Skip to main content

三元九维19683认知体系(trinary19683)

把《三元九维19683体系》(729 份语料、19683 卦)构建为可复算、可证伪、可演化的确定性符号认知层——可被 LLM 与 Agent 调用。

它是什么

不是"算命"工具,而是一个可生长的确定性认知系统,分两层:

① 三元九维确定性推理层

  • 每卦 = 上·中·下三层 × 3 爻,三态(D 承载 / R 判定 / T 增益),共 19683 卦
  • 确定性自适配等级(5 维结构签名,19683 卦 100% 可复算)
  • 动态势能流推演、三态公理语义推导、时序演化路径

② 认知棋盘 v2(升级层)

  • 证伪动力学:三档证伪(全命中硬迁/部分降置信/预设外降级),可逆,治幻觉
  • 元棋盘 L4:M(X) 元评估 + 策略调整 + M(M(X)) 递归自省(自指/反思)
  • 多 Agent 共享协议 L5:冲突定位到具体迁移边 + 共享证据证伪对撞 + 可复算联合链

安装

pip install trinary19683

首次使用拉取全量知识库(可选,用于全文查询/检索):

python3 scripts/download_data.py   # 从 HuggingFace 拉取 19683 卦全量数据

快速开始

# 确定性等级
from level9 import level9_str
print(level9_str("RRRTTTDDD"))            # → 中等(可复算)

# 语义推导(从三态公理,不依赖语料)
from infer import infer_by_num
print(infer_by_num(14, 27, 1)["上层输出"])

# 动态推演(自下而上势能流)
from dynamics import flow
nodes, final = flow("DDDTTTRRR")

# 证伪器(认知棋盘)
from cognition_board import Stance, Evidence, Refuter
r = Refuter(); r.add_condition("P", ["反证A"], all_required=True, fallback="Q")
s, e = r.check(Stance("P", {"ACT": 1.0}, confidence=0.8), Evidence({"反证A": True}))

本地服务 / 控制台

trinary-server 8000     # 或 python3 server.py 8000
# 浏览器打开 http://127.0.0.1:8000/

离线单文件模型:三元九维19683_离线模型.html(双击即用,含推演/推导/等级/扰动/演化建议/路径)。

文档

  • 三元九维19683_使用与设计总说明书.md
  • 三元九维19683_开放API文档.md
  • 认知棋盘v2设计提案.md

License

Apache-2.0

Metadata

Release files for trinary19683 2.6.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for trinary19683 2.6.0
File Size Uploaded Provenance
trinary19683-2.6.0.tar.gz 34.1 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for trinary19683 2.6.0
File Interpreter ABI Platform
trinary19683-2.6.0-py3-none-any.whl Python 3 none any Details

Total release size: 67.9 kB

Release files / trinary19683-2.6.0.tar.gz

Download URL trinary19683-2.6.0.tar.gz
Size 34.1 kB
Tags Source
SHA-256 checksum
How to use checksums
a0625e23d85e55c374d41c2eda1829588e2875064f050e33ed9d50f9843656e7
BLAKE2b-256 checksum
How to use checksums
40f4e86e9f615787329da7bb37029da5649b1b23326bf7227ac15e9e2c927332
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.11

Release files / trinary19683-2.6.0-py3-none-any.whl

Download URL trinary19683-2.6.0-py3-none-any.whl
Size 33.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1628b1c805ea8b309fa3d248f309ba6f98f1a4236195e675e1dd0bb4907de187
BLAKE2b-256 checksum
How to use checksums
af2dfadada3b789885cba04c81a511f3e12a16ec77c6e8ba24a92d414c52c29e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.11

Security for trinary19683 2.6.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Release history Release notifications | RSS feed

This release

2.6.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page