Update model card: added DISC section
Browse files
README.md
CHANGED
|
@@ -36,3 +36,17 @@ By Convergent Intelligence LLC: Research Division
|
|
| 36 |
|
| 37 |
|
| 38 |
*Last updated: 2026-03-28 12:58 UTC*
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
|
| 37 |
|
| 38 |
*Last updated: 2026-03-28 12:58 UTC*
|
| 39 |
+
|
| 40 |
+
## Discrepancy Calculus Foundation
|
| 41 |
+
|
| 42 |
+
This model is part of the [Convergent Intelligence LLC: Research Division](https://huggingface.co/reaperdoesntknow) portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model *should* produce and what it *actually* produces.
|
| 43 |
+
|
| 44 |
+
DISC treats training singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as **structural signals** that reveal the geometry of the learning problem. Key concepts:
|
| 45 |
+
|
| 46 |
+
- **Discrepancy Operator (D):** Measures the gap between expected and observed behavior at each training step
|
| 47 |
+
- **Jump Sets:** Boundaries where model behavior changes discontinuously — these are *features*, not bugs
|
| 48 |
+
- **Ghost Imprinting:** Teacher knowledge that transfers to student models through weight-space topology rather than explicit distillation signal
|
| 49 |
+
|
| 50 |
+
For the full mathematical treatment, see [Discrepancy Calculus: Foundations and Core Theory](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194).
|
| 51 |
+
|
| 52 |
+
**Citation chain:** [Structure Over Scale](https://huggingface.co/reaperdoesntknow/Structure-Over-Scale) (DOI: 10.57967/hf/8165) → [Three Teachers to Dual Cognition](https://huggingface.co/reaperdoesntknow/DualMind_Methodolgy) (DOI: 10.57967/hf/8184) → [Discrepancy Calculus](https://huggingface.co/reaperdoesntknow/Discrepancy_Calculus) (DOI: 10.57967/hf/8194)
|