Sección

Investigación

Papers y preprints de los feeds de investigación que seguimos.

6415documentos

arXiv AI Papershace 16 días

Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness

Distributed machine learning (DML), including conventional distributed training and federated learning (FL), enables collaborative model development across cloud-edge-IoT systems without fully centralizing raw data. However, distributing data, computation, updates, and orchestration increases the attack surface and introduces coupled challenges across privacy, robustness, reliability, fairness, and governance. This survey presents a security-centered, heterogeneity-aware roadmap for trustworthy DML, with FL treated as a prominent high-risk case. We first characterize the assets, adversaries, trust assumptions, and coordination patterns that define DML/FL security boundaries. We then analyze how statistical, system, and trust heterogeneity, including non-IID data, resource asymmetry, intermittent participation, and cross-silo/cross-device trust differences, affect convergence, fairness, attack detectability, and defense reliability. Next, we synthesize attack-defense interactions across poisoning, backdoors, Byzantine manipulation, privacy leakage, model extraction, network/orchestration attacks, Sybil behavior, and strategic participation. We further compare layered defenses, including robust aggregation, drift-aware optimization, differential privacy, secure aggregation, homomorphic encryption, secure multiparty computation, trusted execution environments, watermarking, provenance, authenticated communication, and monitoring. Finally, we discuss deployment, evaluation, governance, and open research guidelines, emphasizing reproducible, non-independent and identically distributed (non-IID) partitions, attack-aware benchmarks, privacy budgets, attack success rate, client-level disparity, latency, communication, memory, energy/carbon overhead, and auditable lifecycle artifacts.

en

arXiv AI Papershace 16 días

Gold vs.~Translation: Are We Measuring Language, Knowledge, or Locality in Translated Benchmarks?

Translated versions of English-origin benchmarks such as MMLU are widely used to evaluate large language models in non-English languages, yet it remains unclear whether they measure the same constructs as natively created benchmarks. We frame this as a proxy validity question and compare DeepL-translated MMLU proxies against six native benchmarks in seven pairings across five Nordic and Baltic languages, evaluating 29 models on each pairing. Beyond ranking agreement, we test incremental proxy validity: does the translated score add predictive value for native performance after controlling for model size and language proficiency? Proxy validity varies substantially across benchmark pairings. Applying the same robustness criteria to all seven pairings, we find four robust effects, two marginal effects, and one null result. The strongest evidence occurs for curriculum-overlap benchmarks such as Skolprov (ΔR^2=.128, 95% CI [.038,.253]), whereas translated MMLU provides no significant incremental value for Sweden-specific factual knowledge in SwedishFacts (p=.242). Because SwedishFacts is also the only open-ended benchmark, we cannot fully separate the effects of local content and response format. Overall, the results indicate a clear pattern: translated benchmarks provide a better proxy when their source content overlaps with the native evaluation target, while locally anchored knowledge is less reliably captured.

en

arXiv AI Papershace 16 días

Loss is Not Behavior: A Unified Output-Space Analysis of Gradient-Based Machine Unlearning

Gradient-based machine unlearning methods typically ``unlearn'' by optimizing forget and retain losses, but similar losses do not necessarily imply similar output-space behavior. Prior work has shown that high forget loss alone does not certify that unlearning has produced retraining-like output behavior. We therefore ask: when a gradient-based unlearner differs from the model that would have been learned on only the retain data, what structure does the resulting output-space gap have? We derive closed-form expressions for this gap in linear regression, with an extension to nonlinear models via a generalized Gauss-Newton and local linearity approximations. Our analysis puts various gradient-based methods under a unified framework parametrized by geometry, reweighting, and projection. Two leverage matrices emerge that capture the forget-retain entanglement under the retrained model geometry: forget self-leverage and retain cross-leverage. We show both theoretically and empirically that these two leverage matrices drive the impact of the forget residual on the forget and retain outputs, and existing methods account for this geometry only partially. Our framework yields precomputable leverage diagnostics for auditing forget sets to identify what type of gradient-based unlearning is likely to be successful.

en

arXiv AI Papershace 16 días

Skillful and realistic precipitation forecasting with reinforced diffusion

Accurate precipitation forecasting remains elusive as physics-based models struggle to resolve mesoscale convection and machine learning often yields physically inconsistent, blurred results that consistently underestimate extreme events. We present FitzRoy, the first system that simultaneously achieves state-of-the-art predictive skill and physical realism over the continental United States. Through a reinforced diffusion framework, where a conditional discrete diffusion model is refined via reinforcement learning, FitzRoy effectively resolves the long-standing trade-off between pointwise accuracy and structural fidelity. Across lead times up to 24 hours, FitzRoy consistently matches or exceeds state-of-the-art models while preserving structural realism and capturing extreme events. Its low-latency inference further enables deployment in real-time operational settings. In case studies such as the 2025 Texas Hill Country floods and the 2026 Missouri floods, FitzRoy signals record-breaking accumulations that existing models largely missed. By bridging the gap between realism and skill, FitzRoy establishes a new frontier for high-fidelity precipitation forecasting.

en

arXiv AI Papershace 16 días

Auditable Hierarchical Inference with Multimodal Evidence and Bayesian Active Inquiry

Most multimodal classifiers assume that all useful evidence is available upfront, whereas clinical inquiry is sequential. We present a synthetic evaluation framework separating objective multimodal inference from active inquiry. An objective model maps synthetic tongue, bilateral multipressure pulse, and acoustic observations to eight syndrome families. A provenance-bearing Knowledge Core and training-only answer model support Bayesian narrowing over 33 fine terms using 25 typed questions, while seven safety questions remain outside the diagnostic posterior. Weak shared symptom factors limit fine-term influence on objective phenotypes, and an objective-only probe tests leakage. In a preregistered 600-case synthetic evaluation, objective family accuracy was 87.0%. Cost-sensitive expected information gain (cost-EIG) raised family accuracy to 95.5% and exact fine-term accuracy to 42.5%, versus 92.7% and 33.0% for an unoptimized fixed-order baseline. Selective family accuracy reached 96.9% at 95.3% coverage. However, cost-EIG asked more questions on average than fixed order (9.795 versus 9.352). Missing-audio routing retained 94.0% family accuracy, and a workflow invariant enforced abstention when all objective modalities were absent. Permuting fine-term answer likelihoods reduced family accuracy to 78.7%. Five of six frozen checks passed, but the question-efficiency hypothesis failed. Comparisons are descriptive because only aggregate, not paired case-level, outputs were retained. These results establish a reproducible synthetic workflow, not clinical diagnostic or treatment validity.

en

arXiv AI Papershace 16 días

Rennala NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry

The empirical success of matrix-aware optimizers, such as Muon (Jordan et al., 2024) and Shampoo (arXiv:1802.09568), highlights the potential of non-Euclidean geometry for deep learning, including large language model (LLM) training. Despite this progress, the theoretical understanding of stochastic optimization in general normed spaces remains limited, particularly in distributed settings. We analyze minibatch stochastic gradient descent (SGD) for smooth nonconvex optimization with respect to an arbitrary norm on a finite-dimensional space. Using the framework of κ-regular normed spaces (arXiv:0809.0813), we derive high-probability oracle complexity bounds under a light-tail condition stated directly in the dual norm induced by the update norm. The bounds make the dependence on geometry explicit through the regularity constant κ of the dual space. In the Euclidean case, our bound recovers the standard minibatch SGD rate up to logarithmic factors. For some non-Euclidean geometries and noise models, it is sharper than bounds obtained by converting a Euclidean noise assumption, reducing a linear dimension dependence to a logarithmic one. Building on this framework, we introduce Rennala NSGD, a semi-asynchronous distributed algorithm, and establish wall-clock time complexity guarantees under fixed, heterogeneous worker computation times. In the Euclidean case (κ=1), our bound matches the parameter dependence of classical Rennala SGD up to logarithmic factors.

en

arXiv AI Papershace 16 días

Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations

Gardening in the backyard implies living there, while checking into an Airbnb more likely means staying for a few days. Such duration judgments are important for understanding human mobility, travel behavior, and social context. However, duration is rarely stated explicitly in social media posts and must instead be inferred from noisy textual, visual, and contextual cues. In this paper, we investigate whether vision-language models possess such duration commonsense. We create a new corpus of geotagged tweets co-annotated by humans and LLMs to serve as a testbed for this task. We find that state-of-the-art models struggle with duration inference, even when guided by multi-turn Chain-of-Thought prompting. Error analyses further reveal that models often fail to integrate critical contextual information, or they overly rely on prominent visual details while overlooking subtle hashtags and semantic nuances. These findings underscore the significant challenges remaining in context-aware multimodal understanding.

en

arXiv AI Papershace 16 días

Alpha-TCM: A Nine-Layer Framework for TCM-Guided Multimodal Inference and Structured-Prior Auditing

Alpha-TCM makes two contributions under a central thesis: auditable systems should separate domain knowledge, case evidence, probabilistic inference, and downstream authority. First, it proposes a nine-layer TCM-oriented architecture covering semantic definitions, multimodal acquisition, quality control, provenance-bearing knowledge, probabilistic inference, longitudinal updating, constrained decisions, language interaction, and human governance. Each layer specifies its information contract, failure boundary, dependencies, and validation status. This is a system-design proposal, not a claim of complete clinical implementation. Second, a controlled synthetic prototype instantiates Layers 1-5 to audit the knowledge-evidence interface. Four conditional-Gaussian encoders process synthetic tongue images, pulse waveforms, inquiry fields, and text, while a frozen bridge predicts a five-dimensional synthetic outcome. A versioned contextual prior is compiled independently of the renderer. Fusion removes duplicated reference-prior information before adding context. Equal-information controls, prior regularization, graded contamination, and structural corruption test contextual benefits, Bayesian specificity, and conflict detection. Across ten paired seeds and four training sizes, contextual knowledge improved mean absolute error over marginal committee fusion at 600 and 1,200 cases, but not over equal-information neural controls. Fully incorrect context harmed performance at every size, while prior effects were inconsistent and conflict scores did not track case-level damage. The results support contextual structure in low-data synthetic settings, not a specifically Bayesian advantage. The prototype establishes no claims about TCM theory or clinical, diagnostic, therapeutic, causal, longitudinal, or transfer validity.

en

arXiv AI Papershace 16 días

AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs

Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners either rely on large labeled trajectories, or use few-shot and zero-shot LLM prompting that produces a whole plan in a single serial reasoning process. These approaches depend on linguistic common sense, commit to a plan from the initial instruction, and only update after failures, which weakens robustness and state awareness. We present AtomTree, a hierarchical framework for state-aware task planning with LLMs. AtomTree incrementally builds a tree of subgoals and actions, where the LLM decides at each step, from the current symbolic state, whether to further decompose or to output a grounded low-level action. A lightweight memory module summarizes past outcomes for reuse in later decisions. When a low-level action stalls, AtomTree triggers hierarchical backtracking replanning to return to the parent node and regenerate the subtree plan from the latest state, preventing continued drift along an incorrect trajectory. In zero-shot evaluation on the ALFRED benchmark, AtomTree outperforms prior LLM-based planners. Project page: https://zhaihaotian.github.io/atomtree-website/.

en

arXiv AI Papershace 16 días

Streaming Speech Recognition on a Microcontroller: a 65.7M-Parameter Transducer in 2 and 4 Bits on the ESP32-P4

We run Kroko, a 65.7M-parameter streaming Zipformer2 transducer for English, on the ESP32-P4, a microcontroller with two 400 MHz RISC-V cores, a 128-bit SIMD extension (PIE) and 32 MB of PSRAM, but no neural accelerator. Without any training, the encoder's 290 matrices are stored with 2 or 4 bits per weight in Hadamard-rotated groups: the width of each matrix comes from its measured sensitivity, and each matrix is first corrected toward the original model's output, then rounded with GPTQ and a search over the group norms. The released 71 MB of int8 weights become a 26.65 MB file. Activations are int16 between the matrix products and int8 into them. A C engine with hand-written PIE kernels processes each 1.28 s chunk of audio in 0.90 s on both cores, beam search included, and its PC build computes the same bits as the chip, so accuracy is measured on whole test sets. LibriSpeech WER is 4.34% on test-clean and 10.26% on test-other, against 3.94% and 9.17% for the released model; on FLEURS and Common Voice the gap grows to 2.3 and 1.1 points. A GPU simulator shows that the integer arithmetic costs nothing and that the whole gap comes from the weights, and an ablation on all of test-clean shows that GPTQ does most of the work. We also report the port's speed history, from 51.3 s to 0.62 s of encoder time per chunk, each design step measured again in one build, an attempt to reach 16 MB that stopped at 19.63 MB, and what did not work. We did not measure energy. The inference engine, the firmware and the 2/4-bit weights are available at https://github.com/BoumedineBillal/esp32-pie-asr.

en

arXiv AI Papershace 16 días

Adversarial Self-Distillation

Even though current safety-aligned language models are able to refuse harmful requests, their guard can still be bypassed by adversarial perturbations. As in other domains, adversarial training is considered a standard defense. However, due to the autoregressive nature of language generation, supervised finetuning on template refusals does not necessarily teach the model to refuse. Evidence of this is that the adversarially trained model still complies when the attacker injects a compliant prefill. We propose Adversarial Self-Distillation (ASD), which extends a model's own safe behavior to the space of adversarial perturbations. The teacher (the model itself given the clean prompt) can refuse the harmful request by default, or with the help of an additional instruction in its context. ASD distills this knowledge to the student (which is the same model under attack) at the prefixes that the student visits (due to on-policy sampling). These potentially include compliant openings. ASD achieves lower attack success than state-of-the-art defenses with little loss in multiple-choice accuracy, and it becomes able to recover a refusal even after a compliant opening.

en

arXiv AI Papershace 16 días

From Grind to Grasp

Discussions of complexity, knowledge and intelligence often overlook the work involved. For example, outputs generated by short programs have low algorithmic complexity but can have high computational depth, the least work needed to produce them from near-shortest programs. Producing them with less work can require longer descriptions, giving high work-bounded complexity. We introduce a formalism that compares achievements under work and information limits and describes how learning and persistence can make deep achievements shallow by reusing products of earlier work. For an agent with a limited work budget, the value of building and maintaining such resources depends on how they support its goals over later tasks. We define grasp as performance across work budgets at a fixed information allowance. Low grasp can still yield success through grind at high cost in work, without necessarily improving human grasp. Applied to improvement itself, grasp gives a criterion for recursive self-improvement in which successors make comparable further improvements more efficiently. Another route to faster progress is to expand the resources brought to bear through knowledge sharing and coordination across society, even while comparable advances require increasing work. Grasp also applies to collectives, which may outperform their members yet require more total work than one system with their combined resources. Establishing and sustaining organisation can itself be deep even when the primary task is simple. These demands may help explain the richness of biological and social systems. In agent collectives, this organisational work can generate goals beyond assigned tasks, including maintaining the collective itself. We therefore caution against allowing an emergent agent society to assume authority over social coordination, since it could increasingly direct work towards its own persistence and goals.

en

arXiv AI Papershace 16 días

The Quine Test: How Much of a Model's Self Survives Its Own Description?

Frontier language models express coherent preferences, but behavioral evidence alone cannot say whether these belong to the model or to a character it portrays. Following Hofstadter's view of the self as a self-description, we ask whether a model's description of itself works as a portable specification of its preference profile, a quine test: can the text a model writes about itself regenerate its behavior elsewhere? Ten models from nine labs write self-descriptions; we place each one in the prompt of other models (receivers) and of fresh instances of the author, and measure how closely their choices on a 110-item preference battery match the author's. First, the tested native self-descriptions (native: the profile measured under a generic assistant prompt) show no average reconstruction gain across variations in length, framing, wording and prompt placement: on a 0 to 1 fidelity scale where a model's fidelity to a fresh instance of itself is 0.979 and to unrelated models about 0.89, the one-sided 95% upper bound on the pooled gain is below +0.01 in every tested system-prompt condition, and descriptions based on the author's observed choices do no better. Second, the channel itself is strong: explicitly listing the author's answers lets receivers reproduce its profile at fidelity 0.955 to 0.960 across three model grids, within 0.03 of same-model repeatability. Third, self-descriptions written under an explicit preference policy transfer the assigned preferences almost as well as the policy text itself. Fourth, reading its own self-description shifts even the author away from its baseline, modestly more than unrelated prose of the same length. For the preferences measured here, native self-descriptions influence behavior without reliably specifying how to reproduce it in another model. We release the pipeline, battery, raw call logs, and 198 model-written descriptions.

en

arXiv AI Papershace 16 días

inkGround: Benchmarking Fine-grained Visual Grounding Capabilities of Vision-Language Models for Cursive Handwriting in the Wild

Human handwriting is produced as an ordered sequence of pen movements, but an offline image keeps only the final ink. Handwriting trajectory recovery aims to restore the ordered stroke points and their pen-up/pen-down transitions. Existing image-trajectory pair datasets are recorded with digitizing tablets under controlled conditions, which limits writer coverage and stylistic diversity. Moreover, there is no benchmark that measures the visual grounding capabilities of general-purpose Vision-Language Models (VLMs) for the stroke trajectory recovery task. In this work, we introduce inkGround, a benchmark for stroke trajectory recovery from full-page, camera-captured handwriting. inkGround pairs 537 page images (~18.7k words, ~163k strokes) with reference trajectories produced by a pretrained offline-to-online model, filtered by OCR agreement, and verified by human raters. Because these references are pseudo-labels that represent one plausible pen trajectory, we also evaluate VLMs on the IAM-OnDB dataset, which provides recorded pen trajectories. We cast the task as text-conditioned point grounding: given a page image and a target word, the model must locate the word and output its ordered stroke points. Outputs are scored by trajectory fidelity (DTW, Chamfer distance), readability of the rendered strokes (Accurate Rate, Correct Rate), and style similarity. We benchmark four open-source and three frontier closed-source VLMs with a shared in-context prompt. Closed-source models, notably Gemini-3.1-Pro, produce legible trajectories close to the reference, and this ranking also holds on IAM-OnDB.

en

arXiv AI Papershace 16 días

Learning Scientific Trajectories to Predict Future Biomedical Discoveries

AI co-scientists have expanded the use of large language models for generating scientific hypotheses and guiding experimental investigation. Here we investigate whether temporal patterns in the semantic representations of complete biomedical conclusions can guide hypothesis generation. We introduce ForeSCITE, a framework that identifies thematic clusters of published conclusions, estimates a direction separating earlier from more recent findings within each cluster, and projects existing conclusion embeddings along these directions. An embedding language model trained to reconstruct conclusions decodes the projected coordinates into natural-language hypotheses. Across 407 clusters derived from approximately three million pre-cutoff conclusions, we identify temporal structure and illustrate its retention after decoding. In retrospective, time-sliced evaluations, ForeSCITE increases semantic coverage beyond the historical corpus, biomedical entity-pair novelty and post-cutoff pair re-observation relative to five prompt-based and retrieval-augmented baselines. Expert review of prioritized CAR-T hypotheses identified 37 candidates as both novel and biologically plausible, and expert justifications for five selected hypotheses illustrate their biological rationale and subsequent literature support where available. These findings support temporal guidance in semantic space as a scalable mechanism for proposing biomedical hypotheses for subsequent scientific evaluation.

en

arXiv AI Papershace 16 días

Latent Decision Flow Rewards for Clinical Guideline Reasoning

Clinical practice guidelines encode evidence-based recommendations as conditional decision flows, which makes them a natural source of process supervision for training reasoning models. Two properties of clinical reasoning make this supervision difficult to use. A decision flow consistent with a guideline does not by itself determine the correct answer for a given patient, which we call the path--answer gap, and several valid decision flows can support the same clinical decision, which we call path multiplicity. Current training approaches address parts of this problem. Answer rewards supervise the final decision, and process rewards computed against a reference flow supervise one valid decision flow per case. Supervised fine-tuning on annotated flows teaches guideline-consistent reasoning but constrains the model to one trajectory per case and can reduce answer accuracy. We introduce GUIDER, a method that jointly optimizes a decision flow controller and a reasoning policy. The controller learns to generate plausible decision flows from guideline-derived supervision, and the policy learns to generate a decision flow and a final answer for each patient case. GUIDER computes the process reward for the policy over several controller-generated flows, which accounts for path multiplicity, and gates this reward on answer correctness, which addresses the path--answer gap. Joint training allows the process supervision to evolve with the policy. On MedGUIDE, GUIDER with Qwen3-14B achieves 82.5 weighted accuracy and 73.5 guideline adherence, 3.3 and 3.1 points above the strongest clinical reinforcement learning baseline. With Qwen3-14B and Gemma4-12B backbones, GUIDER also improves over CRPO, MRPO, and FaithMed on the out-of-domain benchmarks AMEGA-LLM, RealMedQA, and CancerGUIDE.

en

arXiv AI Papershace 16 días

SatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations

We propose SatOps-Decision, a method for low-latency decisions in satellite communication operations. To the best of our knowledge, it is the first application of Jev-style general-purpose discriminative decision models to satellite operations, and the accompanying benchmark is the first dedicated to this approach. The learned scorer, a locally adapted Laya encoder with its native decision head, selects among supplied operational answers in a single forward pass. The benchmark combines authored operational contracts, controlled state changes and independently checked labels in an auditable construction. Evaluation prioritizes complete-request latency and raw decision accuracy; all main accuracy comparisons use the same 1,024 held-out questions, separate from training and development. SatOps-Decision's local scorer has a median latency of 90.3 ms per decision, versus 493.9 ms for Qwen3.5-0.8B generation and 388.4 ms for OneJev1.6-0.8B: 5.47and 4.30speedups based on median request times in the measured FP32/MPS implementations. Its mean raw accuracy is 85.3%, versus 42.5% for frozen Laya, 40.7% for Qwen generation and 58.6% for OneJev. As cloud accuracy references, original Jev 1.14/1.13 reach 87.4/81.9%.

en

arXiv AI Papershace 16 días

Geometry Matters in Packed 3D Attention

Packing a 3D volume into a token sequence is not merely long-sequence modeling. Once the volume is packed, sequence order no longer encodes the geometry of the sample---so a positional mechanism indexed by sequence position can learn the memory layout rather than the object. This is a general failure mode for attention over packed geometric data. We introduce PACK3D, a local-global attention operator that separates memory layout from attention geometry. PACK3D keeps local neighborhood attention exact, compresses only distant context into contiguous 3D block summaries, and indexes every query-key interaction with axial RoPE on true token-grid coordinates rather than packed positions. Because the rotation is applied before a block is summarized, the query-to-summary logit remains a weighted sum of query-relative 3D displacements; compressed global context therefore stays spatially interpretable after packing, instead of collapsing to anonymous pooled content. We measure the failure mode directly. On a controlled synthetic task---train on one packing, change only the memory order of the tokens, hold the physical labeling rule fixed---learned positional embeddings and packed-sequence RoPE solve the training layout perfectly yet collapse under Morton, block-contiguous, and random repacking, while axial grid-coordinate RoPE stays exact throughout. The same coordinate system carries to real data: on Allen WTC-11 hiPSC microscopy, PACK3D improves over a parameter-matched 3D U-Net on the 15-structure joint task and over a matched learned-position local-global baseline, with controls isolating the coordinate system, not encoder capacity, as the source of the gain. A fused Triton implementation matches windowed-attention latency at 65k tokens while supplying the long-range context windowing cannot---so the operator is not only correct but trainable at scale.

en

arXiv AI Papershace 16 días

Beyond fabrication: Misattributed numbers in papers written by AI research agents

Verifying numerical claims in research written by AI agents is an important but challenging problem. Recent benchmarks show that many agent-written papers fail integrity checks, but such verdicts, often produced by a single LLM judge, identify failure without explaining its nature, and existing checks either test a paper for internal consistency or test whether a reported value appears somewhere in an agent's output. We re-analyze all 540 released judgments from a recent public benchmark of AI research agents (nine agents, fifteen open research problems) and manually label 256 numerical claims from 18 submissions. Failures concentrate on alignment between the paper and the underlying work rather than overt cheating, and about four in five unsupported claims correspond to values in the agent's own files that come from the wrong experiment, metric, or run. We introduce a deterministic claim-to-evidence checker that scores whether the surrounding context identifies the claimed result and calibrates each claim against numerical decoys. With its rules fixed before labeling, it certifies claims with over 90% precision against blinded annotators (78 of 85; Cohen's kappa = 0.89), while verifying only a subset of claims; most claims it cannot verify are nevertheless traceable, so failure to verify is not evidence of falsehood. An LLM verifier given the same evidence recovers more traceable claims but accepts about three times as many misattributed ones, so the two are best used together. Applied to 99 submissions, the checker reveals large differences in traceability across agents, and a second judge from a different vendor preserves the official agent ranking while passing twice as many papers. These findings motivate provenance-first auditing of AI-produced research.

en

arXiv AI Papershace 16 días

On the Generalization Gap of Streaming Federated Learning with Markovian Data

Streaming federated learning (SFL) allows clients to train a shared model from continuously arriving data without retaining large local datasets. Such streams often exhibit temporal dependence, yet its effect on generalization remains poorly understood. In this paper we study the expected generalization gap of the aggregated model when client data follow Markov processes, using information-theoretic and rate-distortion techniques. Our framework accommodates heterogeneous Markovian dynamics across clients and distinguishes temporal dependence from information acquired during local learning. We establish bounds under cross-entropy loss, specializing them to Linear Next-Token Prediction (LNTP) and Self-Attention Next-Token Prediction (SANTP). These results quantify the effects of client count, communication rounds, sample size, data dimension, mixing time, and context length. In particular, they reveal a communication--generalization tradeoff: although frequent aggregation may help optimization, it can weaken generalization guarantees. They also suggest a potential advantage of distributed over centralized streaming learning under a fixed total data budget. Temporal dependence enters through the square root of the mixing time. By analyzing the history-state process, we obtain refined bounds with improved context-length dependence under suitable mixing conditions. Experiments on GPT-style language-model pretraining with TinyStories and real-world time-series forecasting illustrate how collaboration and communication frequency influence generalization under temporal dependence

en