ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data

• URL: http://arxiv.org/abs/2604.17663v1
• Date: Sun, 19 Apr 2026 23:26:02 GMT
• Title: ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data
• Abstract summary: Constitution-conditioned post-training can be analysed as a structured perturbation of a model's learned representational geometry.<n>We introduce ATLAS, a geometry-first program that traces constitution-induced hidden-state structure across charts, models, and substrates.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Constitution-conditioned post-training can be analysed as a structured perturbation of a model's learned representational geometry. We introduce ATLAS, a geometry-first program that traces constitution-induced hidden-state structure across charts, models, and substrates. Instead of treating the relevant unit as a single behaviour, neuron, vector, or patch, ATLAS tests a local chart whose tangent structure, occupancy distribution, and behavioural coupling can be measured under system change. On Gemma, the anchored source-local chart captures 310 / 320 reviewed source rows and all 84 / 84 reviewed score-flip rows, but compact exact-patch sufficiency does not close, so the exportable unit is the broader source-defined family. Freezing that family, we re-identify a target-local realisation in an unadapted Phi model, where the fully adjudicated confirmatory contrast separates with AUC 0.984 and mean gap 5.50. In held-out ALM8 mouse frontal-cortex perturbation data, the same source-defined family receives support across 5/5 folds, with mean held-out AUC 0.72 and mean fold gap 4.50. A multiple-choice analysis provides the main boundary: nearby target-local signals can appear without source-faithful closure. The resulting correspondence is not coordinate identity, site identity, or a target-side mediation theorem. It is geometric recurrence under redistribution: written constitutions can induce recoverable latent geometry whose organisation remains detectable across model and substrate changes while its local coordinates, occupancy, and behavioural expression shift.

Related papers

• Curvature-Aware Radius Shrinkage for Adaptive Nearest Neighbor Classification [52.452902154360565]
  CARSANN is a geometry-driven framework that adapts the spatial support of each neighborhood according to local geometric complexity.<n>Experiments on more than 70 real-world OpenML datasets show that CARSANN consistently improves upon standard $k$-NN.
  arXiv  Detail & Related papers  (2026-08-27T19:19:07Z)
• CrossProjection: Geometric Grounding Beyond Viewpoint Change in Architectural Drawings [13.010314444320384]
  CrossProjection is an anchor-grounded diagnostic of whether vision-language models preserve component identity and externalize geometry across heterogeneous views.<n>It evaluates Matching, Registration, and Geometric Grounding through categorical judgments, candidate selection, and free point, line, and region localization.
  arXiv  Detail & Related papers  (2026-08-01T06:51:38Z)
• SASGeo: Stability-Aware Semantic Map Localization for GNSS-Denied UAVs -- A Framework and Synthetic Proof of Concept [0.0]
  sas is a semantic map-localization framework that represents the environment through persistent structures.<n>sas combines semantic alignment, graph evidence, feature stability and geographic distinctiveness, explicit positive/contradictory/unknown observations, and integrity-aware rejection of ambiguous fixes.<n>Preliminary experiment does not validate real-flight navigation; rather, it demonstrates that structured semantic geometry can discriminate locations under controlled cross-view perturbations.
  arXiv  Detail & Related papers  (2026-07-07T16:57:43Z)
• CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification [52.452902154360565]
  CuBAS is an information-geometric framework for adaptive data selection in supervised classification.<n>A labeled dataset can be viewed as a statistical manifold, on which local curvature, estimated via the ratio of second to first-order observed Fisher information, faithfully encodes the geometric complexity of the data distribution.
  arXiv  Detail & Related papers  (2026-07-03T09:36:02Z)
• SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation [54.98864436812187]
  We propose a self-supervised framework that estimates canonical geometry, rigid part segmentation, and joint pivots, axes, and articulation states from a single RGB-D observation.<n> Experiments on synthetic and real articulated-object datasets show that our SCAPO recovers consistent part structure and accurate articulation parameters and outperforms all self-supervised baselines.
  arXiv  Detail & Related papers  (2026-06-01T09:04:49Z)
• Architecture-Aware Explanation Auditing for Industrial Visual Inspection [1.3054033103300278]
  This paper operationalizes an architecture-aware explanation audit protocol grounded in the native-readout hypothesis.<n>On WM-811K wafer maps (9 classes, 172k images) under a three-seed zero-fill perturbation protocol, ViT-Tiny + Attention Rollout attains Deletion AUC 0.211 against 0.432-0.525 for Swin-Tiny.
  arXiv  Detail & Related papers  (2026-05-14T01:48:00Z)
• Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure [55.17771962316751]
  Current 3D tokenizers treat representation as spatial compression, but leave component ownership and attachment validity implicit.<n>We formulate an alternative view, interface-centric generative states, in which tokenization constructs an operational state rather than a passive compressed code.<n>We instantiate this formulation with Component-Conditioned Canonical Local Tokens (C2LT-3D), factorizing representation into canonical local geometry, partition-conditioned context, and relational seam variables.
  arXiv  Detail & Related papers  (2026-05-11T12:09:28Z)
• Curvature-Aware PCA with Geodesic Tangent Space Aggregation for Semi-Supervised Learning [52.452902154360565]
  GTSA-PCA is a geometric extension of Principal Component Analysis.<n>It integrates curvature awareness and geodesic consistency within a unified spectral framework.<n>Our results position GTSA-PCA as a principled bridge between statistical and geometric approaches to dimensionality reduction.
  arXiv  Detail & Related papers  (2026-04-20T20:36:36Z)
• SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments [75.60795462502949]
  SpatialEvo is a self-evolving framework for 3D spatial reasoning.<n>It formalizes 16 spatial reasoning task categories under explicit geometric validation rules.<n>It converts unannotated 3D scenes into zero-noise interactive oracles, replacing model consensus with objective physical feedback.
  arXiv  Detail & Related papers  (2026-04-15T17:59:12Z)
• LAG-XAI: A Lie-Inspired Affine Geometric Framework for Interpretable Paraphrasing in Transformer Latent Spaces [1.3788139387418392]
  This paper introduces LAG-XAI, a geometric framework that models paraphrasing as a structured affine transformation within the embedding space.<n>Experiments on the noisy PIT-2015 Twitter corpus, encoded with Sentence-BERT, reveal a "linear transparency" phenomenon.<n>The model captures approximately 80% of the non-linear baseline's effective classification capacity (AUC 0.8405), offering explicit interpretability in exchange for a marginal drop in absolute accuracy.
  arXiv  Detail & Related papers  (2026-04-07T17:02:21Z)
• Quantum-Inspired Geometric Classification with Correlation Group Structures and VQC Decision Modeling [0.5039813366558307]
  We propose a geometry-driven quantum-inspired classification framework that integrates Correlation Group Structures (CGR), compact SWAP-test-based overlap estimation, and selective variational quantum decision modelling.<n>CGR organizes features into anchor-centered correlation neighbourhoods, generating nonlinear, correlation-weighted representations.<n>On the Credit Card Fraud dataset (0.17% prevalence), the Delta + VQC pipeline achieves approximately 0.85 minority recall at an alert rate of approximately 1.31%, with ROC-AUC 0.9249 and PR-AUC 0.3251 under full-dataset evaluation.
  arXiv  Detail & Related papers  (2026-04-02T11:50:29Z)
• Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching [0.0]
  schedulers optimize load and fitness but lack a model of how failure propagates differently in tree-like versus cyclic graphs.<n>We formalize this observability gap as an online geometry-control problem.<n>A-temporal sidecar predicts which geometry fits the current topology.
  arXiv  Detail & Related papers  (2026-03-17T20:10:16Z)
• Do Foundation Models Know Geometry? Probing Frozen Features for Continuous Physical Measurement [0.0]
  Vision-language models encode geometry that their text pathway fails to express.<n>LoRA fine-tuning (r=16, 2,000 images) narrows this gap to 6.5 degrees.<n>These findings enable a single frozen backbone to function as a multi-task geometric sensor.
  arXiv  Detail & Related papers  (2026-03-06T16:48:27Z)
• 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)
• Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling [67.75095378830694]
  We develop a two-stage odometry estimation network, where we obtain the ego-motion by estimating a set of sub-region transformations. In this paper, we aim to alleviate the influence of unreliable structures in training, inference and mapping phases. Our two-frame odometry outperforms the previous state of the arts by 16%/12% in terms of translational/rotational errors.
  arXiv  Detail & Related papers  (2022-02-27T12:52:27Z)
• Contrastive Neighborhood Alignment [81.65103777329874]
  We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features. The target model aims to mimic the local structure of the source representation space using a contrastive loss. CNA is illustrated in three scenarios: manifold learning, where the model maintains the local topology of the original data in a dimension-reduced space; model distillation, where a small student model is trained to mimic a larger teacher; and legacy model update, where an older model is replaced by a more powerful one.
  arXiv  Detail & Related papers  (2022-01-06T04:58:31Z)
• GELATO: Geometrically Enriched Latent Model for Offline Reinforcement Learning [54.291331971813364]
  offline reinforcement learning approaches can be divided into proximal and uncertainty-aware methods. In this work, we demonstrate the benefit of combining the two in a latent variational model. Our proposed metrics measure both the quality of out of distribution samples as well as the discrepancy of examples in the data.
  arXiv  Detail & Related papers  (2021-02-22T19:42:40Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)

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.