Skip to content

Commit 33fc9c4

Browse files
authored
Streamline README onboarding (#835)
1 parent 28dbbf7 commit 33fc9c4

3 files changed

Lines changed: 41 additions & 151 deletions

File tree

README.md

Lines changed: 37 additions & 98 deletions
Original file line numberDiff line numberDiff line change
@@ -26,104 +26,6 @@ an MCP server and is also available as a CLI and Python library. Agents can use
2626
it to compute invariants, search for examples or counterexamples, work with
2727
solver artifacts, and check formal proofs.
2828

29-
An agent can do plenty of mathematics directly: choose a representation, spot a
30-
useful theorem, simplify a small expression, or propose a proof. Jacobian is
31-
for the part that benefits from an executable mathematical system and a clear
32-
record of what happened: exact computation, finite search, solver certificates,
33-
or formal proof checking.
34-
35-
It does not replace an agent's mathematical strategy or prescribe a workflow.
36-
The agent decides what to investigate and which operation to use. Jacobian
37-
exposes focused operations through a common interface, and keeps results
38-
visible as typed values or durable artifacts.
39-
40-
## Why use a mathematical tool?
41-
42-
The model's weights provide mathematical intuition and strategy, but an answer
43-
produced in conversation is not automatically a reproducible calculation or a
44-
proof. Jacobian gives the agent a way to hand the brittle or exact part of a
45-
problem to a maintained mathematical backend, then retain the result's scope
46-
and evidence.
47-
48-
| An agent can do directly | Jacobian adds when it matters |
49-
| --- | --- |
50-
| Propose an approach, a candidate, or a proof idea | Execute exact algebra, bounded search, SAT/SMT solving, graph computation, or Lean checking |
51-
| Explain why a result seems plausible | Record the inputs, result, scope, status, and provenance |
52-
| Report that a solver or search succeeded | Independently check a witness, certificate, or formal proof for the exact claim |
53-
54-
The important boundary is that a successful computation is not automatically a
55-
proof. Jacobian labels a result according to what has actually happened:
56-
57-
- **heuristic**: a plausible result from a model, search, or unchecked witness;
58-
- **computed**: a deterministic calculation with a tested software contract;
59-
- **verified**: evidence independently checked for the exact claim and scope.
60-
61-
A **witness** is a concrete object that establishes a claim. For example, `2`
62-
is a witness for “there exists an even prime”; `2` is also a counterexample to
63-
“every prime is odd.” Search may find such an object, but a separate checker
64-
must establish that it really satisfies the stated property. Finding no witness
65-
does not prove that none exists unless the search scope is complete and that
66-
completeness is established.
67-
68-
## A simple counterexample
69-
70-
Here is a small counterexample an agent can reason about directly:
71-
72-
```text
73-
Claim: every prime is odd
74-
Agent checks: 2 is prime and even
75-
Counterexample: 2
76-
Conclusion: the claim is false
77-
```
78-
79-
Here `2` is the **witness**: the actual example that disproves the claim. The
80-
same idea applies when the concrete example is difficult to find or check, such
81-
as a counterexample among millions of possible graphs. The agent still chooses
82-
the claim and search strategy; Jacobian can run the exact search and save the
83-
resulting graph and checks for later inspection.
84-
85-
In this documentation:
86-
87-
- **candidate** means an example not yet checked;
88-
- **witness** means an example that establishes or disproves a claim;
89-
- **verification** means checking that exact example really has the claimed
90-
property; and
91-
- **artifact** means a saved mathematical object or piece of evidence.
92-
93-
## Jacobian, Lean, SAT, and the model
94-
95-
Jacobian supports Lean, SAT/SMT, computer algebra, and other mathematical
96-
systems as backends. It does not replace them or compete with them.
97-
98-
| System | Main job |
99-
| --- | --- |
100-
| Model | Proposes ideas and chooses a mathematical strategy |
101-
| CAS / SAT / SMT | Calculates or searches in a specialized domain |
102-
| Lean | Checks a formal, general mathematical proof |
103-
| Jacobian | Lets an agent discover and use those systems through one interface, while retaining typed results, scope, saved evidence, provenance, and verification status |
104-
105-
## A small example
106-
107-
Suppose an agent is testing the claim **`F` is injective.”**
108-
109-
A search returns two points, `p` and `q`, with the same image. That is a
110-
candidate counterexample, not yet a trusted conclusion.
111-
112-
```text
113-
p ≠ q
114-
F(p) - F(q) = 0
115-
```
116-
117-
An independent checker confirms those relations exactly. The checked collision
118-
can then be bound to the original claim and checker identity, producing
119-
`FALSE · VERIFIED`.
120-
121-
If the search finds nothing, times out, is cancelled, or fails, the claim
122-
remains `UNKNOWN`. Absence of a witness is not proof.
123-
124-
The [introductory tutorial](docs/tutorials/first-verified-result.md) shows the
125-
same boundary in a runnable graph example.
126-
12729
## Quickstart
12830

12931
For a guided user-local install:
@@ -179,6 +81,43 @@ mathematical runtime, not a JavaScript dependency tree.
17981
To run the exact code in a clone, follow
18082
[Configure an agent from a source checkout](docs/how-to/setup-agent-from-source.md).
18183

84+
## A simple counterexample
85+
86+
Here is a small counterexample an agent can reason about directly:
87+
88+
```text
89+
Claim: every prime is odd
90+
Agent checks: 2 is prime and even
91+
Counterexample: 2
92+
Conclusion: the claim is false
93+
```
94+
95+
Here `2` is a witness: the actual example that disproves the claim. For a much
96+
larger search, Jacobian can preserve the candidate and the exact checks used to
97+
establish it.
98+
99+
## A checked counterexample
100+
101+
Suppose an agent is testing the claim **`F` is injective.”**
102+
103+
A search returns two points, `p` and `q`, with the same image. That is a
104+
candidate counterexample, not yet a trusted conclusion.
105+
106+
```text
107+
p ≠ q
108+
F(p) - F(q) = 0
109+
```
110+
111+
An independent checker confirms those relations exactly. The checked collision
112+
can then be bound to the original claim and checker identity, producing
113+
`FALSE · VERIFIED`.
114+
115+
If the search finds nothing, times out, is cancelled, or fails, the claim
116+
remains `UNKNOWN`. Absence of a witness is not proof.
117+
118+
The [introductory tutorial](docs/tutorials/first-verified-result.md) shows the
119+
same boundary in a runnable graph example.
120+
182121
## Available mathematics
183122

184123
The installed operations vary with local providers, but the maintained

README.zh-CN.md

Lines changed: 0 additions & 43 deletions
Original file line numberDiff line numberDiff line change
@@ -35,49 +35,6 @@
3535

3636
Jacobian 为 AI 智能体提供小型、可组合的数学操作,而不是一个不透明的通用求解器。智能体可以构造对象、计算不变量、搜索见证,并将精确证据提交给独立的检查器。每一步都会以类型化结果或 artifact 的形式保持可见。
3737

38-
智能体当然可以直接做许多数学工作:选择表示法、联想到有用的定理、化简小表达式,或提出证明思路。Jacobian 服务于更需要可执行数学系统和清晰记录的部分,例如精确计算、有限搜索、求解器证书和形式化证明检查。它不替代智能体的数学策略,也不规定研究流程;智能体决定研究什么、使用哪个操作以及何时停止。
39-
40-
模型权重提供数学直觉和策略,但对话中的答案不自动成为可重放的计算或证明。Jacobian 让智能体把问题中脆弱或需要精确性的部分交给受维护的数学 backend,并保留结果的范围和证据。
41-
42-
| 智能体可直接完成 | Jacobian 在需要时提供 |
43-
| --- | --- |
44-
| 提出方法、候选对象或证明思路 | 执行精确代数、有限搜索、SAT/SMT 求解、图计算或 Lean 检查 |
45-
| 解释结果为何看似可信 | 记录输入、结果、范围、状态和出处 |
46-
| 报告求解器或搜索成功 | 独立检查精确命题的见证、证书或形式化证明 |
47-
48-
**见证**是能确立命题的具体对象。例如,`2` 是“存在偶素数”的见证;`2` 也是“所有素数都是奇数”的反例。搜索可以找到见证,但独立检查器必须确认它确实满足所述性质。除非搜索范围完整且其完整性也已确立,否则没有找到见证并不代表不存在见证。
49-
50-
## 一个简单的反例
51-
52-
这里是智能体可以直接推理的一个小反例:
53-
54-
```text
55-
命题:所有素数都是奇数
56-
智能体检查:2 是素数且是偶数
57-
反例:2
58-
结论:该命题为假
59-
```
60-
61-
这里的 `2`**见证**:实际推翻该命题的例子。同一概念也适用于具体例子难以寻找或检查的情形,例如要在数百万个图中寻找反例。智能体仍然选择命题和搜索策略;Jacobian 可以执行精确搜索,并保存得到的图和检查结果以供之后查看。
62-
63-
本文档中:
64-
65-
- **候选对象**是尚未检查的例子;
66-
- **见证**是能确立或推翻命题的例子;
67-
- **验证**是检查该确切例子是否真的具有所声明性质;
68-
- **artifact** 是保存的数学对象或一份证据。
69-
70-
## Jacobian、Lean、SAT 与模型
71-
72-
Jacobian 将 Lean、SAT/SMT、计算机代数系统和其他数学系统作为可选 backend 支持;它不替代这些系统,也不与它们竞争。
73-
74-
| 系统 | 主要职责 |
75-
| --- | --- |
76-
| 模型 | 提出想法并选择数学策略 |
77-
| CAS / SAT / SMT | 在专门领域中计算或搜索 |
78-
| Lean | 检查形式化的一般数学证明 |
79-
| Jacobian | 让智能体通过一个接口发现和使用这些系统,并保留类型化结果、范围、保存的证据、出处和验证状态 |
80-
8138
搜索结果、求解器状态、模型答案、超时或评分都不会直接升级为 `VERIFIED`。只有经过操作者授权的检查器才能生成已验证记录,并且该记录必须绑定到确切的命题、候选对象、范围、语义、证书格式和检查器身份。
8239

8340
<a id="quickstart"></a>

docs/index.md

Lines changed: 4 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -7,16 +7,10 @@ guide for a specific task, consult reference material for exact contracts, and
77
read the explanations for design rationale.
88

99
Jacobian exposes composable mathematical capabilities through an MCP server,
10-
CLI, and Python library. An agent still owns the mathematical strategy:
11-
choosing a representation, candidate, and next operation. Jacobian supplies
12-
the executable part when exact computation, bounded search, solver evidence,
13-
or formal proof checking is useful.
14-
15-
Each capability has one mathematically atomic, agent-visible outcome. A search
16-
may return a concrete witness or counterexample; a separate authorized checker
17-
can establish whether that exact object proves the stated claim in its declared
18-
scope. Optional workflows preserve intermediate artifacts. This keeps
19-
heuristic, computed, and independently verified results distinct. The
10+
CLI, and Python library. Capabilities have mathematically atomic,
11+
agent-visible outcomes; agents compose them into research strategies. Optional
12+
workflows preserve intermediate artifacts, and only operator-authorized
13+
independent checkers may promote exact evidence to a verified result. The
2014
[product model](explanation/product-blueprint.md) defines the capability
2115
contract and ownership boundaries.
2216

0 commit comments

Comments
 (0)