Daily report — 2026-10-16

In Hebbian learning from examples a Hopfield network of $N$ neurons is not supplied with the $K$ archetypes it has to retrieve but with $M$ blurred examples of each, of quality $r$, and whether it can infer them depends on the load $α=K/N$ (interference among them) and on the dataset entropy $ρ=(1-r^2)/(Mr^2)$ (how little the examples say about them). We transfer this protocol to the exponential H

Claimed: none extracted

Evidence: + cheap/closed-form ("closed form"); + small/synthetic data ("MNIST"); + concrete method ("closed form"); + formal statement ("theorem"); + code: https://github.com/francescoalemanno/hebb-attention; + keywords: monte carlo

heuristic

Existing feature attribution methods that account for feature dependencies do not scale to high dimensions. We propose causal integrated gradients (CIG) and causal expected gradients (CEG), which extend integrated gradients to incorporate prior causal structure among input features while retaining its computational efficiency and, under conditions on the causal graph, its axiomatic guarantees.

Claimed: none extracted

Evidence: + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + public benchmarks ("benchmark"); + formal statement ("theorem"); + claims simplicity ("simple"); + code: https://github.com/sifrimlab/CausalIG; + keywords: ranking

heuristic

In this paper, we present a lightweight algorithm for modelling tabular data containing both continuous and discrete variables. The method uses empirical marginal distributions and a selected quantile function to transform the data into a continuous latent space, where a distribution of choice, e.g.

Claimed: none extracted

Evidence: + toy/synthetic experiments ("synthetic"); + CPU-friendly ("lightweight"); + small/synthetic data ("synthetic"); + formal statement ("Bound"); + claims simplicity ("simple"); no public code found; + keywords: sampling, monte carlo

heuristic

Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets. Real-world customer delivery is different: forward-deployed engineers (FDEs) must clarify ambiguous requirements, work in live systems, and uncover unstated constraints.

Claimed: none extracted

Evidence: + toy/synthetic experiments ("simulated"); + small/synthetic data ("simulated"); + public benchmarks ("benchmarks"); + code: https://github.com/deeplethe/fde-gym; + 56 HF upvotes

heuristic

Retrieving relevant lemmas is crucial for formal theorem proving, enabling provers to build machine-checkable proofs from established mathematical results. Recent retrieval systems match library declarations to a target theorem or its intermediate proof steps, but make limited use of multi-hop dependencies among declarations.

Claimed: recall 12.0%

Evidence: + public benchmarks ("benchmarks"); + formal statement ("Theorem"); + claims simplicity ("simple"); + code: https://github.com/PlusLabNLP/LeanGraphSearch; + keywords: retrieval, ranking

heuristic

Robust covariance estimation under entry-wise contamination and missing data is challenging in various signal processing applications. Under the Student-$t$ model, observation-level reweighting induces a uniform attenuation across samples, which can lead to cumulative information loss even when most coordinates remain informative.

Claimed: none extracted

Evidence: + cheap/closed-form ("closed form"); + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + concrete method ("closed form"); - system/framework (many moving parts) ("framework"); no public code found; + keywords: sampling

heuristic

Recommender systems often need to balance multiple conflicting objectives. Controllable Multi-Objective Recommendation (CMOR) enables dynamic adjustment of objective trade-offs at inference time without retraining, adapting to shifting user or system requirements.

Claimed: none extracted

Evidence: + CPU-friendly ("lightweight"); + public benchmarks ("benchmarks"); + formal statement ("we prove"); + code: https://github.com/35798642/RECSOUP.git; + keywords: ranking

heuristic

Classical PAC-Bayesian generalization theory places prior distributions over Euclidean parameter space $Θ\subseteq \mathbb{R}^D$, causing relative entropy to scale with network dimension $D$. For modern overparameterized neural networks where $D \gg n$, this parameter-counting dependency yields vacuous generalization bounds ($> 1{,}000\%$).

Claimed: none extracted

Evidence: + cheap/closed-form ("closed form"); + small/synthetic data ("MNIST"); + public benchmarks ("benchmark"); + concrete method ("closed form"); + formal statement ("Theorem"); no public code found

heuristic

We study bounded regression under model misspecification, evaluating a function $f$ by its $L_1(P_X)$ distance to the conditional mean $η(x)=\mathbb{E}[Y\mid X=x]$, rather than the standard $L_2(P_X)$. This $L_1$ metric is natural for downstream decision problems such as bandits and reinforcement learning.

Claimed: none extracted

Evidence: + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + formal statement ("bound"); + claims simplicity ("simple"); no public code found; + keywords: bandit

heuristic

Generative visual verifiers play a crucial role in advancing multimodal intelligence. To enhance the robustness of visual verifiers in complex multimodal scenarios involving compositional requirements, we move beyond conventional binary verifiers that produce only True/False discrete judgments and introduce a verifier that automatically decomposes complex prompts or environmental rules into fine-g

Claimed: none extracted

Evidence: + toy/synthetic experiments ("simulation"); + claims simplicity ("simple"); - system/framework (many moving parts) ("framework"); + code: https://github.com/Cominclip/OmniVerifier; + 25 HF upvotes

heuristic