SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning

• URL: http://arxiv.org/abs/2605.14619v1
• Date: Thu, 14 May 2026 09:37:26 GMT
• Title: SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning
• Abstract summary: We propose SliceGraph, a problem-model-cell graph built by mutual-kNN over sparse activation-key Jaccard similarity between CoT slices.<n>We show that correct CoTs sharing the same normalized answer split into multiple process families.<n>We also show that process families navigate the same atlas with distinct transition kernels under matched null controls.
• Score: 60.650808962786364
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-run chain-of-thought reasoning is usually collapsed to final-answer aggregates, which discard howsampled trajectories share, split, and rejoin through intermediate computation. We propose SliceGraph, a post-hoc problem-model-cell graph built by mutual-kNN over sparse activation-key Jaccard similarity between CoT slices, and treat it as a measurement object for process geometry rather than as a decoding program. Across sampled CoT ensembles from three primary 4B/8B models on math and science benchmarks, blinded annotation supports SliceGraph biconnected components as shared reasoning-state units and process families as within-family strategy-coherent route units. In 85.5% of 954 problem-model cells, correct CoTs sharing the same normalized answer split into multiple process families; among cells with at least two such runs, 76.6% of run pairs are cross-family on average. We call such same-answer, family-divergent correct trajectories process isomers. A label-seeded reward field provides a separate value-landscape layer: success-associated regions often split into disconnected high-value cores, and route families specialize over these core footprints rather than merely duplicating one another. A typed-state transition analysis further shows that process families navigate the same atlas with distinct transition kernels under matched null controls. Representation ablations, a cross-architecture replication, and two cross-scale replications support the robustness of the route-family scaffold, showing that final-answer aggregation overlooks this structured multi-route process geometry.

Related papers

• TripleBound: Triplet-Guided Heterogeneous Graph Learning for Microservice Decomposition [1.516795490965608]
  TripleBound is a hybrid framework for automated monolith-to-microservices decomposition.<n>It augments a heterogeneous graph neural network with weakly supervised triplet constraints.<n>It achieves the highest decomposition score under the selected weighting on AcmeAir, DayTrader, and JPetStore.
  arXiv  Detail & Related papers  (2026-09-10T08:15:24Z)
• Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling [61.28599393707943]
  Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps.<n>We propose a task-shared core scorer and progress-conditioned generation expansions, optimized through generation decomposition and cross-task core alignment.<n> Experiments on two representative UMM architectures demonstrate consistent quality--efficiency improvements across both tasks, retaining 98.03% of dense understanding performance with a 1.93times$ end-to-end inference speedup.
  arXiv  Detail & Related papers  (2026-08-29T14:27:55Z)
• Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition [1.3290717106567922]
  We exploit a shared key-value template $(S)U$ to develop Unpack, a backward recursion that decomposes credit through both sublayers.<n>On GPT-2 small, the method recovers all three composition connections described by Wang et al. (2023), including the mode-specific routing of each connection.<n>Across the Pythia family from 160M to 6.9B parameters, this suppression pattern is consistently recovered at every scale.
  arXiv  Detail & Related papers  (2026-05-22T09:03:01Z)
• Federated Cross-Client Subgraph Pattern Detection [3.903194329577748]
  Subgraph pattern detection aims to uncover complex interaction structures in graphs.<n>State-of-the-art graph neural network (GNN)-based solutions assume centralized access to the entire graph.<n>We formalize this as a structural observability problem, where subgraph patterns crossing partition boundaries become locally unidentifiable.
  arXiv  Detail & Related papers  (2026-05-07T15:35:37Z)
• TractoRC: A Unified Probabilistic Learning Framework for Joint Tractography Registration and Clustering [9.66539105471215]
  Two key tasks in tractography analysis include: 1) tractogram registration that aligns streamlines across individuals, and 2) streamline clustering that groups streamlines into compact fiber bundles.<n>We propose TractoRC, a unified probabilistic framework that jointly performs tractogram registration and streamline clustering within a single optimization scheme.
  arXiv  Detail & Related papers  (2026-03-11T05:04:53Z)
• COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation [58.47973015036709]
  3D pose estimation from sparse multi-views is a critical task for action recognition, sports analysis, and human-robot interaction.<n>We propose COMPOSE, a novel framework that formulates multi-view pose correspondence matching as a hypergraph problem.<n> COMPOSE achieves improvements of up to 23% in average precision over previous optimization-based methods and up to 11% over self-supervised end-to-end learned methods.
  arXiv  Detail & Related papers  (2026-01-14T18:50:17Z)
• Kernel Alignment-based Multi-view Unsupervised Feature Selection with Sample-level Adaptive Graph Learning [23.32756750343138]
  We propose a Kernel Alignment-based multi-view unsupervised FeatUre selection with Sample-level adaptive graph lEarning method (KAFUSE) to address these issues.<n>Experiments on real multi-view datasets demonstrate the superiority of KAFUSE over state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-01-12T07:50:51Z)
• SepFormer: Coarse-to-fine Separator Regression Network for Table Structure Recognition [0.5120567378386615]
  We present SepFormer, which integrates the split-and-merge paradigm into a single step through separator regression with a DETR-style architecture.<n>SepFormer can run on average at 25.6 FPS while achieving comparable performance with state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2025-06-27T05:20:42Z)
• CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation [73.89509052503222]
  This paper presents a simple but performant semi-supervised semantic segmentation approach, called CorrMatch. We observe that the correlation maps not only enable clustering pixels of the same category easily but also contain good shape information. We propose to conduct pixel propagation by modeling the pairwise similarities of pixels to spread the high-confidence pixels and dig out more. Then, we perform region propagation to enhance the pseudo labels with accurate class-agnostic masks extracted from the correlation maps.
  arXiv  Detail & Related papers  (2023-06-07T10:02:29Z)
• One-step Bipartite Graph Cut: A Normalized Formulation and Its Application to Scalable Subspace Clustering [56.81492360414741]
  We show how to enforce a one-step normalized cut for bipartite graphs, especially with linear-time complexity. In this paper, we first characterize a novel one-step bipartite graph cut criterion with normalized constraints, and theoretically prove its equivalence to a trace problem. We extend this cut criterion to a scalable subspace clustering approach, where adaptive anchor learning, bipartite graph learning, and one-step normalized bipartite graph partitioning are simultaneously modeled.
  arXiv  Detail & Related papers  (2023-05-12T11:27:20Z)
• ClusterFuG: Clustering Fully connected Graphs by Multicut [20.254912065749956]
  In dense multicut, the clustering objective is given in a factorized form as inner products of node feature vectors. We show how to rewrite classical greedy algorithms for multicut in our dense setting and how to modify them for greater efficiency and solution quality.
  arXiv  Detail & Related papers  (2023-01-28T11:10:50Z)
• Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision [63.429704654271475]
  We propose a novel weakly supervised method RWSeg that only requires labeling one object with one point. With these sparse weak labels, we introduce a unified framework with two branches to propagate semantic and instance information. Specifically, we propose a Cross-graph Competing Random Walks (CRW) algorithm that encourages competition among different instance graphs.
  arXiv  Detail & Related papers  (2022-08-10T02:14:39Z)
• DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution [136.7261709896713]
  We propose a data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances. The proposed method achieves promising results on both ScanetNetV2 and S3DIS. It also improves inference speed by more than 25% over the current state-of-the-art.
  arXiv  Detail & Related papers  (2020-11-26T14:56:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.