What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization

arXiv:2609.17637 · cs.AI, cs.LG · Submitted 2026-09-15 · Read on arXiv

cs.AI, cs.LG

Submitted: 2026-09-15

Updated: 2026-09-20

Comments: 16 pages, 2 figures, 5 tables. Preregistered fresh-world confirmation of arXiv:2608.20054; related companion study: arXiv:2609.11365

Code: https://github.com/tokenosopher/populus-evidence-partitioning

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 28× in this paper · explained in 1 episode
• Generalization — 13× in this paper · explained in 13 episodes
• Redundancy — 9× in this paper · explained in 2 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Compositional Generalization — 4× in this paper · explained in 4 episodes
• Provenance — 4× in this paper · explained in 4 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Generative AI — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Causal Abstractions of Neural Networks
• Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells
• What You Can't See Is What You Learn: Slot-Selective Evidence Masking Favors Compositional Generalization in Shared-Genome Language-Model Societies
• Qwen2.5 Technical Report

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection