EFX allocations do not exist for n ≥ 3 agents and m ≥ n+5 goods with monotone valuations; a counterexample is constructed via SAT solving and the encoding is verified in Lean.
super hub Canonical reference
Title resolution pending
Canonical reference. 75% of citing Pith papers cite this work as background.
681
Pith papers citing it
24
external citations · Crossref
Background
75% of classified citations
abstract
Predicting missing facts in a knowledge graph (KG) is crucial as modern KGs are far from complete. Due to labor-intensive human labeling, this phenomenon deteriorates when handling knowledge represented in various languages. In this paper, we explore multilingual KG completion, which leverages limited seed alignment as a bridge, to embrace the collective knowledge from multiple languages. However, language alignment used in prior works is still not fully exploited: (1) alignment pairs are treated equally to maximally push parallel entities to be close, which ignores KG capacity inconsistency; (2) seed alignment is scarce and new alignment identification is usually in a noisily unsupervised manner. To tackle these issues, we propose a novel self-supervised adaptive graph alignment (SS-AGA) method. Specifically, SS-AGA fuses all KGs as a whole graph by regarding alignment as a new edge type. As such, information propagation and noise influence across KGs can be adaptively controlled via relation-aware attention weights. Meanwhile, SS-AGA features a new pair generator that dynamically captures potential alignment pairs in a self-supervised paradigm. Extensive experiments on both the public multilingual DBPedia KG and newly-created industrial multilingual E-commerce KG empirically demonstrate the effectiveness of SS-AG
hub tools
citation-role summary
background 159
method 19
baseline 6
dataset 2
other 2
citation-polarity summary
claims ledger
- abstract Predicting missing facts in a knowledge graph (KG) is crucial as modern KGs are far from complete. Due to labor-intensive human labeling, this phenomenon deteriorates when handling knowledge represented in various languages. In this paper, we explore multilingual KG completion, which leverages limited seed alignment as a bridge, to embrace the collective knowledge from multiple languages. However, language alignment used in prior works is still not fully exploited: (1) alignment pairs are treated equally to maximally push parallel entities to be close, which ignores KG capacity inconsistency;
- background 5.1.1 Data Filtering. To reduce the presence of misinformation and biases, an intuitive approach involves the careful selection of high-quality pre-training data from reliable sources. In this way, we can ensure the factual correctness of data while also minimizing the introduction of social biases. As early as the advent of GPT-2, Radford et al. [252]underscored the significance of exclusively scraping web pages that had undergone rigorous curation and filtration by human experts. However, as p
authors
co-cited works
representative citing papers
Max Independent Set on twin-width-4 graphs admits no polynomial-time n to the power gamma over (log log n) squared approximation unless ETH fails.
Isotopically purified 70Ge hole spin qubits achieve T2* >20 us on sweet spot and >3 us off sweet spot with >99.9% gate fidelity while revealing a quadrupolar nuclear-noise channel from residual 73Ge.
Multi-distribution Rényi divergences are positive integrals of coincidence divergences C_α over four strata (simplex interior, mixed-sign cones, tropical boundary, KL edges).
Proves finite moments E[S_T^p] < ∞ for p < p_ρ in rough Bergomi under ρ ∈ [-1,0) and positive atom at zero for rough Heston variance process.
TerminalWorld builds a scalable benchmark of 1,530 real terminal tasks from recordings and finds frontier models and agents reach at most 62.5% pass rate with only weak correlation to prior expert-curated sets.
Machine learning methods discover a new noncrossing-partition statistic interpreting q,t-Narayana polynomials and yield a combinatorial proof of their symmetry.
A hybrid randomized smoothing method yields a closed-form certificate for joint discrete-continuous perturbations that generalizes prior Gaussian and discrete smoothing approaches.
A theoretical model derives the universal mammalian vascular branching exponent α* ≈ 2.72 from a network-level minimax principle and topological rigidity theorem grounded in ATP costs, yielding α*_model ≈ 2.626 with heterogeneities shifting it to observed values.
APIOT is the first LLM framework to complete the full autonomous discovery-to-remediation cycle on bare-metal OT devices, reaching 90% success across 290 runs on Zephyr RTOS.
NeuroTaint is the first taint tracking framework for LLM agents that uses offline auditing of semantic, causal, and persistent context to detect flows from untrusted sources to privileged sinks.
A bidirectional reduction between suffix random access and function inversion enables improved asymmetric streaming algorithms for exact/approximate pattern matching and relative Lempel-Ziv compression.
A new heuristic compiler for multi-qubit iceberg patches reduces circuit depth by 34 percent, cuts gate counts, and improves fidelity metrics on 71 benchmarks compared with naive mapping.
SlopCodeBench shows coding agents degrade in structural quality and verbosity across iterative extensions, with no agent solving any problem completely and agent code 2x more eroded than human code.
Entropy production for the Landau equation with Maxwell molecules is non-increasing after a finite time under moment and temperature-distribution conditions, partially resolving a 1966 conjecture.
SWE-Gym supplies 2438 executable real-world Python tasks to train SWE agents and verifiers, yielding up to 19% gains and new open-weight SOTA of 32% on SWE-Bench Verified.
SOAP runs Adam in the eigenbasis of Shampoo's preconditioner, cutting iterations by over 40% versus AdamW on 360M-660M language models while adding only one hyperparameter.
OSWorld provides the first unified real-computer benchmark for open-ended multimodal agent tasks, exposing large performance gaps between humans and state-of-the-art LLM/VLM agents.
Linear representations of high-level concepts in LLMs are formalized via counterfactuals in input and output spaces, unified under a causal inner product that enables consistent probing and steering.
Mind2Web is the first large-scale dataset of real-world web tasks for developing generalist language-guided agents that complete complex actions on diverse websites.
X-CAPPS generates coherent attosecond X-ray pulse pairs from Cu Kα1 stimulated emission pumped by SASE XFEL pulses and measures their time delays, amplitudes, and phases via interference spectra on sequential Bragg spectrometers.
SpheRoPE modifies rotary position embeddings in diffusion transformers to enforce spherical topology for zero-shot 360 panorama generation across multiple backbones.
An adaptive fine-tuning workflow for foundation-model MLIPs enables efficient CSP in the CaFeNi ternary, reproducing the low-pressure hull and predicting a new phase Ca6FeNi stable above 100 GPa.
HASTE enables training-free dynamic compression of pre-trained CNNs by patch-wise LSH-based merging of redundant channels, reporting 46.2% FLOPs reduction on ResNet34 CIFAR-10 with 1.25% accuracy drop.
citing papers explorer
-
A Counterexample to EFX $n \ge 3$ Agents, $m \ge n + 5$ Items, Submodular Valuations via SAT-Solving
EFX allocations do not exist for n ≥ 3 agents and m ≥ n+5 goods with monotone valuations; a counterexample is constructed via SAT solving and the encoding is verified in Lean.
-
Independent Set Hardness in Graphs of Bounded Twin-Width and Low-Radius Merge-Width
Max Independent Set on twin-width-4 graphs admits no polynomial-time n to the power gamma over (log log n) squared approximation unless ETH fails.
-
High-Fidelity Hole Spin Qubits Reveal Quadrupolar Nuclear-Bath Dynamics in Isotopically Purified Planar Germanium
Isotopically purified 70Ge hole spin qubits achieve T2* >20 us on sweet spot and >3 us off sweet spot with >99.9% gate fidelity while revealing a quadrupolar nuclear-noise channel from residual 73Ge.
-
All you need is log
Multi-distribution Rényi divergences are positive integrals of coincidence divergences C_α over four strata (simplex interior, mixed-sign cones, tropical boundary, KL edges).
-
Moments in Rough Bergomi and Boundary Attainment in Rough Heston
Proves finite moments E[S_T^p] < ∞ for p < p_ρ in rough Bergomi under ρ ∈ [-1,0) and positive atom at zero for rough Heston variance process.
-
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
TerminalWorld builds a scalable benchmark of 1,530 real terminal tasks from recordings and finds frontier models and agents reach at most 62.5% pass rate with only weak correlation to prior expert-curated sets.
-
Mapping Uncharted Symmetries: Machine Discovery in Combinatorics
Machine learning methods discover a new noncrossing-partition statistic interpreting q,t-Narayana polynomials and yield a combinatorial proof of their symmetry.
-
Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
A hybrid randomized smoothing method yields a closed-form certificate for joint discrete-continuous perturbations that generalizes prior Gaussian and discrete smoothing approaches.
-
The Incommensurability Principle in Biological Transport
A theoretical model derives the universal mammalian vascular branching exponent α* ≈ 2.72 from a network-level minimax principle and topological rigidity theorem grounded in ATP costs, yielding α*_model ≈ 2.626 with heterogeneities shifting it to observed values.
-
APIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks
APIOT is the first LLM framework to complete the full autonomous discovery-to-remediation cycle on bare-metal OT devices, reaching 90% success across 290 runs on Zephyr RTOS.
-
Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents
NeuroTaint is the first taint tracking framework for LLM agents that uses offline auditing of semantic, causal, and persistent context to detect flows from untrusted sources to privileged sinks.
-
Suffix Random Access via Function Inversion: A Key for Asymmetric Streaming String Algorithms
A bidirectional reduction between suffix random access and function inversion enables improved asymmetric streaming algorithms for exact/approximate pattern matching and relative Lempel-Ziv compression.
-
Logical Compilation for Multi-Qubit Iceberg Patches
A new heuristic compiler for multi-qubit iceberg patches reduces circuit depth by 34 percent, cuts gate counts, and improves fidelity metrics on 71 benchmarks compared with naive mapping.
-
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
SlopCodeBench shows coding agents degrade in structural quality and verbosity across iterative extensions, with no agent solving any problem completely and agent code 2x more eroded than human code.
-
On the monotonicity of the entropy production in the Landau-Maxwell equation
Entropy production for the Landau equation with Maxwell molecules is non-increasing after a finite time under moment and temperature-distribution conditions, partially resolving a 1966 conjecture.
-
Training Software Engineering Agents and Verifiers with SWE-Gym
SWE-Gym supplies 2438 executable real-world Python tasks to train SWE agents and verifiers, yielding up to 19% gains and new open-weight SOTA of 32% on SWE-Bench Verified.
-
SOAP: Improving and Stabilizing Shampoo using Adam
SOAP runs Adam in the eigenbasis of Shampoo's preconditioner, cutting iterations by over 40% versus AdamW on 360M-660M language models while adding only one hyperparameter.
-
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
OSWorld provides the first unified real-computer benchmark for open-ended multimodal agent tasks, exposing large performance gaps between humans and state-of-the-art LLM/VLM agents.
-
The Linear Representation Hypothesis and the Geometry of Large Language Models
Linear representations of high-level concepts in LLMs are formalized via counterfactuals in input and output spaces, unified under a causal inner product that enables consistent probing and steering.
-
Mind2Web: Towards a Generalist Agent for the Web
Mind2Web is the first large-scale dataset of real-world web tasks for developing generalist language-guided agents that complete complex actions on diverse websites.
-
X-ray Coherent Attosecond Pulse Pair Spectroscopy
X-CAPPS generates coherent attosecond X-ray pulse pairs from Cu Kα1 stimulated emission pumped by SASE XFEL pulses and measures their time delays, amplitudes, and phases via interference spectra on sequential Bragg spectrometers.
-
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
SpheRoPE modifies rotary position embeddings in diffusion transformers to enforce spherical topology for zero-shot 360 panorama generation across multiple backbones.
-
Adaptive fine-tuning of foundation models for crystal structure prediction: Discovery of high-pressure phases in the CaFeNi system
An adaptive fine-tuning workflow for foundation-model MLIPs enables efficient CSP in the CaFeNi ternary, reproducing the low-pressure hull and predicting a new phase Ca6FeNi stable above 100 GPa.
-
HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks
HASTE enables training-free dynamic compression of pre-trained CNNs by patch-wise LSH-based merging of redundant channels, reporting 46.2% FLOPs reduction on ResNet34 CIFAR-10 with 1.25% accuracy drop.
-
SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics
SABER-Math is an automated benchmark for mathematical IR that uses LLM summaries, topic similarities, and preference tournaments on 283K problems to create reranking tasks, showing embedding models outperform baselines but struggle in symbol-heavy areas and that MTEB does not predict math performanc
-
Priced Motion Through Optimal Faces: A Normal-Fan Geometry for Non-Stationary Adversarial MDPs
Introduces priced face-crossing via normal-fan geometry on occupancy polytopes to decompose dynamic regret into intrinsic motion cost plus within-face error in non-stationary adversarial MDPs.
-
OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators
OperatorSHAP trains FastSHAP-style explainers for neural operators via a function-space attribution framework that remains consistent across grid resolutions without retraining.
-
On the independence of the slow and fast scales in multiple-scale expansions, with application to Van der Pol's equation
Nonlinearity induces an exponentially small phase shift in Van der Pol's equation that couples the slow and fast scales in multiple-scale expansions.
-
Event-based Gaze Control System for Accurate Real-time Spin Estimation in Professional Ball Games
An event-camera system with active gaze control and contrast-maximization spin estimation achieves real-time performance in table tennis with 8.8% magnitude error, 6.4° axis error, 3 ms latency, and 750 Hz throughput.
-
Nonexistence of finite-time blow-up for the equivariant harmonic map heat flow from $B^2$ to $S^2$
Proves nonexistence of finite-time blow-up for D-equivariant harmonic map heat flow from B² to S² when D ≥ 3 under general smooth time-dependent boundary data.
-
Canopies: A Generalization of Vines and Vineyards for Parameterized Persistence
Canopies generalize vines and vineyards by tracking simplex pairs in filtered chain complexes instead of persistence diagram points, with proofs of homeomorphism and applications to multiplicity and monodromy.
-
FairBED: A Bayesian Experimental Design Approach to Gathering Fairer Data
FairBED quantifies dataset fairness as uninformative about sensitive attributes and uses fairness-aware BED to gather data yielding better fairness-accuracy trade-offs than random or standard BED acquisition.
-
Koshur Pixel: a large-scale synthetic ocr dataset for kashmiri
Koshur Pixel is the first large-scale synthetic OCR dataset for Kashmiri with 613,078 image-text pairs generated via SynthOCR-Gen from the KS-PRET-5M corpus across multiple fonts and granularities with 25+ augmentations.
-
Lost in Aggregation: A Multi-Scale Diagnostic Benchmark for LLM Spatial Navigation
A new diagnostic benchmark decomposes LLM spatial navigation into three cognitive scales and shows that cross-scale aggregation, not single-level deficits, causes failure beyond small mazes.
-
The Representational Limit of Scalar Interactions: An Interventional Decomposition
Signed pairwise interaction scores conflate U/R/S; Stochastic Hi-Fi uses interventional masked inference to recover per-feature uniqueness, redundancy, and synergy profiles.
-
Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark
PhySciBench benchmark shows current AI models achieve at most 33.5% accuracy on physical science tasks; DelveAgent framework improves accuracy by up to 7.5 points and cuts costs to one-third.
-
ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues
ReproRepo uses GitHub issues as natural supervision to benchmark LLM agents on detecting reproducibility blockers across 1,149 ML papers, with the top agent finding related issues for roughly 90% of cases.
-
A T-API-Compliant ReAct Agentic Loop for Optical Networks: Generic vs. Domain-Specific Tool Abstractions
Presents the first T-API-compliant ReAct loop for optical networks and shows domain-specific composite tools achieve 90% oracle-validated correctness with threefold token savings versus generic tools.
-
When Representative Samples Produce Worse Outcomes: Scale-up Decisions and Testing in Small-Budget RCTs
In small-budget RCTs where significance tests decide scale-up, optimal pilot sampling shifts from representative to single homogeneous subpopulation as budget shrinks.
-
Consensus Time in 3-Majority and 2-Choices Is Determined by the Maximum Initial Opinion Density
Consensus time in 3-Majority is ilde{\Theta}(\min\{1/\|\alpha^{(0)}\|_\infty, \sqrt{n}\}) and in 2-Choices is \tilde{\Theta}(1/\|\alpha^{(0)}\|_\infty) w.h.p., governed by maximum initial opinion density for every starting configuration.
-
How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
Activation patching reveals that citation decisions in Llama-3.1-8B RAG are implemented by a distributed attributional ensemble of heads and layers; targeted interventions fix most missed and spurious citations on PopQA.
-
Targeting World Models to Compromise Robot Learning Pipelines
World models introduce a stealthy poisoning vector into robot learning pipelines where malicious prompts or dynamics in teleoperated data activate only during synthetic trajectory generation, enabling backdoors in downstream policies.
-
Optical Music Recognition for Real-World Manuscripts with Synthetic Data
Domain adaptation via synthetic manuscript images improves OMR performance on real-world piano manuscripts without requiring in-domain symbols.
-
Geodesics of Dynamic Graphs for Regime Change Detection
Models regimes in temporal graphs as geodesic trajectories and detects changes as drifts from estimated geodesics, outperforming baselines on synthetic data and showing better alignment with external events on COVID mobility data.
-
Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation
Consequence-aware scheduler using an issue-text predictor routes more compute to high-cost failures and cuts cost-weighted loss by 22-33% versus difficulty-based allocation on SWE-bench tasks.
-
Correcting Neural Operator Spectral Bias via Diffusion Posterior Sampling with Sparse Observations
FreqNO-DPS corrects neural operator spectral bias in 3D elastic wavefield prediction by frequency-dependent guidance in diffusion posterior sampling conditioned on sparse observations, achieving near-zero bias at 2-5% sensor coverage.
-
Timelike ideal boundary of non-positively curved Lorentzian spaces
Defines timelike ideal boundary for non-positively curved Lorentzian length spaces, proves upper curvature bounds on the resulting space, and relates it to generalized cones.
-
Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning
CoT reasoning exhibits a two-phase entropy structure with a detectable confidence region that enables CUSUM-based early exit achieving 63.06% accuracy at 11.1% token reduction and better test-time scaling than self-consistency.
-
Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs
FilterMoE uses joint node-channel routing of Chebyshev filter experts through a 3D gating tensor in pre-propagation GNNs and outperforms baselines on nine of eleven benchmarks while ranking first on all three large-scale ones with a 1.53-point average gain.
-
PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects
PolySpeech-100 is a new benchmark for native-level speech comprehension across 110 linguistic variants that evaluates 22 models and reports E2E advantages on dialects, robustness gaps on low-resource languages, and degradation from Chain-of-Thought prompting.