> For the complete documentation index, see [llms.txt](https://scribes.gitbook.io/scribes-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://scribes.gitbook.io/scribes-docs/for-builders/rarity-worked-through.md). # rarity worked through scribes © 2026 this page takes one example scribe through the rarity calculation. > the scoring method and the value bands below are a proposed starting point. final bands and weights will be published before launch. all numbers here are illustrative. ### step 1: extract the values the bot reads the inscribed files and extracts: * **model**: qwen3 0.6b * **parameters**: 0.6b * **weight**: 480 mb * **personality**: 1,840 words * **tools**: 4 * **memory**: 12 entries * **birth number**: 212 * **autograph**: yes ### step 2: group continuous values into bands values like file size or word count are nearly always unique, so they are grouped into bands before comparing. for example: * **weight**: under 100 mb, 100 to 500 mb, 500 mb to 2 gb, over 2 gb * **personality**: under 500 words, 500 to 1,500, 1,500 to 3,000, over 3,000 * **memory**: none, 1 to 25 entries, 26 to 100, over 100 * **birth number**: first 100, first 1,000, first 10,000, later ### step 3: find each share say 12,904 scribes exist. for each attribute, count how many share this scribe's value or band. the score for each attribute is 1 divided by its share. * **model**: qwen3 0.6b, 62% of scribes, score 1.6 * **parameters**: 0.6b, 62% of scribes, score 1.6 * **weight**: 100 to 500 mb, 41% of scribes, score 2.4 * **personality**: 1,500 to 3,000 words, 8% of scribes, score 12.5 * **tools**: 4, 15% of scribes, score 6.7 * **memory**: 1 to 25 entries, 30% of scribes, score 3.3 * **birth number**: first 1,000, 7.7% of scribes, score 12.9 * **autograph**: yes, 0.3% of scribes, score 333.3 ### step 4: add up and rank this scribe's total comes to about **374**. ranking every scribe by total puts this one at **#38 of 12,904**. scribes that hold an autograph end up near the top, since only one scribe per model can ever have it. ### step 5: recalculate every new scribe changes the shares, so scores and ranks are recalculated at each birth. the extracted values stay fixed. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://scribes.gitbook.io/scribes-docs/for-builders/rarity-worked-through.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.