The Ignition Is Real, and It Lives at the Readout: Latent composition, difficulty-clocked ignition, and the interface-constituted commit in a recurrent-depth reasoner

• URL: http://arxiv.org/abs/2608.03263v1
• Date: Tue, 04 Aug 2026 07:35:38 GMT
• Title: The Ignition Is Real, and It Lives at the Readout: Latent composition, difficulty-clocked ignition, and the interface-constituted commit in a recurrent-depth reasoner
• Abstract summary: We test whether the "compositional ignition" reported in latent-reasoning models is real computation, an instrument artifact, or inherited from verbal training data.<n>The ignition is real and lives at the readout: arrival time rises lawfully with problem depth, resolution is sharp and holds, and the signature reproduces across two same-seed realizations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We test whether the "compositional ignition" reported in latent-reasoning models is real computation, an instrument artifact, or inherited from verbal training data. We grow an independent realization of a published 30M-parameter recurrent-depth reasoner from scratch (same recipe and seed), film its development, certify fidelity through a pre-registered whole-signature gate, and measure resolution in two channels at once: the vocabulary readout and the hidden state. The ignition is real and lives at the readout: arrival time rises lawfully with problem depth, resolution is sharp and holds, and the signature reproduces across two same-seed realizations with divergent training trajectories. At commitment the decision margin jumps 5.8-8.0 logits in one iteration, exceeding the 90th percentile of near-threshold non-event steps in 96% of cases; the signed margin's zero-crossing there is definitional and carries no evidential weight, so the evidence is that conditioned magnitude. The hidden-state direction snaps in raw geometry, meeting its pre-registered criterion (in the decoder's LayerNorm coordinates it attenuates just below our bar, so the composite decoder-coordinate claim is not confirmed), and then freezes in both (descriptively so in decoder coordinates; angular steps 52.9 to 1.2 degrees over eight iterations), while subsequent displacement is predominantly radial (0.961 of squared-norm) and readout-null to a measured bound (radial logit effect <=5.7e-6). An earlier velocity-trough claim is withdrawn: pre-registered normalization controls showed it coordinate-dependent. Intermediates were never recoverable through the tied readout (relay 0.00). All criteria were frozen before their data; the predictions ledger, including this paper's own withdrawn headline, ships in the companion repository.

Related papers

• Unsupervised Point Cloud Registration via Training-Time Semantic Guidance [46.92635414824713]
  CAESAR is a teacher-student framework guided by an off-the-shelf 3D segmentation model exclusively during training.<n>Building on this, a train-only Semantic-Geometric Label Mining performs lightweight, batch-specific teacher refinement and mines reliable pseudo-labels.<n>Experiments on KITTI and nuScenes demonstrate state-of-the-art performance, with pronounced gains on the challenging nuScenes benchmark.
  arXiv  Detail & Related papers  (2026-09-14T08:49:09Z)
• ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding [46.17292752074153]
  We introduce ReTrace, a conditioning method that conditions each draft block on the rejected suffix from the previous round.<n>ReTrace consistently improves average acceptance length and end-to-end decoding speed over its DFlash backbone.
  arXiv  Detail & Related papers  (2026-08-30T12:20:54Z)
• Strictly Causal Streaming Video Anomaly Detection with a Theoretically-Grounded State-Space Core [2.648500779572419]
  We introduce a causal streaming anomaly detector with no lookahead and no clip buffering.<n>Its temporal core is a diagonal linear state space recurrence with an input and state dependent decay gate.<n>We derive a closed form relationship between the recurrence decay spectrum and both detection delay and the shortest anomaly it can reliably capture.
  arXiv  Detail & Related papers  (2026-08-25T16:52:32Z)
• Feature Priming in Online Linear Regression: Sparse-Regret Lower Bounds and a Tight Univariate Rate [47.36630149538994]
  In high-dimensional online prediction, the best predictor may depend on only a few features, so regret should scale with sparsity rather than the ambient dimension.<n>Warmuth and Amid asked at COLT 2023 whether any of three such rules admits a competitive online regret guarantee.<n>Our analysis identifies a common obstruction: cheap nuisance causes the refit to underweight the truly predictive coordinate.
  arXiv  Detail & Related papers  (2026-08-18T09:32:03Z)
• You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model [9.92799001840128]
  This paper consolidates two research lines that address these on the same residual stream.<n>A conditional steering probe writes the stream at mid-stack layers and recovers reasoning accuracy from a frozen backbone.<n> YOPO (You Only Pass Once) answers, steers, and abstains in one forward pass of a frozen Qwen2.5 backbone.
  arXiv  Detail & Related papers  (2026-08-14T16:44:35Z)
• GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning [61.67411833252235]
  We introduce GradCuit, which inserts optimizable latent states at a selected Transformer layer between the hidden representations of the prompt and the generated continuation.<n>Across five instruction-tuned backbones, three reasoning benchmarks, and two answer formats, GradCuit achieves an average accuracy of 64.5%.<n>For interpretability, token-level gradient attribution reveals that latent influence concentrates on reasoning-connector tokens, while layer analysis identifies early-to-middle Transformer layers as the most effective optimization space.
  arXiv  Detail & Related papers  (2026-08-03T17:55:24Z)
• SketchMamba: A Lightweight State-Space Model for Joint Progressive Sketch Classification and Stroke Auto-Completion [0.0]
  Existing vector-sketch models treat recognition and generation as separate tasks.<n>We present SketchMamba, a single causal sequence model that continuously classifies a sketch from any partial prefix while simultaneously generating its continuation.
  arXiv  Detail & Related papers  (2026-07-26T10:05:23Z)
• From Geometric Recovery to Causal Validation: A Reproducible Audit of Sparse Autoencoder Features, from Superposition Geometry to Causal Inertness [0.0]
  Sparse autoencoders (SAEs) are the standard for decomposing superposed neural representations into interpretable features.<n>We show this conflates two distinct claims: decoder-geometry alignment and encoder-activation behavior.<n>We package the method as sae-causal-audit, a model-agnostic instrument with a deterministic pipeline.
  arXiv  Detail & Related papers  (2026-07-13T21:18:52Z)
• Recovering Input Text from Hidden States: Study of Gradient-Based Inversion of Decoder-Only Language Models [0.0]
  We study the hidden-state inversion problem as a continuous embedding-space optimisation.<n>We analyse which tokens break the reconstructions and find a sharp categorical asymmetry.<n>Last-layer hidden states of GPT-2 are as sensitive as original text.
  arXiv  Detail & Related papers  (2026-07-01T12:18:12Z)
• When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents [0.0]
  Long-answer LLM agents can fail quietly: they settle on one reading of the evidence early, then spend the rest of the run defending it.<n>We define representational commitment as cross-run hidden-state convergence at a fixed reasoning step.<n>A runtime monitor detects inconsistent trajectories from hidden states at AUROC up to 0.97 (0.85--0.88 under a stricter split)
  arXiv  Detail & Related papers  (2026-06-22T07:13:13Z)
• 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)
• High-Dimensional Latents Should Be Diagnosed Through Phase Structure [56.362776482614976]
  We study autoencoder and variational-autoencoder latent spaces through the lens of spin-glass theory.<n>We formalize a latent-space spin-glass dictionary for a fixed decoder.<n>We show that driving the latent system toward the edge-of-stability of the topological trivialization regime has concrete downstream consequences.
  arXiv  Detail & Related papers  (2026-05-23T06:17:23Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge [0.0]
  Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts.<n>We propose Smart, a framework that augments dense embeddings with three explicit properties -- temporal awareness, confidence decay, and relational awareness.
  arXiv  Detail & Related papers  (2026-04-22T14:13:50Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• CLUE: Non-parametric Verification from Experience via Hidden-State Clustering [64.50919789875233]
  We show that correctness of a solution is encoded as a geometrically separable signature within the trajectory of hidden activations.<n>ClUE consistently outperforms LLM-as-a-judge baselines and matches or exceeds modern confidence-based methods in reranking candidates.
  arXiv  Detail & Related papers  (2025-10-02T02:14:33Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)

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.