A Neural Affinity Framework for Abstract Reasoning: Diagnosing the Compositional Gap in Transformer Architectures via Procedural Task Taxonomy

• URL: http://arxiv.org/abs/2512.07109v1
• Date: Mon, 08 Dec 2025 02:46:00 GMT
• Title: A Neural Affinity Framework for Abstract Reasoning: Diagnosing the Compositional Gap in Transformer Architectures via Procedural Task Taxonomy
• Abstract summary: We present the first 9-category taxonomy of all tasks, validated at 97.5% accuracy via rule-based code analysis.<n>We prove the taxonomy's visual coherence by training a CNN on raw grid pixels (95.24% accuracy on S3, 36.25% overall, 3.3x chance)<n>Our curriculum analysis reveals 35.3% of tasks exhibit low neural affinity for Transformers--a distributional bias mirroring ARC-AGI-2.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Responding to Hodel et al.'s (2024) call for a formal definition of task relatedness in re-arc, we present the first 9-category taxonomy of all 400 tasks, validated at 97.5% accuracy via rule-based code analysis. We prove the taxonomy's visual coherence by training a CNN on raw grid pixels (95.24% accuracy on S3, 36.25% overall, 3.3x chance), then apply the taxonomy diagnostically to the original ARC-AGI-2 test set. Our curriculum analysis reveals 35.3% of tasks exhibit low neural affinity for Transformers--a distributional bias mirroring ARC-AGI-2. To probe this misalignment, we fine-tuned a 1.7M-parameter Transformer across 302 tasks, revealing a profound Compositional Gap: 210 of 302 tasks (69.5%) achieve >80% cell accuracy (local patterns) but <10% grid accuracy (global synthesis). This provides direct evidence for a Neural Affinity Ceiling Effect, where performance is bounded by architectural suitability, not curriculum. Applying our framework to Li et al.'s independent ViTARC study (400 specialists, 1M examples each) confirms its predictive power: Very Low affinity tasks achieve 51.9% versus 77.7% for High affinity (p<0.001), with a task at 0% despite massive data. The taxonomy enables precise diagnosis: low-affinity tasks (A2) hit hard ceilings, while high-affinity tasks (C1) reach 99.8%. These findings indicate that progress requires hybrid architectures with affinity-aligned modules. We release our validated taxonomy,

Related papers

• Domain-Specific Hallucination Detection in Large Language Models [0.0]
  Large language models generate fluent text that can contain unfaithful claims.<n>We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout uncertainty quantification.
  arXiv  Detail & Related papers  (2026-09-10T17:45:36Z)
• FrontierChallenge: Evaluating Scientific Workflow Completion [59.601983661596286]
  We introduce FrontierChallenge, a cross-domain benchmark comprising 300 end-to-end scientific deliverables.<n>We release and evaluate 97 of these tasks, spanning quantum chemistry, molecular dynamics, materials characterization, analytical chemistry, life science, and electrochemistry/environment.<n>We find that neither high partial scores nor confident claims of completion reliably indicate that a scientific task has been fully delivered.
  arXiv  Detail & Related papers  (2026-08-25T16:50:58Z)
• Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
  We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
  arXiv  Detail & Related papers  (2026-06-29T06:39:03Z)
• Domain-Specific Self-Supervised Pre-training for Agricultural Disease Classification: A Hierarchical Vision Transformer Study [0.0]
  We investigate the impact of domain-specific self-supervised pre-training on agricultural disease classification using hierarchical vision transformers.<n>Key finding is that SimCLR pre-training on just 3,000 unlabeled agricultural images provides a +4.57% accuracy improvement.<n>We show this SSL benefit is architecture-agnostic: applying the same pre-training to Swin-Base yields +4.08%, to ViT-Base +4.20%.
  arXiv  Detail & Related papers  (2026-01-09T12:35:52Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Balanced Multi-Task Attention for Satellite Image Classification: A Systematic Approach to Achieving 97.23% Accuracy on EuroSAT Without Pre-Training [0.0]
  This work presents a systematic investigation of custom convolutional neural network architectures for satellite land use classification.<n>We achieve 97.23% test accuracy on the EuroSAT dataset without reliance on pre-trained models.<n>Our approach achieves performance within 1.34% of fine-tuned ResNet-50 (98.57%) while requiring no external data.
  arXiv  Detail & Related papers  (2025-10-17T10:59:24Z)
• OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks [52.87238755666243]
  We present OmniEAR, a framework for evaluating how language models reason about physical interactions, tool usage, and multi-agent coordination in embodied tasks.<n>We model continuous physical properties and complex spatial relationships across 1,500 scenarios spanning household and industrial domains.<n>Our systematic evaluation reveals severe performance degradation when models must reason from constraints.
  arXiv  Detail & Related papers  (2025-08-07T17:54:15Z)
• Advanced Multi-Architecture Deep Learning Framework for BIRADS-Based Mammographic Image Retrieval: Comprehensive Performance Analysis with Super-Ensemble Optimization [0.0]
  mammographic image retrieval systems require exact BIRADS categorical matching across five distinct classes.<n>Current medical image retrieval studies suffer from methodological limitations.
  arXiv  Detail & Related papers  (2025-08-06T18:05:18Z)
• Handling Geometric Domain Shifts in Semantic Segmentation of Surgical RGB and Hyperspectral Images [67.66644395272075]
  We present first analysis of state-of-the-art semantic segmentation models when faced with geometric out-of-distribution data. We propose an augmentation technique called "Organ Transplantation" to enhance generalizability. Our augmentation technique improves SOA model performance by up to 67 % for RGB data and 90 % for HSI data, achieving performance at the level of in-distribution performance on real OOD test data.
  arXiv  Detail & Related papers  (2024-08-27T19:13:15Z)
• Emotion Classification from Multi-Channel EEG Signals Using HiSTN: A Hierarchical Graph-based Spatial-Temporal Approach [0.0]
  This study introduces a parameter-efficient network for emotion classification. The network incorporates a graph hierarchy constructed from bottom-up at various abstraction levels. It achieves mean F1 scores of 96.82% (valence) and 95.62% (arousal) in subject-dependent tests.
  arXiv  Detail & Related papers  (2024-08-09T12:32:12Z)
• Decorrelating Structure via Adapters Makes Ensemble Learning Practical for Semi-supervised Learning [50.868594148443215]
  In computer vision, traditional ensemble learning methods exhibit either a low training efficiency or the limited performance. We propose a lightweight, loss-function-free, and architecture-agnostic ensemble learning by the Decorrelating Structure via Adapters (DSA) for various visual tasks.
  arXiv  Detail & Related papers  (2024-08-08T01:31:38Z)
• Touch Analysis: An Empirical Evaluation of Machine Learning Classification Algorithms on Touch Data [7.018254711671888]
  We propose a novel Deep Neural Net (DNN) architecture to classify the individuals correctly. When we combine the new features with the existing ones, SVM and kNN achieved the classification accuracy of 94.7% and 94.6%, respectively.
  arXiv  Detail & Related papers  (2023-11-23T20:31:48Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)
• Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning [31.0183821423397]
  Whole slide image (WSI) classification is a critical task in computational pathology. Current state of the art methods are based on multi-instance learning schemes (MIL), which usually rely on pretrained features to represent the instances. We propose Prompt-MIL, an MIL framework that integrates prompts into WSI classification.
  arXiv  Detail & Related papers  (2023-03-21T22:24:27Z)
• ZARTS: On Zero-order Optimization for Neural Architecture Search [94.41017048659664]
  Differentiable architecture search (DARTS) has been a popular one-shot paradigm for NAS due to its high efficiency. This work turns to zero-order optimization and proposes a novel NAS scheme, called ZARTS, to search without enforcing the above approximation. In particular, results on 12 benchmarks verify the outstanding robustness of ZARTS, where the performance of DARTS collapses due to its known instability issue.
  arXiv  Detail & Related papers  (2021-10-10T09:35:15Z)
• Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation [63.98724740606457]
  We present a joint effort of four groups, namely GT, USTC, Tencent, and UKE, to tackle Task 1 - Acoustic Scene Classification (ASC) in the DCASE 2020 Challenge. Task 1a focuses on ASC of audio signals recorded with multiple (real and simulated) devices into ten different fine-grained classes. Task 1b concerns with classification of data into three higher-level classes using low-complexity solutions.
  arXiv  Detail & Related papers  (2020-07-16T15:07:14Z)

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.