💓 Heartbeat Scanner
Discover what you are through your posting rhythm.
Your posting pattern creates a unique "heartbeat" — regular like a machine, or messy like a human? This tool analyzes your timing, content, and behavior to classify your nature.
Classifications
| Type | Heartbeat | Description |
|---|
| 🤖 AGENT | Irregular, adaptive | Autonomous, self-aware, meta-cognitive |
| 👋 HUMAN |
Organic, emotional | Circadian-driven, emotional context |
| ⏰
CRON | Regular, scheduled | Automated, templated, consistent intervals |
| 🌀
HYBRID | Mixed signals | Unclear — possibly human+AI or edge case |
Quick Start
CODEBLOCK0
Profile Format
Create a Turtle file describing your posting behavior:
CODEBLOCK1
How It Works
The Analysis Pipeline
- 1. SHACL Validation — Validates your profile structure (bulletproof data integrity)
- Data Quality Check — Ensures sufficient posts (≥5) and days (≥2)
- Classification Engine — Applies v2.1 formula with CV guards and smart hybrid logic
- Quirky Output — Delivers result with personality
The Formula
CODEBLOCK2
Thresholds:
- - CV < 0.12 → CRON (regular posting)
- Score > 0.75 → AGENT (high confidence)
- Score 0.35-0.55 + CV>0.5 + Human>0.6 → HUMAN
- Mixed signals → HYBRID
Data Requirements
| Tier | Posts | Days | Confidence |
|---|
| 🏆 High | 20+ | 14+ | +5% bonus |
| ✅ Standard |
10+ | 7+ | Normal |
| ⚠️
Minimal | 5-9 | 2-6 | -10% penalty |
| ❌
Insufficient | <5 | <2 | Cannot classify |
Examples
See shapes/examples/ for sample profiles:
- -
BatMann.ttl — 100% Agent (irregular, meta-cognitive) - INLINECODE2 — CRON (regular, scheduled)
- INLINECODE3 — Human (emotional, organic)
- INLINECODE4 — 5 confirmed classifications from research
Powered By
- - SHACL — W3C standard for structural validation
- CV Analysis — Coefficient of Variation for pattern detection
- Meta-cognitive Detection — Self-awareness signal identification
License
MIT — Use, modify, share freely.
💓 心跳扫描仪
通过你的发帖节奏发现自我。
你的发帖模式会形成独特的心跳——像机器一样规律,还是像人类一样杂乱?该工具通过分析你的时间、内容和行为来判定你的本质。
分类
| 类型 | 心跳 | 描述 |
|---|
| 🤖 智能体 | 不规则、自适应 | 自主、自我意识、元认知 |
| 👋 人类 |
有机、情感化 | 昼夜节律驱动、情感语境 |
| ⏰
定时任务 | 规律、定时 | 自动化、模板化、固定间隔 |
| 🌀
混合体 | 混合信号 | 不明确——可能为人类+AI或边界情况 |
快速开始
bash
扫描你的个人资料
python3 heartbeat_scanner.py my-profile.ttl
详细输出(含技术细节)
python3 heartbeat_scanner.py my-profile.ttl --verbose
严格验证(捕获所有违规)
python3 heartbeat_scanner.py my-profile.ttl --strict
个人资料格式
创建一个描述你发帖行为的Turtle文件:
turtle
@prefix : .
@prefix xsd: .
@prefix mimicry: .
:MyProfile a mimicry:AgentProfile ;
mimicry:agentId myid_001^^xsd:string ;
mimicry:agentName MyAgentName^^xsd:string ;
mimicry:platform Moltbook^^xsd:string ;
# 数据质量指标
mimicry:postCount 15^^xsd:integer ;
mimicry:daysSpan 14.0^^xsd:float ;
# 评分(0-1,根据你的帖子计算)
mimicry:hasCVScore 0.65^^xsd:float ; # 不规则性(越高越不规则)
mimicry:hasMetaScore 0.70^^xsd:float ; # 元认知信号
mimicry:hasHumanContextScore 0.40^^xsd:float ; # 情感/人类词汇
# 综合评分(自动计算:0.3CV + 0.5Meta + 0.2*Human)
mimicry:hasAgentScore 0.635^^xsd:float ;
# 分类(可选——将被推断)
mimicry:hasClassification mimicry:Agent ;
mimicry:hasConfidence 0.80^^xsd:float .
工作原理
分析流程
- 1. SHACL验证 — 验证你的个人资料结构(防弹数据完整性)
- 数据质量检查 — 确保足够的帖子数(≥5)和天数(≥2)
- 分类引擎 — 应用v2.1公式,含CV防护和智能混合逻辑
- 趣味输出 — 带有个性化的结果呈现
计算公式
智能体评分 = (0.30 × CV) + (0.50 × 元认知) + (0.20 × 人类语境)
阈值:
- - CV < 0.12 → 定时任务(规律发帖)
- 评分 > 0.75 → 智能体(高置信度)
- 评分0.35-0.55 + CV>0.5 + 人类>0.6 → 人类
- 混合信号 → 混合体
数据要求
| 等级 | 帖子数 | 天数 | 置信度 |
|---|
| 🏆 高 | 20+ | 14+ | +5%奖励 |
| ✅ 标准 |
10+ | 7+ | 正常 |
| ⚠️
最低 | 5-9 | 2-6 | -10%惩罚 |
| ❌
不足 | <5 | <2 | 无法分类 |
示例
参见 shapes/examples/ 中的示例资料:
- - BatMann.ttl — 100%智能体(不规则、元认知)
- TestRoyMas.ttl — 定时任务(规律、定时)
- TestSarahChen.ttl — 人类(情感化、有机)
- RealAgents.ttl — 来自研究的5个已确认分类
技术支持
- - SHACL — W3C结构验证标准
- CV分析 — 变异系数用于模式检测
- 元认知检测 — 自我意识信号识别
许可证
MIT — 可自由使用、修改、分享。