arXiv:2608.28905v1 Announce Type: new Abstract: Generative recommenders increasingly emit semantic IDs (SIDs): each item is a short sequence of hierarchical discrete codes from a residual quantizer, decoded autoregressively. Before spending scarce A/B-test, a team may decide offline which decoder or reranking variants are worth testing - a job for off-policy evaluation (OPE). We ask a simple question: can the model's own SID tree serve as the action abstraction for that OPE? Our answer has three parts. (i) Under the near-argmax logging real recommenders use, per-item OPE is hopeless - as item-level effective sample size is usually small on production logs - but marginalizing items to code-prefix clusters restores estimable support and cuts error. (ii) This gain is thanks to coarsening, no…

arXiv:2608.28896v1 Announce Type: new Abstract: Industrial process networks do not maintain a single effective topology while operating: streams are throttled or bypassed, and units move between idle, transition, and active regimes. Models of such systems are typically trained on measured state trajectories while the operating mechanisms that generated them remain latent, and an unconstrained graph network can fit such a trajectory without assigning stable physical meaning to the recovered routing. We address both problems with the Conservative Hybrid Graph Network (CHGN), which learns routing, regime assignment, and removal rates as data-driven surrogates and inserts them into a fixed transport equation, so that the mass balance holds by construction for any predicted routing. CHGN train…

arXiv:2608.28859v1 Announce Type: new Abstract: Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of thought runs about twice as long as the model's own answer probability takes to settle, and how much of that excess is removable varies from problem to problem, so a global length penalty cannot take it out. We take it out by internalizing a causal interpretability finding into the weights. The mechanism is a halt vector: a difference-of-means direction at layer 18 of this model whose steering strength controls how long it thinks, while a replicated value axis does nothing. Installing that intervention in the weights is harder than it looks. Maximizing the scalar projection onto the direction corrupts the off-axis dimensions a frozen downstrea…

arXiv:2608.28853v1 Announce Type: new Abstract: Equivariant graph neural networks provide a principled way to model geometric systems, but efficient first-order architectures remain limited in how vector information can be transformed as it moves across a graph. We introduce \textsc{ESNN}, an Equivariant Sheaf Neural Network that enriches this interaction by learning directed, matrix-valued transport between neighboring vector features while preserving exact Euclidean equivariance. Rather than increasing the order of the representation, ESNN keeps scalar and vector features first-order and places the additional geometric flexibility in the edge transport itself. We characterize this transport theoretically, showing that when relative displacement is the only covariant geometric input, eve…

arXiv:2608.28843v1 Announce Type: new Abstract: We show that smooth two-layer feed-forward networks (FFNs) expose an additional structural model extraction channel under a chosen-input raw-output oracle at the FFN branch; consider transformer FFN branches with GELU or SiLU activations under chosen-input raw-output access, without access to parameters, gradients, or internal activations; exploit a second-order leakage channel in which projected input Hessians form different mixtures of the same hidden symmetric rank-one factors induced by the FFN input weights. We formalize resulting Hessian collection as a partially symmetric decomposition to establish conditions for local identifiability and stability to exploit vector-output stencil reuse to reduce the structural query cost by a factor…

arXiv:2608.28840v1 Announce Type: new Abstract: Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible, yet they can be nearly the same up to some class of transformations. While there exists many methods for alignment between different latent spaces, it is typically done using a set of shared sample correspondences, known as anchors. This leaves a fundamental question: are the geometric signatures of different latent spaces representing similar data sufficient to recover an alignment between them? To that end, we introduce HGA (Hyperspherical Gaussian Alignment), a method that directly optimizes a transformation between two latent spaces by maximizing a geometric measure of "fit" between them.…

arXiv:2608.28771v1 Announce Type: new Abstract: Large reasoning models achieve strong performance on complex tasks by generating extended chain-of-thought (CoT) traces via reinforcement learning with verifiable rewards (RLVR). While current RLVR methods have achieved strong results with correctness-based reward signals, they provide limited guidance on the quality of the reasoning process itself, leaving the internal reasoning structure largely unoptimized. Through empirical analysis across multiple model families, we identify a consistent pattern: correct reasoning trac es exhibit more frequent and larger token-level entropy drops within the thinking phase than incorrect ones. We propose ERR+, a two-phase RLVR framework grounded in this observation. The first phase trains with the Entrop…

arXiv:2608.28600v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance on mathematical reasoning benchmarks, yet the mathematically meaningful skills underlying their reasoning remain underexplored. We introduce \texttt{SHAPE}, a framework that analyzes Chain-of-Thought (CoT) trajectories through two lenses developed in mathematics education: (1) semantic spaces: the model's evolving mathematical interpretations of a problem (e.g., algebraic, geometric), and (2) heuristics: the specific mathematical actions taken within those spaces (e.g., simplifying the problem, working backward). We first use \texttt{SHAPE} to analyze the reasoning patterns of various models. Our findings reveal that the mathematical heuristics employed by a model better explain final a…

arXiv:2608.28599v1 Announce Type: new Abstract: Clinical diagnosis is a step-by-step, cost-aware process: a physician orders examinations one at a time, observes the results, and updates the diagnosis before reaching a final conclusion. Most medical language models instead treat diagnosis as a one-pass classification task and ignore the trade-off between a test's value and its cost. We model diagnosis as a cost-aware sequential decision process and train the policy with reinforcement learning. The main difficulty is credit assignment: the only reliable signal comes once at the end of a long trajectory, so it scores a wasteful workup the same as an efficient one. We propose CDPR (Counterfactual Diagnostic Process Reward), which needs no expert labels and no learned critic. CDPR first finds…

arXiv:2608.28597v1 Announce Type: new Abstract: Online surveys are a foundational data collection instrument in a variety of fields, with attention checks serving as critical guardians of response quality. However, the rapid emergence of agentic AI (goal directed systems powered by a large language model (LLM) brain and/or a multimodal processing unit with tool-augmented capabilities) raises new questions about the robustness of these safeguards. We investigate how well agentic AI architectures can complete web-based surveys and pass standard attention checks. We evaluate a single-agent architecture capable of multimodal input processing and tool-based web interaction on a controlled survey sandbox. We analyze the problem from two perspectives. From an attack perspective, we demonstrate h…

arXiv:2608.28596v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly embedded in scientific workflows for literature analysis, drafting, and review. Existing systems advance autonomous discovery and manuscript generation, but do not resolve the governance problem that arises when ideas, methods, results, and claims propagate through AI-assisted workflows without mandatory human approval or artifact-level traceability. This paper proposes Paper Pilot, a human-in-the-loop expert system for evidence-traceable scientific manuscript generation in applied sciences. It adapts the Collaborative Agent Reasoning Engineering (CARE) methodology to manuscript development through manuscript-owner approval gates, explicit no-pass criteria, claim classification, audit loggin…

arXiv:2608.28595v1 Announce Type: new Abstract: Biomedical NLP pipelines routinely presuppose clean input text, yet large-scale corpora assembled through automated PDF parsing harbour pervasive OCR-like artifacts, token splits and merges, hyphenation remnants, and character-level corruption, that systematically erode lexical evidence and degrade downstream classifiers. We introduce a conservative, fully auditable spell-correction reliability layer conceived as a safety-oriented preprocessing module rather than a maximal-accuracy corrector: under conditions of uncertainty, the system abstains from editing, in accordance with a medical do-no-harm philosophy. The deterministic architecture couples bounded edit-distance candidate generation with corpus-derived n-gram scoring and a suite of bi…

arXiv:2608.28594v1 Announce Type: new Abstract: Conversational analytics systems assume the user already has a well-formed question, leaving a non-expert facing a blank query box on an unfamiliar enterprise schema. Commercial 'proactive' tools narrow this gap only by detecting statistical anomalies over analyst-curated metric layers, and academic next-question recommenders depend on query logs that a fresh dataset lacks. We describe a production analytics system that inverts the interaction model from question-first to analyst-first through two coupled architectural ideas. First, a pluggable domain-expert 'skill' abstraction: a folder-based, database-free subject-matter pack (a manifest, per-stage prompt facets, keyword-routed references, report templates, and optional compute) auto-selec…

arXiv:2608.28593v1 Announce Type: new Abstract: With the increasing development of AI regulatory frameworks, ensuring that artificial intelligence systems, particularly generative models, operate in accordance with legal and ethical standards has become a critical priority. Existing proposals for AI alignment and value-guided behavior, however, face some limitations. Approaches such as Constitutional AI depend on human supervision, while broad normative frameworks like the Good-for-Humanity (GfH) principle may be overly general and ambiguous to provide actionable governance guidance. To overcome these limitations, we propose a hybrid approach called Statutory AI that employs pre-existing human-authored principles drawn from specific themes within a legal corpus. Specifically, Statutory AI…

arXiv:2608.28592v1 Announce Type: new Abstract: Large language models (LLMs) achieve high scores on medical knowledge examinations, yet real-world oncology is not a knowledge test--it is a sequence of guideline-pathway choices, escalation judgments, and commitments under uncertainty. Existing benchmarks largely measure factual recall, leaving open whether frontier LLMs share decision-path blind spots that combining models cannot fix. We built the Oncology Decision Boundary Benchmark (ODBB)--2,005 oncology decision points across NCCN guidelines and colorectal cancer cases--and evaluated nine frontier LLMs (four closed-source, five open-weight families) released between June 2025 and April 2026. A fully deterministic scorer (zero LLM inference) classified outputs into 14 failure types, inde…

arXiv:2608.28591v1 Announce Type: new Abstract: Recent advancements in AI are helping scientists achieve breakthroughs in fields such as mathematics, medicine, and materials sciences. New evaluation datasets for AI models contribute to such advancement in AI. In the STEM domain, frontier models have consumed most of the available online data, creating the need for human-created datasets that codify the knowledge of leading experts in the domain. There are several STEM datasets available for the research community in this field. However, there are some gaps in these datasets, leaving room for improvement. Examples of gaps include (1) saturation in model performance on these datasets, leaving no head-room for meaningful evaluations, (2) skewed taxonomy distributions, (3) multiple choice que…

arXiv:2608.28590v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown promise for automating data-science workflows, yet their end-to-end performance depends critically on the agent harness that represents tasks, manages execution state, constrains output artifacts, and provides evaluation feedback. Existing data-science agents often leave this harness implicit, making results difficult to reproduce, compare, and attribute across heterogeneous tasks. We introduce DS-Lighting, a unified harness toolkit that makes harness design explicit for data-science automation. DS-Lighting decomposes the harness into four reusable layers: data, workflow, execution, and evaluation, and represents diverse agents as executable operator programs that support both predefined pipelines…

The PhD student works to give young people an active role in shaping digital technologies that can support their own well-being.

Discussion | Link

Your companion from the airport to the hotel meet travelers, and a smart assistant keeps you safe Seatlr is a social network for travelers worldwide: enter your flight number and instantly join a chat room with everyone…

v2.3.6·What's new→ The coding agent that runs on your machine. Offline, at zero token cost, with your choice of model, and it asks before it changes a single line. Download GIDE ✓30-day trial · no card Other platforms &…

Speed and accuracy usually pull against each other in text-to-speech. Gradium AI's new default model reports both: an 81.0% human-rated pass rate on 500 hard sentences across five languages, at 216 ms P50 time-to-first-audio on Coval. The evaluation set is open on Hugging Face under CC BY 4.0. The post Gradium AI Releases New Default TTS Model: 81.0% Hard-Case Pass Rate at 216 ms Time-to-First-Audio appeared first on MarkTechPost.

Notifications You must be signed in to change notification settings Fork 2 Star 17 BranchesTags Open more actions menu Latest commit History 18 Commits 18 Commits Folders and files NameName Last commit message Last comm…

Weird little guys of FOSS This is a list of weird little guys in the free software movement and adjacent spaces. Request additions, removals, or changes via email; patches welcome. Don’t harass these people! Don’t engag…

See how Gilbert + Tobin combines CEO-led commitment, rigorous governance, and human accountability to scale ChatGPT Enterprise and Codex across the firm.

Inworld TTS Open Evaluation Toolkit: Reproducible TTS Evals Get started 08.28.2026 Introducing the Inworld TTS Open Evaluation Toolkit An open customizable framework for reproducible, inspectable TTS evaluation. Summari…

MU/TH/UR 6000 — Free Anonymous AI Chat Terminal (No Login) SYSTEM ONLINE __ __ ___ _ _ ___ ___ ___ ___ ___ ___ _ _ ___ ___ | \/ | __| | | | _ \ | _ \ __| _ \_ _/ __| || |/ __| __| | |\/| | _|| |_| | / | / _|| /| | (__|…

PDFs full of charts and tables are notoriously hard to put through a traditional RAG pipeline. In this post, we show how late-interaction multi-vector retrieval lets you search PDFs by what the page looks like: no OCR, no chunking, no text extraction.

Introducing wrapture New from Graham Dumpleton (of wrapt, mod_wsgi, and New Relic's Python agent fame), who describes Wrapture as taking the monkeypatching ideas from wrapt and extending them to apply to testing and tracing at the same time. Wrapture (full documentation here) makes it easy to wrap any function or method such that all access can be traced, or can be overridden to return a different value. It acts as both an alternative to unittest.mock and a way to implement tracing against an existing project: Attaching observation to code you do not control, recording what flows through it, and doing so without disturbing the program being watched, is a problem I have never really stopped thinking about. Wrapture includes OpenTelemetry support and even has an entirely configuration-based…

Google Search If you're having trouble accessing Google Search, please click here, or send feedback.