive rejection, keeps decoding lossless at any temperature. Adaptive trees improve on matched fixed budgets at every temperature; against a tuned chain on the same drafter, TreeSpark accepts 15-25% more draft tokens per round and decodes 8-14% faster in single-request wall-clock, and under rising load it gracefully shrinks the tree back to the chain. Code and artifacts: https://github.com/PopSoda2002/TreeSpark
Read the full abstract

Computation and Language

Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models

The evaluation of large language models (LLMs) on coding tasks has primarily focused on performance metrics such as pass@k. As LLMs continue to advance, many models now meet baseline performance requirements, reducing the discriminative power of performance-based evaluation alone. Yet a key question remains largely unexplored: how do LLMs differ in their coding behavior? We propose CLIC (Code Learning for Identification and Comparison), a visual analytics approach that characterizes LLM coding behavior through token-frequency analysis. CLIC represents each code sample as a feature vector of token frequencies and trains an interpretable decision tree to separate two LLMs' code sets. Beyond classification accuracy, we define two new metrics: robustness, which measures whether the two LLMs remain distinguishable as their most-discriminative tokens are progressively removed, and concentration, which measures whether the difference is driven by a few dominant tokens or spread across many. Interpreting numerous pairwise comparisons (across LLM pairs, tasks, and tokenization levels) and tracing the full analytical chain form an inherently multi-scale, hypothesis-driven exploration task. We therefore develop an interactive visual analytics system to navigate the comparison landscape, identify pairs of interest, and drill down into discriminative tokens and their code contexts. Case studies comparing 10 LLMs across 22 Kaggle ML tasks reveal actionable insights for LLM selection and prompt engineering.
Read the full abstract

All authors Junpeng Wang, Yuzhong Chen, Menghai Pan, Uday Singh Saini, Yiwei Cai

Artificial Intelligence

Function Lives Where Variance Doesn't: Task-Weighted Charts of a Language Model's Computation

How many dimensions does a language model's computation actually use? The question is ill-posed until one names a functional. Task-weighted charts make it well-posed: low-dimensional coordinate systems fit against a chosen functional of the representation, under the functional's own metric, turning distillation into plain least squares. Across six models from three families, spanning 70m to 7B parameters, next-token prediction needs 70–90% of the residual stream's width to stay within 5% of intact perplexity, a width consumed by the rare tail of language, and the variance profile predicts none of it: two directions carry 90% of GPT-2's activation variance and almost none of its function. Dimension is per-functional: the model's own uncertainty reads from six coordinates where the full predictive distribution needs hundreds; and it grows with depth. The dissociation is exploitable: when only a few dimensions can be kept, charts trained under the functional's metric preserve the model's predictions better than variance-based or optimal linear compression.
Read the full abstract

Machine Learning

Diagnosing Faults in Reinforcement Learning Simulators with Canonical Polynomial Invariants

A large literature incorporates physical structure into learned dynamics on the premise that models respecting the underlying physics should predict better. We test this premise using exact polynomial invariants recovered from trajectories and represented canonically as reduced Gröbner bases over Q. We find that exact polynomial invariants provide little additional benefit for residual-based downstream uses. On Gymnasium's Acrobot, consistency regularisation reduces algebraic residuals without improving long-horizon rollout fidelity, while one-step validation error is more strongly associated with long-horizon accuracy; similarly, shaping potentials recovered from systems with mass errors of up to 100% achieve similar learning performance to the physically correct potential. The main benefit observed here instead appears in diagnosis, where canonical representations permit exact ideal-equality and membership decisions, and where a reference generating set supplies a physical vocabulary that generic two-sample tests do not have. We develop a two-level diagnostic comprising screening, which identifies the violated physical constraint, and attribution, which recovers the faulty invariant and identifies the responsible physical parameter. Normal-form deflation removes algebraically trivial multiples, while quotient-space recovery avoids tolerance-based nullspace selection. Across fifteen injected faults, screening localises all fifteen when no observation noise is added, with no observed false alarms. Attribution identifies the responsible parameter in all seven single-parameter faults. Paired difference tests detect all faults but provide no constraint-level localisation, showing that the advantage is localisation and not detection. In conclusion, exactness is more useful for diagnosing violations of physical constraints than for improving prediction.
Read the full abstract

Machine Learning · Cross-listed from math.OC

Exact ReLU realization of binary affine refinement iterates via reflection folding and cone switching

We study vector-valued binary affine refinement operators with finitely supported matrix masks and compactly supported continuous piecewise linear input and forcing data. We prove that every finite refinement iterate admits an exact ReLU realization of fixed width and depth linear in the number of iterations. No separation of the forcing profile from the binary cell seams is required. The main mechanism is universal reflection doubling. Pairing each residual profile with its reflection replaces the two binary transition matrices by one fixed block matrix together with a fixed swap involution. The cell-seam identity makes the two branch candidates agree at the tent fold, while their swap-odd component is bounded linearly by the distance to the fold. This permits exact branch selection by a fixed continuous piecewise linear cone switch, without multiplication by a variable selector. The resulting primal recursion requires the residual orbit in reverse order. We obtain exact backward replay from the residual memory controller developed previously for affine refinement, interpreted here through the reflection quotient of circle doubling. The construction propagates the full vectorized profiles rather than decomposing the input and forcing into reference atoms. We also treat stage-dependent forcing from a fixed finite-dimensional family and show that genuine reflection equivariance reduces the doubled cascade to a single parity sector.
Read the full abstract

Distributed Computing

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

AI-powered search products such as ChatGPT search, Google's AI Overviews, and Perplexity provide LLM-synthesized answers grounded in live web results. We developed OreoLook (formerly lixSearch), an open-source answer engine using automated browser agents and provider-routed LLM inference. Its local search, caching, session-management, and embedding stack runs on commodity CPU hardware; answer synthesis is performed by a remote inference provider. As usage grew, sessions lost context, equivalent queries triggered redundant work, and URLs were repeatedly embedded across sessions. We present a three-layer caching architecture: (1) a Session Context Window maintaining a rolling window of recent messages in Redis with automatic overflow to Huffman-compressed disk archives; (2) a Semantic Query Cache catches rephrasings via cosine similarity on embedding vectors, eliminating redundant LLM invocations; and (3) a URL Embedding Cache that deduplicates embedding computations across sessions. Deployed on a single 8-vCPU Intel Cascade Lake server (2 GHz, 32 GB RAM) running 30 Hypercorn worker processes across three containerized replicas, the evaluated system reported an 89.3% aggregate Redis keyspace hit rate with 0.1 ms read latency and just 1.38 MB of memory overhead. A background LRU eviction daemon migrates idle sessions from Redis to disk and re-hydrates them on demand, enabling conversations that can be resumed hours or days later under the configured retention policy.
Read the full abstract

Game Theory

Large Language Models as Strategic Bidding Agents in P2P Energy Trading Markets

Peer-to-peer (P2P) energy trading markets rely on double auction mechanisms to match prosumers and consumers in smart grid distribution networks. However, the strategic behavior of bidding agents in such markets remains not fully explored, particularly in repeated settings with bounded rationality. This paper proposes a novel framework that integrates large language models (LLMs) as reasoning-driven bidding agents in repeated P2P energy double auctions. We compare the performance of three bidding strategies: random bidding, an $\varepsilon$-greedy multi-armed bandit (MAB) approach, and an LLM-based strategy. Simulation results show that the LLM-based strategy achieves superior cleared trading volume over the first episodes compared to $\varepsilon$-greedy MAB and random bidding baselines, eliminating the exploration burn-in period that statistical learning algorithms inherently require before converging to productive price arms. Importantly, when tested in an environment different from the one used during learning, the performance of the $\varepsilon$-greedy strategy drops significantly, while that of the LLM-based bidding strategy continue to achieve higher surplus and successful trades. Nevertheless, the LLM's advanced contextual reasoning also gives rise to an important market dynamic. In a homogeneous population of LLM agents, sellers increasingly exploit buyers' rational outside options to drive clearing prices above the Nash equilibrium, resulting in a progressively more asymmetric allocation of surplus in favor of sellers that does not converge within the observed time horizon.
Read the full abstract

Artificial Intelligence

ARC-Bench: Closed-Loop Replanning Masks Broken Action Ranking in Frozen JEPA World Models

Reward-free latent world models plan by scoring candidate actions with distances in a frozen latent space: an action is preferred if its predicted future embedding lands closer to the goal embedding. This silently assumes that latent closeness is action-rankable, i.e., that ordering candidates by latent distance agrees with ordering them by true cost. We audit this assumption directly. We introduce ARC-Bench, a no-leak, fixed-candidate protocol that measures whether frozen JEPA-style objectives rank candidate actions correctly, and apply it to official released JEPA-WM checkpoints across navigation and manipulation-style control. The assumption fails, severely and structurally: on the official manipulation audits the top-scored candidate is almost always suboptimal, and the same inversion appears in the maze domains. A controlled visual-backbone extension shows that the defect persists when DINOv2 is replaced by video-pretrained V-JEPA 1 and V-JEPA 2 encoders at ViT-L/ViT-G scale. Provenance, undertraining, matched-budget backbone controls, and metric-circularity controls rule out trivial explanations. We then explain why this defect has stayed invisible: closed-loop replanning masks it. When we reduce the planner's replanning frequency, success collapses in both a navigation and a manipulation domain, and the episodes rescued by frequent replanning are enriched for severe first-plan ranking failures in the PointMaze first-plan diagnostic. Closed-loop success rates therefore systematically overstate the rankability of frozen latent representations. ARC-Bench supplies the measurement, and the masking mechanism the explanation, for methods that adapt, amortize, or replan around latent-space planners without directly auditing released JEPA-WM action rankability.
Read the full abstract

Computation and Language

Redesigning and Auditing Deep Research Writing for Faithful Reports

Rubric-based evaluations of deep-research (DR) systems often obscure fine-grained factual failures in generated reports. We introduce CLAIMPROBE, a claim-level audit that decomposes DR reports into claims and measures hallucination, misattribution, citation hygiene, and necessary-fact recall against retrieved evidence. Using CLAIMPROBE, we find that strong DR pipelines can omit key evidence and misattribute claims even when their rubric scores remain stable. We then propose CLAIMWRITER, a hierarchical claim-based writer that extracts source facts, maps them to a query-derived outline, and drafts each section from a source-linked claim representation. Across three prior DR frameworks, replacing only the report writer with CLAIMWRITER reduces hallucination by 2.6 to 4.5 times and improves necessary-fact recall by 1.2 to 1.7 times, while largely preserving overall report quality. CLAIMWRITER also enables localized revision: when sources change, it propagates changed source facts into revised reports at the highest rate among update methods, while also being more cost-effective.
Read the full abstract

All authors Hiroaki Hayashi, Pranav Narayanan Venkit, Prafulla Kumar Choubey, Chien-Sheng Wu

Artificial Intelligence

From Extraction to Governed Memory: Multi-Agent Knowledge Graph Construction with Domain-Expert Review

Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with little record of who owns a fact, why it was admitted, or how it should be used downstream. We argue that reliable agentic knowledge systems require governance as an essential component of graph construction to bridge this gap. We propose MAGG, a principled multi-agent framework for constructing Governed Knowledge Graphs that introduces explicit governance decisions for reliable and trustworthy knowledge sharing. A domain classifier first induces entity and relation types directly from document content, enabling operation in open-world settings without fixed schemas. Candidate triples are assigned to domain owners, reviewed against supporting evidence, admitted through governance decisions, and stored with audit metadata. The same ownership structure is reused during question answering, where queries are routed to domain-specific graph experts rather than answered through undifferentiated retrieval. Our evaluation demonstrates MAGG's effectiveness: On SciERC, MAGG improves strict triple F1 by 47% and mapped triple F1 by 51% over flat insertion. A blinded review of 120 triples finds governed-only triples more often source-supported than flat-only ones, and revised triples supported in 100% of cases. Finally, on MuSiQue, MAGG outperforms Microsoft GraphRAG by 9.0 exact-match points and 11.2 token-F1 points.
Read the full abstract

All authors Pranav Bykampadi, Neel Mokaria, Vishesh Narayan, Faizan Wajid, Ashok Agrawala

Robotics

Operational digital twin clinics enable task-based evaluation of embodied AI

Embodied artificial intelligence (AI) must be tested in the clinical environments where it will operate, but building realistic, robot-testable settings is costly and difficult to scale. Here we show that routine clinic images can be transformed into operational digital twins for task-based evaluation of embodied AI. Using 39 ophthalmic clinic scenes, we converted single photographs into editable, simulator-ready environments and assessed reconstruction quality, room-scale geometry, mesh grounding, multi-robot feasibility, perturbation sensitivity and closed-loop policy performance. The reconstructed scenes preserved workspace structure, while local editing enabled controlled device reconfiguration. Device meshes, collision proxies and semantic anchors converted visual reconstructions into contact-aware simulation scenes. Across three robot embodiments, shared task targets showed different patterns of reachability and contact feasibility. Small device translations and rotations produced task-specific changes in contact margins that were not captured by visual similarity alone. Digital-twin trajectories also supported local policy learning and closed-loop evaluation. These findings establish operational validity as a key principle for clinical digital twins and provide an intermediate layer between offline development and physical deployment of embodied AI in healthcare.
Read the full abstract

All authors Xinyuan Wu, Jingrao Zhang, Mengdi Xu, Henry K. Chu, Mingguang He, Danli Shi

Computation and Language

Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding

Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases from their training data, resulting in biased behavior when processing portraits from different social groups. Existing debiasing approaches typically compare token probabilities between the original and biased generations during decoding, but they are fundamentally limited by their reliance on a single, stereotyped viewpoint and fail to account for the diversity of social perspectives. Inspired by the social science principle that diversity fosters fairness, we propose Counterfactual Ensemble Decoding (CED), a novel framework that constructs multi-group counterfactual perspectives within the visual representation space and integrates them during decoding to promote equitable model behavior. CED first performs counterfactual steering in the visual space by identifying semantic directions associated with each social group and generating counterfactual representations along these directions, thereby offering diverse perspectives that disrupt stereotypical narratives. During decoding, CED locates the decoder layer exhibiting the greatest divergence among these perspectives and ensembles their token distributions using uncertainty-aware weights, prioritizing high-confidence tokens from different groups to yield a more balanced probability distribution that guides fairer generation. Extensive experiments on three social bias evaluation benchmarks demonstrate that \tool achieves substantial improvements over leading baselines, reducing bias by up to 47.97% across scenarios involving occupations, descriptors, and persona traits. Moreover, CED also preserves the core capabilities of the original model with minimal degradation.
Read the full abstract

All authors Yisong Xiao, Aishan Liu, Yongxin Huang, Zonghao Ying, Shiji Zhao, Tianlin Li, Yong Han, Jian Yang, Xianglong Liu