A Symmetric Layer-Union Audit of Component Collapse in Hierarchical Procedural Corpora

• URL: http://arxiv.org/abs/2608.08892v1
• Date: Sun, 09 Aug 2026 20:13:17 GMT
• Title: A Symmetric Layer-Union Audit of Component Collapse in Hierarchical Procedural Corpora
• Abstract summary: Component-disjoint leakage control can group corpus units by content similarity, hierarchical membership, or both.<n>Guvenilir and Dogan previously showed that merging relation types can create a giant component that obstructs splitting.<n>We examine it through a symmetric audit of a content-near-duplicate layer, a common-container layer, and their union in a fixed panel of six hierarchical procedural corpora.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Component-disjoint leakage control can group corpus units by content similarity, hierarchical membership, or both. Guvenilir and Dogan previously showed that merging relation types can create a giant component that obstructs splitting; we do not claim this phenomenon as new. We examine it through a symmetric audit of a content-near-duplicate layer, a common-container layer, and their union in a fixed panel of six hierarchical procedural corpora. MyFixit and Doc2Dial exhibit the individual-layer-pass/union-fail pattern under the same operational criteria. The resulting two-of-six fraction describes this deliberately constructed panel and is not a prevalence estimate. A prespecified bridge-specific predictor is associated with the pattern, but it is not distinguished from a registered union-density control; the panel therefore does not identify a bridge-specific mechanism. Secondary diagnostics bound the interpretation of threshold sensitivity, annotation coverage, and lexical cues without extending those findings beyond their recorded sources and definitions. The paper's contribution is a bounded measurement and audit: it keeps relation families visible, evaluates their individual and union component structures symmetrically, and reports negative cases and mechanism limits. It proposes neither a new splitting algorithm nor a general causal claim about relation unions.

Related papers

• Operational Identity: A Finite Audit of Declared and Implemented Rules of Sameness [0.0]
  A system can apply consistently and with every record individually correct, a rule of sameness that no artifact declares.<n>A declared identity regime partitions a finite record domain into co-reference classes.<n>A disclosed mechanism induces an operational identity partition of the same domain.
  arXiv  Detail & Related papers  (2026-07-22T21:02:37Z)
• Non-binary bottom-up constituency parsing without arity actions [8.373441227262644]
  We show that this arity parameter is not a necessary transition primitive.<n>We show that its predicted arity profile remains close to the gold treebanks and that high-arity constituents do not collapse when arity actions are removed.
  arXiv  Detail & Related papers  (2026-07-12T06:07:29Z)
• What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility [48.10132234701036]
  We propose a diagnostic evaluation protocol based on three checks -- scale stability, reference validity, and depth utility -- together with per-layer rather than aggregate cosine reporting.<n>Across multiple architectures and methods, our protocol identifies all failures with wide calibration margins.
  arXiv  Detail & Related papers  (2026-06-19T06:04:17Z)
• Departure from Regularity: Degree Heterogeneity and Eigengap as the Structural Drivers of ASE-LSE Latent Subspace Disagreement [2.2201528765499416]
  Two methods for analysing graph data, Adjacency Spectral Embedding and Laplacian Spectral Embedding, often produce different results when applied to the same network.<n>We show that regularity is a sufficient condition for perfect agreement.<n>We prove an explicit bound whose two terms suggest the structural ingredients controlling it: degree heterogeneity, which pushes the methods apart, and community structure strength, which pulls them back together.
  arXiv  Detail & Related papers  (2026-05-21T11:30:37Z)
• A Family of Divergence Measures for Evaluating the Reconstruction Quality of Explainable Ensemble Trees [0.41292255339309664]
  Correlation-based approaches fail to detect systematic discrepancies in co-occurrence structure.<n>We propose a statistical framework grounded in the agreement-association distinction.<n>The framework incorporates four complementary measures capturing distinct structural facets of approximation quality.
  arXiv  Detail & Related papers  (2026-05-19T09:56:04Z)
• Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination [60.197429875410286]
  Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems.<n>Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion.<n>In vision, masking highly coupled components improves robustness without costly adversarial training.<n>In language, the same prefill-stage probe detects hallucination risk before generating any answer tokens.
  arXiv  Detail & Related papers  (2026-03-20T02:07:10Z)
• On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation [51.56484100374058]
  We formalise such information-conditioned interaction patterns as behavioural dependency.<n>This induces a probe-relative notion of $$-behavioural equivalence and a within-policy behavioural distance.<n>Results identify structural conditions under which probe-conditioned behavioural separation is not preserved under common policy transformations.
  arXiv  Detail & Related papers  (2026-02-24T22:55:21Z)
• Fundamental limits to contrast reversal of self-fidelity correlations [0.0]
  In measurement design, it is common to engineer anti-contrast readouts.<n>We ask whether two evolutions can be made uniformly opposite over a broad input ensemble.<n>We adopt the Pearson correlation coefficient as a device-agnostic measure of global opposition between two evolutions.
  arXiv  Detail & Related papers  (2025-09-30T15:07:28Z)
• Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity [46.60221265861393]
  Existing approaches to predictive uncertainty rely on multi-hypothesis prediction, which promotes diversity but lacks principled aggregation.<n>The Structured Basis Function Network addresses this gap by linking multi-hypothesis prediction and ensembling through centroidal aggregation induced by Bregman divergences.<n>A tunable diversity mechanism provides parametric control of the bias-variance-diversity trade-off, connecting multi-hypothesis generalisation with loss-aware ensemble aggregation.
  arXiv  Detail & Related papers  (2025-09-02T19:53:43Z)
• Unsupervised Full Constituency Parsing with Neighboring Distribution Divergence [48.69930912510414]
  We propose an unsupervised and training-free labeling procedure by exploiting the property of a recently introduced metric. For implementation, we develop NDD into Dual POS-NDD and build "molds" to detect constituents and their labels in sentences. We show that DP-NDD not only labels constituents precisely but also inducts more accurate unlabeled constituency trees than all previous unsupervised methods with simpler rules.
  arXiv  Detail & Related papers  (2021-10-29T17:27:34Z)
• Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [72.38919601150175]
  We propose Bilayer Convolutional Network (BCNet) to segment highly-overlapping objects. BCNet detects the occluding objects (occluder) and the bottom GCN layer infers partially occluded instance (occludee)
  arXiv  Detail & Related papers  (2021-03-23T06:25:42Z)

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.