Jan 2026· arXiv.org· Vol abs/2601.19094· 1 citation· 80 references
Computer Science
TL;DR
Under atomic tuple initialization and invariant readout, it is shown that \kfnet{k} is no more graph-discriminative than k-FWL; on BREC, each evaluated variant matches the success set of its corresponding WL reference.
Abstract
Learning algorithmic computation often requires explicit relational intermediate states, yet many graph processors maintain their primary states on individual entities. We introduce \fnet and \textbf{Pivotal Attention} (PA), which maintain ordered pair states and update a target relation $(i,k)$ by attending over candidates formed from $(i,j)$ and $(j,k)$ for every pivot $j$. Motivated by the pair-and-pivot structure of Floyd--Warshall, PA learns relation composition and pivot weighting in parallel rather than executing its ordered min-plus recurrence. The \kfnet{k} framework extends this operation to ordered $k$-tuples, with Self-Attention and PA as its $k=1$ and $k=2$ cases at the attention-operation level. Under atomic tuple initialization and invariant readout, we show that \kfnet{k} is no more graph-discriminative than k-FWL; on BREC, each evaluated variant matches the success set of its corresponding WL reference. \fnet further achieves 96.64\% mean accuracy under the reported CLRS-30 protocol and a 99.8\% optimality rate with 10 samples on held-out non-metric TSP instances.
The framework extracts each conversational turn into typed nodes and attributed edges, answers questions from a two-hop subgraph, and periodically prunes nodes that score low on a weighted combination of recency, access frequency, degree centrality, and age.
Theo Rusu, S. Khanzadeh, Manar H. Alalfi· 3 citations· ⚡1
The \emph{unit} is proposed as an explicit primitive at the level of task semantics as an explicit primitive at the level of task semantics in supervised learning.
The results of Corr2Cause support a bounded design principle: externalize the latent object that defines the label, constrain its form, and test whether downstream answers use it.
Wen-Tao Sun, João Paulo Nogueira, Dominique Verchere et al.· 0 citations
The RunningTensor is introduced, which generalizes this memory to an order-o tensor, updated by a rank-1 outer product and read by contracting against $o-1$ vector queries, and improves performance on language-understanding and non-synthetic retrieval tasks, suggesting that higher-order recurrent state can provide usef...
Luca Herranz-Celotti, Vincent Guigue· arXiv.org· 1 citation
This work proposes query-difficulty-gated fusion of reasoning views, a fused ranking that uses no relevance labels at inference, no re-ranking, and no fine-tuning of the retriever; the gate is trained leave-one-task-out.
J. Holdcroft, Abdelrahman Abdallah, Adam Jatowt· 0 citations
Agents that answer questions from compressed or retrieved memory must recognize when the evidence a query needs is no longer in memory. Benchmarks for this task usually create insufficient-evidence examples by deleting supporting passages. We show that this construction leaks the label through memory size: on MuSiQue,...
Joyanta J. Mondal, Md. Shifatul Ahsan Apurba, Mridul Banik et al.· arXiv.org· 1 citation
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.