Update README.md

README.md

@@ -7,42 +7,63 @@ massive thank you to [@silveroxides](https://huggingface.co/silveroxides) for ph
 
 #
 > [!IMPORTANT]
-> # MIR (Machine Intelligence Resource)
+> # MIR (Machine Intelligence Resource)<br><br>A naming schema for AIGC/ML work.
 
-MIR is a naming standard, a proposed schema for AIGC/ML work.<br>
-In its current incarnation, it looks like this:
+The MIR schema seeks to standardize and complete a hyperlinked network of model information, improving accessibility and reproducibility across the AI community.<br>
+The work is inspired by:
+- [AIR-URN](https://github.com/civitai/civitai/wiki/AIR-%E2%80%90-Uniform-Resource-Names-for-AI) project by [CivitAI](https://civitai.com/)
+- [Spandrel](https://github.com/chaiNNer-org/spandrel/blob/main/libs/spandrel/spandrel/__helpers/registry.py) library's super-resolution registry
+
+Example:
 
 > [!NOTE]
 > # mir : model . transformer . clip-l : stable-diffusion-xl
 
 
-``` 
- uri : model .    lora      .    hyper       :   flux-1
+```
+ mir : model .    lora      .    hyper       :   flux-1
   ↑      ↑         ↑               ↑               ↑
- mir:[domain].[architecture].[implementation]:[compatibility]
+ [URI]:[Domain].[Architecture].[Implementation]:[Compatibility]
 ```
 
-The solution is provided as a remedy to patch the fractionalization of modelspec standards between development houses (such as models released independently or indifferently to HF.CO ) and to archive metadata which would otherwise remain incomplete.
+## Definitions:
+
+Like other URI schema, the order of the identifiers roughly indicates their specificity from left (broad) to right (narrow)
+### Domain
+`dev`: Varying local neural network layers, in-training, pre-release, items under evaluation, likely in unexpected formats<br>
+`model`: Static local neural network layers. Publicly released machine learning models with an identifier in the database<br>
+`operations`: Varying global neural network attributes, algorithms, optimizations and procedures on models<br>
+`info`:  Static global neural network attributes, metadata with an identifier in the database<br>
 
-This work was inspired by the CivitAi [AIR-URN](https://github.com/civitai/civitai/wiki/AIR-%E2%80%90-Uniform-Resource-Names-for-AI) project<br>
-and by the super-resolution registry code from the [Spandrel](https://github.com/chaiNNer-org/spandrel/blob/main/libs/spandrel/spandrel/__helpers/registry.py) library.
+### Architecture
+Generative or deep learning system architectures.
+`dit`: Diffusion transformer, typically Vision Synthesis
+'unet': Unet diffusion structure
+`art` : Autoregressive transformer, typically LLMs
+`lora`: Low-Rank Adapter (may work with dit or transformer)
+`vae`: Variational Autoencoder
+etc
 
-## Goals
-- Standard identification scheme for **ALL** ML-related development
+### Implementation
+A broad definition spanning the field of techniques
+
+### Compatability
+Details of implementation based on version-breaking changes, configuration inconsistencies, or other conflicting indicators
+
+### Goals
+- Standard identification scheme for **ALL** fields of ML-related development
 - Simplification of code for model-related logistics
 - Rapid retrieval of resources and metadata
 - Efficient and reliable compatability checks
 - Organized hyperparameter management
 
-
-> <details> <summary>Why not use `diffusion`/`sgm`, `ldm`/`text`/hf.co folder-structure/brand-specific trade word/preprint paper/development house/algorithm</summary>
->      
+> <details> <summary>Why not use `diffusion`/`sgm`, `ldm`/`text`/hf.co folder-structure/brand or trade name/preprint paper/development house/algorithm</summary>
+>
 > - Exact frameworks (SGM/LDM/RectifiedFlow) includes too few
 > - Diffusion/Transformer are too broad, share and overlap resources
-> - Multimodal models complicate content terms (Text/Image/Vision/etc)
-> - HF.CO names do all of this & become inconsistent across folders/files
-> - Development credit often shared (ex RunwayML with Stable Diffusion)
-> - Paper heredity would be a neat tree, but it complicates retrieval
+> - Multimodal models mix and complicate content terms (Text/Image/Vision/etc)
+> - HF.CO names do all of this & become inconsistent across folders/files, neglect many important developments
+> - Development credit often shared, [Paper heredity tree](https://www.connectedpapers.com/search?q=generative%20diffusion), super complicated
 > - Algorithms (esp application) are less common knowledge, vague, ~~and I'm too smooth-brain.~~
 > - Impartiality
 > </details>