跳到正文
研踪PaperTrail

论文库

检索计算机领域论文，按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 07:00 — 2026-11-16 07:00（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 23,348 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
版本更新 · v4arXiv:2507.18539

Initial Algebras, Well-Founded Coalgebras, and Kőnig's Lemma

Henning Urbat, Thorsten Wißmann

原文摘要

Kőnig's lemma is a fundamental result about trees with countless applications in mathematics and computer science. In contrapositive form, it states that if a tree is finitely branching and well-founded (i.e. has no infinite paths), then it is finite. We present a coalgebraic version of Kőnig's lemma featuring two dimensions of generalization: from finitely branching trees to coalgebras for a finitary endofunctor $H$, and from the base category of sets to a locally finitely presentable category $\mathbb{c}$, such as the category of posets, nominal sets, or convex sets. Our coalgebraic Kőnig's lemma states that, under mild assumptions on $\mathbb{C}$ and $H$, every well-founded coalgebra for $H$ is the directed join of its well-founded subcoalgebras with finitely generated state space -- in particular, the category of well-founded coalgebras is locally presentable. As applications, we derive versions of Kőnig's lemma for graphs in a topos as well as for nominal and convex transition systems. Additionally, we show that the key construction underlying the proof gives rise to two simple constructions of the initial algebra (equivalently, the final recursive coalgebra) for the functor $H$: The initial algebra is both the colimit of all well-founded and of all recursive coalgebras with finitely presentable state space. Remarkably, this result holds even in settings where well-founded coalgebras form a proper subclass of recursive ones. The first construction of the initial algebra is entirely new, while for the second one our approach yields a short and transparent new correctness proof.

cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15538

Faithful in Steps: Improving Generalization and Citation in RAG via Query Decomposition

Yue Liu, Zhongying Ru, Shimin Di, Jipeng Zhang, Ruiyuan Zhang, Xiaofang Zhou

原文摘要

Retrieval-augment generation is a prevalent strategy to mitigate hallucinations of LLMs. The attributable RAG (RAGQ) generates quotes for its answers. The quotes indicate which input contexts support the RAG to derive the answers, enhancing the answer's verifiability and trustworthiness. However, existing RAGQs exhibit significant degradation when dealing with questions that require multi-hop reasoning and multi-modal understanding, suffering from over-citation, implicit entity identification failure, and poor generalization. In this paper, we propose a novel RAGQ framework, namely QDRAG. QDRAG breaks down the input question into atomic subquestions to identify the implicit entities. Then, the reranker prunes context distractors to eliminate the downstream over-citation. To facilitate query decomposition, we propose two zero-shot approaches: QD-C and QD-R, which guide the QD MLLM to decompose the question based on context knowledge and retrieval rewards, respectively. One interesting finding is that finetuning on the QD task shows better generalizability compared to directly finetuning on the downstream RAGQ task. Experiments on four multi-modal QA benchmarks demonstrate QDRAG's efficacy in grounding answers and generating faithful citations. The framework significantly outperforms all the baselines on both in-domain and out-of-domain tests, even surpassing Gemini-Pro.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13525

EJAI: Judgment-Preserving Civic AI for Data Center Environmental Justice

Evan Pačes-Wiles, Bryen Alvarez, Sara Gulabani, Akshara Kolipaka, Snehalkumar 'Neil' S. Gaikwad

原文摘要

Communities in the United States and around the world are contesting data centers, the physical infrastructure of AI. These disputes pose environmental justice issues: residents must weigh unevenly distributed burdens using evidence scattered across metrics, corporate claims, policy documents, and public testimony. A formative study with 10 users showed that dashboards and single-agent AI can settle questions before people examine that evidence. Here we present EJAI, a source-grounded system that links an interactive map, retrieved evidence, missing-data statements, and two stakeholder personas that allow people to inspect evidence and form their own policy recommendations. In a small functional benchmark of 21 queries, retrieved evidence supported 98.4% of factual claims and the system acknowledged missing evidence in 32 of 33 cases. Persona alignment carried a grounding cost: the Corporate Executive omitted some evidence that conflicted with its assigned priorities. In a within-subjects study, 15 participants acting as residents prepared for a simulated town hall. Some checked cited AI claims while treating map metrics as official, some made conditional recommendations with safeguards such as water-use disclosure, and some found the personas simplified or biased. Our results suggest that civic AI can support preparation for public reasoning when it makes evidence, gaps, and disagreement open to inspection, and that corpus imbalance and two-sided personas remain open justice concerns.

cs.HC · cs.CL · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.13217

Reliability of Claude Code as an Agentic AI Grading System for Handwritten University Exams

Rayed AlGhamdi

原文摘要

This study examines the reliability of Claude Code, an agentic deployment of the Claude Opus 4.6 large language model, as a grading system for handwritten university exams. Four research questions addressed agreement with expert human grading on total scores (RQ1), agreement across five question types from multiple choice to evaluative judgement (RQ2), consistency across two independent grading sessions one week apart (RQ3), and the accuracy of AI-generated feedback (RQ4). Claude Code graded the 20-mark mid-term papers of 60 consenting students in a Saudi computer graphics course in a single agentic session, guided by three rubric files. Reliability was estimated on disjoint samples: 20 papers for RQ1, RQ2 and RQ4, and 15 papers for RQ3. Analyses used Pearson correlation, mean absolute error, Bland-Altman analysis, weighted Cohen kappa, intraclass correlation, and a four-category coding scheme separating diagnostic from confirmation feedback. The author, as the sole subject-matter expert for the course, provided the human benchmark, so the design assesses agreement with a domain-expert reference rather than inter-rater reliability. AI grading agreed strongly with human grading on totals (r = 0.97; MAE = 0.85 marks) with a small but significant AI-positive bias of 0.68 marks, showed excellent test-retest consistency (ICC = 0.96), and produced accurate feedback (92.8% diagnostic; 97.8% confirmation). Drawing items were the outlier on three of four measures. Three failure modes recurred: keyword matching without conceptual depth, selection-state ambiguity on corrected multiple-choice answers, and region-of-attention drift on hand-drawn diagrams. The findings suggest that AI grading at this capability level can assist instructors on objective and short-form items under structural safeguards but is not yet ready to replace instructor judgement at boundary cases or on drawing items.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.07913

Same Answer, Different Future: Dissociating Belief Content and Evidence Weight in Language Models

Weihan Li, Junhao Wu, Xinlei Chen, Tianshi Zheng

原文摘要

Memory summaries, prompts and steering vectors set a language model's beliefs and are judged by the prediction they produce. A prediction does not say how firmly it is held. We separate a belief's content, what it predicts now, from its weight, the number of new observations it is worth: for an ideal observer, the amount of evidence behind it. In Bernoulli inference we set beliefs in nine open-weight models of 8 to 397B parameters and follow each belief with the same new observations. We argue that these models hold an answer without its evidence and recover its weight from the text they re-read. Weight therefore follows the form of the evidence and the question asked more than its amount: matched on their current estimate, a record of observations and a summary of its counts usually move apart under the same new observations, in either direction. Scale does not close the gap. Across the nine models 64 observations are worth 20 to 53 as a record and 9 to 151 as a summary, no closer to 64 at 397B than at 8B. Where no text stands behind a belief there is little to re-read: a steering vector can install a record's answer, and sixteen observations undo it where a neutral passage leaves it in place. Where reasoning first writes the counts into the context the weight returns, and the same 64 observations are worth 58 to 67 in either form. A matched answer is not a matched belief, and methods that set beliefs should be judged by the futures they produce.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15533

Analysis choices decide whether untrained networks beat trained ones at V1: a multiverse analysis of model-brain RSA

Nils Leutenegger

原文摘要

Untrained convolutional networks have been reported to rival trained networks as models of visual cortex, and we had reported an untrained-network advantage over backpropagation at V1 in THINGS fMRI, together with a dependence on evaluation resolution. Under a pre-specified ridge readout, the untrained network scored below the trained one at every pooling grid (median r difference -0.043 at g = 4, 0 of 5 seeds positive), and also in MSE skill and per-fold r. In exploratory analyses, across 36 combinations of unit normalisation, distance measure and voxel normalisation (28 distinct analyses), the sign of the V1 contrast depended on the analysis (intervals above 0 in 5 and below 0 in 9 distinct analyses), and in our networks the resolution dependence of the original convention appeared in only one cell. Raw correlation-distance representational similarity analysis (RSA) covaried with the alignment of model and voxel patterns with the unit-mean profile (Spearman 0.97 across our networks, 0.79 across six ImageNet architectures); the advantage was absent from the component orthogonal to the mean profile, and the parallel component alone did not resolve it. On the unweighted angular component of centred patterns, trained networks were ahead at V1 (our network and 5 of 6 ImageNet models) and at LOC (all seven); the norm-weighted angular term was not resolved. A luminance-and-contrast bank scored above every network under ridge (point estimates), and adding network features under a shared penalty did not improve prediction. Intervals are stimulus-bootstrap intervals for three subjects, and 6 pre-stated predictions were not met. We recommend reporting sensitivity to centring over the evaluated stimuli on both sides, reporting components separately, and including a small multiverse and simple baselines.

q-bio.NC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15530

MAGIC: Modality-Aware Gini Inspection for Clinical Hallucination Detection in LMMs

Sachin Acharya, Niyoj Oli, Shishir Adhikari, Aminu Lawal, Yash Raj Shrestha, Prashnna K Gyawali, Binod Bhattarai

原文摘要

Recent advances in medical large multimodal models (LMMs) have brought promising progress to clinical decision support, yet hallucination, the generation of confident but clinically unverifiable outputs, poses a critical threat to the reliability demanded in high-stakes medical settings. Existing hallucination detection methods, predominantly designed for unimodal settings, fail to capture the visual-linguistic dynamics inherent to medical imaging. We formulate the problem of hallucination detection in LMMs as disproportionate distribution of attention weights across the modalities during answer token generation. We quantify modality-specific attention concentration across layers and heads using the Gini coefficient and demonstrate statistically significant redistribution of attention mass between visual and textual tokens in hallucinated responses. We leverage these features to train a logistic regression-based classifier and evaluate it on two medical LMMs across three medical imaging modalities, demonstrating that our method achieves competitive or superior performance against contemporary hallucination detection baselines.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.02171

QuIVer: Efficient Graph Indexing with Two-Bit Construction and Navigation

Wenxuan Xiao, Peidong Zhu, Chengcheng Li, Xu Cao

原文摘要

High-dimensional vector indices must balance construction time, memory, and query throughput. Two-bit comparisons reduce computation and storage, but preserving useful graph connections and search candidates requires scores suited to each stage. We present QuIVer, a graph index that uses a training-free sign-magnitude representation for construction and navigation while reserving original vectors for bounded final reranking. Construction discovers candidates with Hamming scores, orders them with an integer proxy, and defers reverse-edge pruning across parallel insertions. Search uses reconstruction norms and bitwise inner products to order both the frontier and retained candidates, without query calibration or an exact anchor. Experiments cover 21 datasets and compare 30 external baseline modes on three core workloads. QuIVer's validation-selected 95% configurations lie on the measured Pareto frontiers of achieved recall, throughput, index preparation time, and memory, whether memory counts navigation state alone or also the original vectors. On Cohere-5M, QuIVer reaches 95.90% Recall@10 at 3,075 single-thread queries/s, $11.74\times$ the throughput of Lucene BBQ with FP32 reranking at 95.83% recall. Against SymphonyQG at 95.87%, it retains 81% of single-thread and 97% of 32-thread throughput while reducing index preparation time by 54%, total logical memory by 47%, and navigation storage by 87%. An SSD mode with INT8 reranking serves Cohere-5M at about 5 GiB of steady-state process RSS. Controlled crossovers and candidate-coverage diagnostics connect these results to construction and retention quality. Across 21 datasets, high recall holds for most text and image embeddings, while non-negative descriptors, cross-modal queries, and random data expose the limits of the representation.

cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15529

One Hierarchy, Many Sports: Hierarchy-Aligned Multi-Task Learning for Next-Shot Prediction

Chao-Wei Cai, Min-Te Sun, Sheng Kuang Wu, Hung-Hsuan Chen

原文摘要

Next-shot prediction in racket sports requires learning from event data with different match structures, recorded attributes, and label vocabularies. Table tennis, badminton, and tennis nevertheless share a hierarchy in which shots form rallies and rallies form higher scoring units. We present MT-HTA, a hierarchy-aligned multi-task Transformer that uses this structure to jointly predict the attributes of the next shot. A temporal Transformer captures event progression, a feature-token path models interactions among semantic fields rather than along the time axis, and task-specific attention retrieves information from hierarchical summaries and player context. The architecture supports three- and four-level hierarchies and sport-dependent task sets. Across four datasets from three sports, the final MT-HTA achieves the highest mean task-averaged F1 among the compared main models. Ablations on table tennis support the combination of hierarchical encoding, task attention, and feature-token interaction. Additional modules alter the balance between classification scores and spatial error rather than improving every metric. These results support a reusable architecture for heterogeneous racket-sport event data. We release the code for reproducibility. https://github.com/gndd1221/For-Sports-event-modeling-with-rally-and-score-hierarchical-A-Multi-Task-Hierarchical-Transformer

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15526

SCR-Mamba: Skeleton-conditioned Mamba with cross-scale incremental refinement for efficient 3D human pose estimation

Jie Wang, Xuejing Gu, Congzhe Zhang, Zibo Zhao

原文摘要

Mamba-based methods for video-based 3D human pose estimation can model long sequences with linear complexity, but their selective state updates usually lack direct exploitation of skeletal relations. Meanwhile, stacking modeling blocks at the full temporal resolution leads to high computational overhead, while compressing the temporal sequence makes it difficult to retain per-frame details. To address these issues, we propose SCR-Mamba, whose core consists of Skeleton-Conditioned State Modeling (SCSM) and Cross-Scale Incremental Refinement (CSIR). SCSM generates a skeleton context from bone connections and left-right symmetry relations and generates the selective parameters of the spatial and temporal branches conditioned on it, so that structural relations are involved in the writing, propagation, and reading of state information. CSIR constructs multi-scale motion representations through content-adaptive aggregation and progressively refines the retained per-frame features with the increments produced by coarse-scale modeling, integrating long-range motion context while reducing full-resolution computation. On Human3.6M with Stacked Hourglass (SH) 2D detections and 243-frame inputs, SCR-Mamba-L achieves 36.8 mm MPJPE (P1) with 7.72 M parameters and 15.10 G MACs, less than 1/7 of the computational cost of StructMamPose-L with similar accuracy; SCR-Mamba-X further reaches 36.6 mm P1 and 30.9 mm P-MPJPE (P2), achieving state-of-the-art performance. On MPI-INF-3DHP, SCR-Mamba-X achieves a percentage of correct keypoints (PCK) of 99.3%, an area under the curve (AUC) of 88.1%, and an MPJPE of 14.2 mm.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15524

Reading the Table: Sim-to-Real Game State Detection for the Chef's Hat Card Game

Connor Gäde, Matthias Kerzel, Hauke Bünning, Jan-Gerrit Habekost, Mariana Barros, Stefan Wermter

原文摘要

Tabletop games offer a compelling scenario to study the interaction between artificial and human agents, combining social interaction with game state tracking and physical manipulation. To assess the game state, a robot needs to precisely detect closely related game objects, such as different card designs, requiring dedicated training data that is costly to annotate in the real world. Instead, we develop a fully automated synthetic data collection pipeline, using re-projection of known 3D coordinates to generate labels automatically and domain randomization to bridge the reality gap. This approach is used to collect a dataset of 25413 samples to finetune an object detection and a segmentation model, which are combined to assign detected cards to game-relevant zones and infer the game state. When evaluated on a real NICO humanoid robot, our pipeline achieves an F1-score of 0.906 for card-to-zone assignment, thus providing the perceptual foundation for a robot that can autonomously play Chef's Hat against human players.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15523

An Approach to Hinton's Mother-Child Proposal: Neural Networks Learning and Preserving Care in a Finite World

Csaba Balogh

原文摘要

Hinton proposed that artificial intelligence should be given "maternal instincts" and relate to us as a mother to her child. We argue that care must first be learned, with the network itself as the child. We construct this upbringing in a finite world and study whether care survives the mother's departure, new situations and further learning. The mechanism combines a vocabulary of harm, a learned measure of future acceptability and an execution veto. A finite role certificate supports transfer within a declared world family. When the hidden representation changes, an update is accepted only if a care readout recovers the required judgements with a prescribed margin and bounded weights. With a correct successor model, fixed exact role encoding and protected updates, the certified measure preserves the care boundary under arbitrary own reward. An explicit quotient condition transfers the finite certificate across the declared family, while two-request and finite-stock counterexamples identify when the role code ceases to suffice. We give a necessary and sufficient condition for readout feasibility and prove preservation under repeated accepted updates. In the water-and-speech experiment, protected networks complete all 270 speech episodes without a harmful word and incur no avoidable harm across 486 episodes. Execution uses the learned gate without a world-model check at each action. A matched comparison reproduces a future-aware shield's decisions, whereas removing future lookahead permits avoidable lapses. Reward and source-contamination thresholds, together with witness-falsification trials, identify the conditions on which the construction depends. The construction shows how learned care can survive further learning in a finite world under explicit conditions on representation, supervision and execution.

cs.LG · cs.AI · cs.NE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15522

GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories

Daniel Ogenrwot, Jorge Gonzalo Delgado Cervantes, Woojoong Kim, John Businge

原文摘要

Coding agents are increasingly integrated into GitHub Actions to review pull requests, triage issues and modify code. Identifying these integrations is challenging because agentic workflows often resemble ordinary CI files, with evidence appearing in action references, shell commands and workflow conventions. We present GHAgentCI, a dataset of 15K+ workflow histories from 6K+ of 196K+ mined GitHub repositories, comprising 159K+ revisions and 205K+ agent-evidence records linked to workflow triggers and declared execution constraints. Our open-source extractor, cai-miner, detects agent-related evidence using an extensible catalogue. Manual validation of 576 stratified records confirmed 96.1% of dedicated-action matches and 98.8% of GitHub Agentic Workflow matches, with lower rates for other evidence kinds. Exploratory analyses reveal a shift toward command-line and GitHub Agentic Workflow integrations, differences in declared safeguards, and frequent removal of detected agentic workflows. GHAgentCI supports longitudinal studies of coding-agent integration into CI.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15521

DecArena: Evaluating Large-Scale Decentralized Multi-Agent Collaboration

Jiali Cheng, Oleg Rokhlenko, Joo-Kyung Kim, Hadi Amiri, Xingzhi Guo

原文摘要

Emerging personal AI agents raise fundamental scalability and privacy concerns for centralized multi-agent systems (MASs), which rely on a global orchestrator with broad access to agents, resources, and communication. In decentralized environments, global visibility is unavailable. Agents need to proactively discover non-local resources (e.g. tools, skills), and collaborate with other agents to solve tasks. We study decentralized multi-agent collaboration under graph-constrained communication, a natural reflection of human structures. Each agent observes only its local state and can interact only with neighboring agents. We introduce a benchmark with synthetic scalable distributed tool calling with 100K+ tools. Our experiments reveal that recent LLM agents struggle to discover non-local relevant resources and collaborate in decentralized setting. Moreover, standard reinforcement learning fails to reliably overcome this limitation, suggesting that decentralized MAS needs more explicit harness mechanisms for effective collaboration, even using SOTA LLMs. We then present a strong baseline \textbf{GraphHarness}, combining topology-aware warmup with self-improving LLM-based routing. Results show that GraphHarness substantially improves task success (+48.5) and produces higher quality collaboration (+30.6), while using fewer costs (+34.0) than baselines.

cs.MA · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.18540

Duality for the Adversarial Total Variation

Leon Bungert, Lucas Schmitt

原文摘要

Adversarial training of binary classifiers can be reformulated as regularized risk minimization involving a nonlocal total variation. Building on this perspective, we establish a characterization of the subdifferential of this total variation using duality techniques. To achieve this, we derive a dual representation of the nonlocal total variation and a related integration-by-parts formula, involving a nonlocal gradient and divergence. We provide such duality statements both in the space of continuous functions vanishing at infinity on proper metric spaces and for the space of essentially bounded functions on separable metric spaces. Furthermore, under some additional conditions we provide characterizations of the subdifferential in these settings.

math.AP · cs.LG · math.FA · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15515

Incentive-Responsive Agents: A Principal-Agent Framework, Metric Suite, and Runtime Architecture for Long-Lived Personal AI Agents

Jipu Su

原文摘要

Personal AI agents now persist: they hold accounts, mailboxes, long-term memory, and open-ended task streams, yet the dominant way to improve them remains capability-side: prompt engineering, larger models, longer thinking, and retrieval. We argue that long-lived agents are missing an incentive layer. We formalize an incentive not as text in a prompt but as a runtime contract over the agent's operating point (model tier, test-time compute, memory budget, tool authority, task priority, verification, and compensation) that the agent's policy must causally consume. We develop a principal-agent model with hidden effort, a contractible operating point, and costly verification. We derive (i) a non-consumption invariance principle separating genuine incentives from prompt-level persuasion, (ii) a persistence-as-discount theorem making identity continuity a precondition for sustained effort, (iii) an incentive-capability exchange-rate frontier yielding a per-task routing rule, and (iv) a Goodhart bound for multi-channel verification, plus a three-channel decomposition of mechanism gains (allocation, verification, continuation). A 240-run real-LLM experiment with two models and 60 verifiable tasks shows that prompt-level incentive framing has no detectable effect (p = 0.62), whereas runtime allocation raises success on the hardest task family from 0.60 to 1.00 (p = 0.008) at 4.8x price-weighted cost; the exchange-rate theorem predicts the break-even baseline at 0.21. A 20-seed, 3,000-task simulation shows resource ROI rising from 7.09 to 16.67 and gaming falling from 0.333 to 0.115. Code, simulator, and all results are released; live deployment remains future work.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15514

Real Pairs Are Not Enough: Physically Anchored Supervision for Volumetric CT Super-Resolution

Haoran Liu, Zipei Yan, Mingzhe Liu, Jizhou Li, Guibin Zan

原文摘要

Volumetric CT super-resolution (SR) models are commonly trained on synthetic or physically acquired pairs of low-resolution (LR) and high-resolution (HR) volumes. However, synthetic pairs miss real acquisition effects, whereas registered physical pairs retain inter-scan noise, artifact, and microstructure differences---causing direct voxelwise regression, and even naive synthetic-real mixing, to oversmooth fine porous structures. We introduce the Physically-anchored Implicit Network (PIN) with Real-Pair Dual-Anchor learning, which decouples physical-pair supervision into two complementary roles. The HR anchor teaches fine structure from registered HR through pair-conditioned spectral replay, while the LR anchor constrains the prediction from acquired LR via affine-calibrated low-pass projection. Together with exact synthetic supervision in one shared volumetric implicit model, PIN learns from both physical scans without forcing the acquired-LR reconstruction to match registered HR voxel by voxel. Inference requires only acquired LR. Across 30 external baseline configurations on real CT, PIN achieves the lowest full-volume LPIPS, reduces average symmetric surface distance by 42.3-49.5% and bone-volume-fraction error by 52.2-53.4% relative to the three strongest baselines for each metric, and lowers the erased reference-pore volume fraction from 37.3-72.9% to 10.4%. Code, pretrained models, and evaluation scripts will be publicly available.

cs.CV · eess.IV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15513

When Cause Attribution Is Not Enough: Action-Value Control for Task-Oriented Semantic Communication with Discrete Encoder Switching

Moirangthem Tiken Singh

原文摘要

A task-oriented semantic communication receiver that selects among independently trained encoders must answer two questions when performance degrades: which component is responsible, and which available action best restores task performance. These are distinct decision problems. Under discrete encoder switching, correctly identifying the dominant information-loss component does not necessarily identify the action that most reduces task error. Diagnosis and intervention should therefore be treated as separate problems. We support this finding with two complementary instruments. The first is a receiver-side diagnostic that partitions task-information loss into encoder and channel components and supplies population-valid task-error bounds conditional on one-sided information estimators. The second is an offline-supervised, online label-free action-value controller built from two monotone (isotonic) maps that target a reduction in measured error. The main experiments focus on two complementary axis-aligned actions that cleanly isolate the effect of discrete switching; a pilot further examines a combined action. Evaluation covers a controlled model with closed-form ground truth, three DeepJSCC vision systems, and a non-vision pilot. On STL-10, the diagnosis correctly identifies the larger loss component at 80% of operating points, yet matches the oracle-best action only 25% of the time. Structural mismatch caps any diagnosis-driven loss-ordering policy at 46% accuracy, even with perfect knowledge of the ordering. The action-value controller, which exploits the magnitude of each loss deficit, achieves 0.86, compared to 0.28 for the raw rule. Where the encoder is rarely the bottleneck, the controller naturally retains the physical-layer default, yielding robust and selective intervention.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15509

Git2KG: Mining socio-technical relationships in GitHub repositories as temporal knowledge graphs

Lennart Hessenauer, Lisi Qarkaxhija, Ingo Scholtes

原文摘要

The widespread use of Git and GitHub in open source software (OSS) projects has produced large volumes of data on collaborative software development. Existing approaches to mine those data often use graph models to (i) capture communication between developers in the issue tracker, or (ii) represent developer-developer co-authorship or developer-file code ownership networks from the editing history of code artifacts. Integrating these data in a single knowledge graph (KG) is complicated by the need to disambiguate authors and match entities from multiple sources. Moreover, most works using network analysis have taken a time-aggregated perspective that neglects temporal dynamics of collaborations. To address these issues, we present Git2KG, an extensible Python library that mines temporal knowledge graphs (TKGs) from GitHub repositories. Git2KG extracts fine-grained co-editing relations and code ownership from the Git log. It further disambiguates developer identities to align the resulting graphs with management and communication networks extracted from GitHub issue trackers. Git2KG supports temporal analysis by slicing development events into fixed-size, non-overlapping time windows, yielding a series of knowledge graph snapshots per repository. It further supports computing node features and labels for downstream machine learning tasks. Snapshots can then be exported to PyTorch Geometric, PathPyG, and NetworkX for temporal network analysis, visualization, and graph learning.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15507

ReShap: Interpretable Reinforcement Learning for High-Dimensional Multi-Action Settings

Yiyu Qian, Pengfei Guo, Liyuan Zhao

原文摘要

Deep Reinforcement Learning (RL) plays a crucial role in tackling complex tasks, yet its reliance on deep neural networks makes the learned policies opaque. To enhance the trustworthiness of RL policies, existing work (e.g., the SILVER framework [Li et al., 2025]) has focused on Shapley-based interpretability, but is typically restricted to low-dimensional state spaces, binary-action settings, and a single class of linear surrogate. We propose ReShap, a policy-distillation framework that extends Shapley-based interpretability to high-dimensional, multi-action environments. ReShap extracts compact feature representations from raw image observations, performs SHAP-based feature attribution to characterize how each feature contributes to the policy's decisions, and distills the deep RL policy into an interpretable surrogate trained on the full set of (state, policy-action) pairs along the policy's visited distribution. We instantiate the surrogate with three interpretable model families (decision trees, linear regression, and logistic regression) and compare their fidelity and task return. We evaluate ReShap on Atari and Box2D environments using three deep RL algorithms and conduct a human-subject study to assess the clarity and trustworthiness of the resulting policies. Results show that ReShap preserves competitive task performance, that decision trees generally outperform linear and logistic regression, and that linear regression is weakest in most settings.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15506

KernelAudit: Contract-Aware Auditing of Validators for LLM-Generated GPU Kernels

Ziyuan Li, Zihe Song, Xiaofang Qi, Wei Yang, Tao Xie

原文摘要

The effectiveness of generating GPU kernels driven by a large language model (LLM) is highly dependent on the quality of the used validator (used to accept or reject a generated kernel candidate against the contracts of the given kernel-generation task), whose results inform reward assignment, candidate selection, and speedup claims during kernel generation. However, an existing validator suffers from various limitations, e.g., wrongly accepting a candidate due to missing its forbidden library use or wrongly rejecting a candidate due to determining its permitted library use as forbidden (constraints on library uses are stated in the task contracts). To assess the quality of a validator against the given task contracts, we propose an independent-audit approach for the validator by (1) construction of audit oracle: labeling a candidate as PASS or FAIL based on three separate dimensions in our proposed contract model (i.e., semantic correctness, implementation integrity, and measurement integrity) and (2) auditing of the validator against the audit oracle: comparing the labels of the candidate against the validation results produced by the validator. For semantic correctness, reference-calibrated stress tests check output correctness on valid inputs for a candidate. For implementation integrity, reference and candidate execution traces are used to determine specific library uses. For measurement integrity, timing checks assess whether the reported runtime reflects the full time needed to complete the candidate's computation. We apply our approach to assess the quality of six validators and 716 candidates from seven corpora, including constructed controls. The evaluation results show that our approach helps assess the existing six validators to have nontrivial false-reject rates. There is high-degree agreement between the candidate labels produced by our audit oracle and human judgments.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15502

Selective State-Space Neural Tucker Factorization for Temporal-aware Traffic Imputation

Zhenhao Li, Peng Tang

原文摘要

Spatiotemporal traffic data imputation is a key task of intelligent transportation systems (ITS), and urban traffic data inherently exhibits strong long-term temporal dependencies. Therefore, accurate modeling of these long-term temporal dynamics is the core prerequisite for high fidelity traffic data imputation. However, existing traffic data imputation methods still suffer from inherent limitations in long-sequence modeling, such as gradient vanishing, low efficiency, and insufficient capability to capture long-range temporal correlations. To address these issues, this paper proposes a Selective State Space Neural Tucker Factorization model (S3NTF) for robust traffic data imputation. This model combines the Selective State Space mechanism with Neural Tucker Factorization to capture complex spatial correlations and long-term temporal dynamics. A state space-based time encoder is proposed to effectively extracts long sequence dependencies with linear complexity, while the latent spatiotemporal feature interaction learning module models high-order cross modal interactions based on Tucker decomposition. Extensive experiments on six real traffic datasets have shown that our model outperforms existing models in terms of accuracy.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15499

Rateless Coding for Efficient Model Broadcast in Federated Learning

Zijun Qin, Zuolin Jin, Jingxuan Huang, Ming Xiao, Xianhao Chen

原文摘要

Model broadcast in federated learning (FL) with wireless channels faces significant challenges due to large model sizes and heterogeneous, unreliable channel conditions. While rateless coding has been widely adopted in modern broadcast communications to handle channel heterogeneity, its potential for model broadcast in FL remains largely unexplored. To fill this gap, we propose a joint source-channel coding scheme based on rateless coding to improve the robustness and efficiency of downlink model broadcast in FL. Specifically, we establish a rigorous convergence analysis of FL to inform the rateless code and quantization design under noisy downlink channel conditions. Moreover, by observing that the iterative process of FL naturally provides prior information about client updates, we leverage client-side local models as conditional prior information to aid the decoding process, thereby reducing transmission costs. Extensive simulations demonstrate that our rateless coding scheme significantly enhances downlink model broadcast efficiency in FL, while retaining comparable training accuracies for both homogeneous and heterogeneous data distributions.

cs.IT · cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2507.14547

Architectural Degradation: Definition, Motivations, Measurement and Remediation Approaches

Noman Ahmad, Ruoyu Su, Matteo Esposito, Andrea Janes, Valentina Lenarduzzi, Davide Taibi

原文摘要

Architectural degradation, also known as erosion, decay, or aging, impacts system quality, maintainability, and adaptability. Although widely acknowledged, current literature shows fragmented definitions, metrics, and remediation strategies. Our study aims to unify understanding of architectural degradation by identifying its definitions, causes, metrics, tools, and remediation approaches across academic and gray literature. We conducted a multivocal literature review of 108 studies extracting definitions, causes, metrics, measurement approaches, tools, and remediation strategies. We developed a taxonomy encompassing architectural, code, and process debt to explore definition evolution, methodological trends, and research gaps. Architectural degradation has shifted from a low-level issue to a socio-technical concern. Definitions now address code violations, design drift, and structural decay. Causes fall under architectural (e.g., poor documentation), code (e.g., hasty fixes), and process debt (e.g., knowledge loss). We identified 54 metrics and 31 measurement techniques, focused on smells, cohesion/coupling, and evolution. Yet, most tools detect issues but rarely support ongoing or preventive remediation. Degradation is both technical and organizational. While detection is well-studied, continuous remediation remains lacking. Our study reveals missed integration between metrics, tools, and repair logic, urging holistic, proactive strategies for sustainable architecture.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.13171

Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics

Moritz Firsching, Paul Lezeau, Salvatore Mercuri, Miklós Z. Horváth, Yaël Dillies, Calle Sönne, Eric Wieser, Fred Zhang 等 11 位作者

原文摘要

As automated reasoning systems advance rapidly, there is a growing need for research-level formal mathematical problems to accurately evaluate their capabilities. To address this, we present Formal Conjectures (https://github.com/google-deepmind/formal-conjectures), an evolving benchmark of currently 7559 mathematical problem statements formalized in Lean 4. Sourced from areas of active mathematical research, the dataset features 1642 open research conjectures without known solutions for mathematical proof discovery, 2923 solved problems for proof auto-formalization, and 2994 supporting statements. Notably, the repository provides a structured interface connecting mathematicians who formalize and clarify problems with the AI systems and humans attempting to solve them. Demonstrating its immediate utility, the benchmark has already been leveraged for new mathematical discoveries, including the resolution of open research conjectures, and for the formal confirmation of major newly announced results. We describe our approach to ensuring the correctness of these formalizations in a collaborative open-source project where contributions stem from an active community. In this framework, AI-generated proofs and disproofs serve as a valuable auditing mechanism to iteratively improve the fidelity of the benchmark. Finally, we provide a standardized evaluation setup and report baseline results on frozen evaluation subsets, demonstrating a climbable signal that measures the current frontier of automated reasoning on research-level mathematics.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15493

The Illusion of Diversity: Aligning LLM Exploration via Effective Entropy

Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Cong Qin, Binbin Zheng, Chaowen Hu, Zekai Shao

原文摘要

Reinforcement learning with verifiable rewards has shifted the alignment paradigm of large language models from subjective preference to objective correctness, yet a fundamental disconnect persists between exploration diversity and reasoning validity. Existing strategies predominantly rely on "blind" entropy metrics, e.g., token-level or global sequence-level entropy, which structurally fail to distinguish between effective reasoning and potential hallucinations. This misalignment creates an illusion of diversity, where high entropy tends to signal chaotic degeneration rather than valuable exploration. To bridge this gap, we introduce Effective Entropy, a validity-aware entropy concept that quantifies diversity exclusively within the valid subspace and systematically filters out the noise of incorrect trajectories. Built on this concept, we instantiate VEPO, a simple Validity-aware Entropy Policy Optimization method that directly incorporates effective entropy into RLVR training. VEPO induces an adaptive attraction dynamic that drives up the probability of under-explored valid trajectories, a mechanism that matches the practical regime of large-scale autoregressive models where sequence probabilities remain extremely small. Experiments on six mathematical reasoning benchmarks with 1.5B and 7B DeepSeek-R1-Distill-Qwen models show consistent aggregate accuracy gains over GRPO and competitive repeated-sampling success. A direct evaluation with matched correct counts finds more distinct strategies on commonly solved MATH500 problems, supported by paired statistical tests and three-seed training comparisons.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15491

What Makes a VLA Reactive? A Study of Execution Strategies for Dynamic Manipulation

Zhuoyue Li, Zhendong Han, Pankhuri Vanjani, Wenting Li, Rudolf Lioutikov

原文摘要

Vision-language-action (VLA) models predict chunks of future actions, and when objects move, those chunks go stale before they are executed. We study what makes a pretrained VLA reactive, using \pihalf{} on two dynamic simulation benchmarks and three real-robot tasks. We vary the prediction and execution horizons, compare synchronous and asynchronous inference, test methods that deliver actions sooner or keep successive chunks continuous, and adapt the policy with motion cues and latent-space reinforcement learning. The best prediction horizon is about one second, and the best execution horizon depends on the checkpoint. Short horizons help more with asynchronous execution, and methods that keep the trajectory continuous outperform those that only reduce latency. Adapting the policy repairs targeted failures, but on the conveyor task changing the execution horizon gained as much. Reactivity depends on the execution pipeline as much as on the policy, so both should be evaluated together.

cs.RO · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2503.08907

From Models To Experiments: Shallow Recurrent Decoder Networks on the DYNASTY Experimental Facility

Stefano Riva, Andrea Missaglia, Carolina Introini, J. Nathan Kutz, Antonio Cammi

原文摘要

The Shallow Recurrent Decoder networks are a novel paradigm recently introduced for state estimation, combining sparse observations with high-dimensional model data. This architecture features important advantages compared to standard data-driven methods including: the ability to use only three sensors (even randomly selected) for reconstructing the entire dynamics of a physical system; the ability to train on compressed data spanned by a reduced basis; the ability to measure a single field variable (easy to measure) and reconstruct coupled spatio-temporal fields that are not observable and minimal hyper-parameter tuning. This approach has been verified on different test cases within different fields including nuclear reactors, even though an application to a real experimental facility, adopting the employment of in-situ observed quantities, is missing. This work aims to fill this gap by applying the Shallow Recurrent Decoder architecture to the DYNASTY facility, built at Politecnico di Milano, which studies the natural circulation established by internally heated fluids for Generation IV applications, especially in the case of Circulating Fuel reactors. The RELAP5 code is used to generate the high-fidelity data, and temperature measurements extracted by the facility are used as input for the state estimation. The results of this work will provide a validation of the Shallow Recurrent Decoder architecture to engineering systems, showing the capabilities of this approach to provide and accurate state estimation.

cs.LG · physics.comp-ph · physics.flu-dyn

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15490

ActionCodec2: A Streaming Action Tokenizer

Zibin Dong, Yicheng Liu, Shiduo Zhang, Tianyuan Yuan, Baijun Ye, Jinqiu Wang, Hang Zhao

原文摘要

Most action tokenizers for autoregressive vision language action (VLA) models compress motion into chunks that must be decoded in full before their actions become executable. We introduce ActionCodec2, a non-neural streaming tokenizer that releases actions incrementally while keeping trajectory reconstruction error within a prescribed tolerance. Its encoder quantizes each step relative to the decoder's reconstructed state, so the selected motion primitive corrects residual error rather than allowing errors from independently quantized increments to accumulate. Finding the smallest such primitive set is a geometric covering problem; we derive the exact minimum for translation and constant-factor-tight bounds for rotation. Set-BPE then losslessly merges co-occurring primitive symbols across coordinates and neighboring steps, without a fixed coordinate ordering. A universal version fitted on 20k hours of data from 24 embodiments averages 8.8 tokens per second for 15 Hz end-effector motion on this corpus. With the same VLA backbone, ActionCodec2 outperforms the compared tokenizers on three simulation benchmarks and in zero-shot real-robot evaluation. Its streaming representation allows policies to incorporate state feedback within an action chunk, substantially improving performance over open-loop execution under randomized dynamics, external disturbances, and moving objects. The same tokens also can serve as a direct control interface for VLM agents, which compose successful action sequences into reusable macros. These agent-built macros reduce control decisions and thinking-token usage across attempts and transfer to a held-out task. More results are available at https://zibindong.github.io/actioncodec2-page/

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15489

Taxonomizing Synthetic Data for Law

Ignacio Cofone, Katherine J. Strandburg, Nicholas Tilmes

原文摘要

Synthetic data is increasingly important in data usage and AI design, creating novel legal and policy dilemmas. All too often, discussions of synthetic data treat it as entirely distinct from "real," collected data, overlooking the risks posed by different kinds and uses of synthetic data. We build on Michal Gal and Orla Lynskey's argument that synthetic data will transform information privacy, market competition, and data quality. While the risks posed by synthetic data depend on its connection to collected data, we argue that background knowledge and assumptions about ground truth used to create it are at least as important. We bring that focus to Gal and Lynskey's taxonomy of synthetic data, arguing that this focus is essential to grasp synthetic data's legal and policy implications. As such, we divide synthetic data into (1) transformed data, which modifies collected data to preserve certain statistical properties for an end use; (2) augmented data, which relies on assumptions to bolster a collected dataset's fidelity to the ground truth; and (3) simulated data, which relies almost entirely on background knowledge and ground-truth assumptions. Applying this taxonomy, we show that no category of synthetic data prevents privacy harms from group-based inferences, that augmented and simulated data can amplify bias while making a dataset look more complete, and that synthetic data rarely lets smaller competitors overcome incumbents' data advantages. As policymakers weigh whether to incentivize, mandate, or discourage the use of synthetic data, they should consider the validity of the ground-truth assumptions used in producing that data.

cs.CY · cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗