Model base robustness and transfer learning asymmetries

Investigates how neural network bases (B10 vs B9) differ in fine-tuning stability and cross-base transfer, with density as a key predictor of robustness.

5 members. Each node is clickable.

Loading graph…

Drawn from 2 sources

The papers/notes whose extracted claims & findings make up this cluster.

The Guanyin Protocol: A Framework for Immediately Establishing an Understanding of Both Causality and Compassion in LLM Systems Using Semantic Anchoring4 members
2026-05-12_room-to-play-in-eval-cohort.md1 member

Bridges (2)

Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.

Few-shot anchoring & latent structure5 shared
Cross-base fine-tuning transfer asymmetry3 shared

Claims (3)

Fine-tuning reduces mismatch dr, retrieval increases effective cohesion ρd, and few-shot adjusts the budget kUnified interpretation of different adaptation methods via UCCT terms
Higher-density priors (B10) are more robust to fine-tuning than lower-density ones (B9).Interpretation of cross-base transfer asymmetry.
The bottleneck was never what to write—three slots are 80% done. The missing step is shipping, not research.

Findings (2)

Cross-base fine-tuning yields asymmetric transfer: B10 transfers most robustly, B9 leastIn-base gains accompanied by uneven OOD drops; higher-density priors more robust.
Cross-base transfer: B10 transfers most robustlyB10 fine-tuning yields smallest OOD drops when transferring to other bases