← starnum.com.tw

System Card

System Card v2.0 AI-Assisted Astrology Platform

Version 2.0 · · Governance 2.0 public evidence surface

Governance 2.0 Overview

This page is part of the starnum public Governance 2.0 surface and uses the same evidence layer as the system card, data governance, transparency report, use policy, and security policy.

Governance Summary

This page is the canonical public system disclosure for platform behavior, model/provider boundaries, and evidence-backed governance.

Scope

System behavior, AI assistance boundaries, public claims, governance metrics, provider alignment, and release integrity.

Implementation Status

Version 2.0 is the source structure used to align the other public governance pages.

This System Card extends the Model Card and describes starnum.com.tw overall platform capabilities, knowledge-base infrastructure, AI-assisted pipelines, quality-assurance mechanisms, and known limitations.

1. System Overview

Platform NameStarnum Platform
Versionv5.0 (2026-04-12)
Core FeaturesZi Wei Dou Shu chart analysis, Numerology (Life Path) calculation, astrology knowledge-base articles
Target AudienceTraditional Eastern metaphysics enthusiasts; Traditional Chinese and multilingual users
Knowledge SystemZi Wei: Lu Binzhao school (Zhongzhou) San-He + Si-Hua; Numerology: Pythagorean system
Charting Engineiztro v3.x (open source, GitHub-verifiable)
AI ExecutionGoverned, task-specific agent routes with bounded inputs, verification, and fail-closed release gates
Language Support10 languages (zh-TW / zh-CN / en / ja / ko / es / vi / th / ms / id)
Deployment InfrastructureCloudflare Worker Assets + Workers, R2 object storage, and D1 indexes

2. Knowledge-Base Infrastructure

2.1 Scale

Zi Wei Dou Shu KB225+ files, 88 indexes, 8-volume structure (01-fundamentals ~ 09-advanced)
Numerology KB141 files ~56,544 lines
Total KB Scale2,758 files ~1,537,711+ lines of structured text
Vector IndexLarge-scale semantic vector database (Qdrant)
Knowledge GraphKnowledge graph (Neo4j, stars × palaces × Si-Hua)

2.2 Knowledge Quality Grading

2.3 School-Integrity Mechanism

Si-Hua viewpoints not belonging to the Lu Binzhao school are labeled with ⚠️ Non-Lu Binzhao school. The knowledge base maintains a blocklist preventing re-crawl of sources flagged for prompt injection.

3. AI-Assisted Pipelines

3.1 Chart Plain-Language Analysis Pipeline

Layer A: Chart Casting — the iztro open-source engine calculates from submitted birth facts; production chart records are served through the Worker API from R2 with a compact D1 index
Layer B: Evidence Retrieval — semantic search, graph expansion, and bounded KB slices provide supporting evidence without replacing primary chart facts
Layer C: AI-Assisted Generation — tier-specific governed agent routes produce only the sections allowed by the chart contract
Layer D: Automated Validation117 astrology hard rules and output-integrity gates block invalid or contaminated results
Layer E: Controlled Write and Readback — a single authorized writer saves through the governed chart API and closes work only after independent R2/D1 verification

3.2 Article Production Pipeline

Topic Selection — startup-check.js analyzes gaps, prioritizing uncovered 14 main-stars × 12 palaces combinations
AI-Assisted Writing — Drafts generated per 19 editorial skill packs based on KB precision slicing
Quality Validation — 232-item six-dimension automated checklist (HTML structure / SEO / Schema / internal links / translation / ads)
Multi-provider governance audit — Claude / OpenAI / Anthropic / Google Gemini governance references vote; majority FIX required to apply changes
SHA256 Integrity Verification — Every article computes a content hash to ensure post-publication integrity

4. Quality-Assurance Mechanisms

4.1 Six-Layer Closed-Loop Quality Model

  1. L1 Output Layer: 232 validations per article; failures block publication
  2. L2 Error Layer: failure log → ≥3 recurrences auto-propose a new rule
  3. L3 Performance Layer: GA4 + Cloudflare traffic feedback identifies articles needing refresh
  4. L4 Meta-Rule Layer: rule-audit.js audits the rule system itself, retiring rules untriggered for 90 days
  5. L5 Environment Layer: security headers, dependency vulnerabilities, credential expiry monitored automatically
  6. L6 Strategy Layer: quarterly strategic review benchmarked against the competitive landscape

4.2 Key Quality Metrics

Astrology Hard Rules117 (41 Four Transformations rules + 49 chart-pattern rules + 17 core-metric rules + 10 meta-rules)
Editorial Skill Modules19 skill packs (prompts/skills/)
Terminology Dictionary221 terms × 9 languages (glossary.json)
Case Library435 anonymized + verified astrology cases
Automated Quality Validation232-item checklist (sop-checklist.md)

5. Limitations & Known Boundaries

5.1 Knowledge Limitations

5.2 Known Risks of AI Assistance

6. Governance & Updates

Human Supervisormychenan (site owner, astrology researcher)
AI CollaboratorsClaude Sonnet 4.5 × 20 (Anthropic)
Independent VerificationRisk-appropriate machine checks and a separate verifier review bounded artifacts before release
Update CycleSystem Card updated quarterly; major capability changes trigger immediate updates
Public DocumentsMethodology / Model Card / Benchmark / Ethics Statement
Governance DocumentsEthics Statement / Transparency Log

Contact: Instagram @mychenan

External standards and primary sources

These primary sources inform this page. They are benchmarks, not third-party endorsements of this site.

Current Machine Audit Snapshot

This block uses only traceable local audit data. No unsupported metrics or model claims are added.

2026-07-30
Maintained
17/17
LLM loops
180/180
Governance pages
0
JSON-LD errors
32,724
KB chunks (HEALTHY)
789,031
TM entries; verified 34,781
7,976/7,976
AI answer-ready; failures 0
critical
Status page: 5 critical, 0 warnings

Content Maintenance And Update Decision

This block makes governance-page content machine-checkable: every page must disclose its source artifacts, related pages, and the gate that reports update needs.

Update Decision

This is not static copy. When source artifacts, related policies, public metrics, or generators change, AI Ops reports evidence and an AI agent decides whether the page needs edits.

Human Boundary

Systems detect, report, and preserve machine-readable evidence. Codex/Claude agents perform final judgment and repair.

Verification Command

node scripts/verify-trust-pages.js --check

Verifiable Evidence Layer

This block is not a narrative claim. Each core assertion has a claim id, source JSON, hash, and a repeatable verification command. Public pages disclose governance evidence without exposing source code, secrets, private data, or exploitable attack details.

Claim IDVerifiable valueStatusOwnerSource and verification
claim.public-url-manifest.indexable-count
Public URL and canonical inventory
38,965 indexable URLs verified sitewide node scripts/generate-public-evidence-manifest.js --dry
claim.trust-pages.audit-pass-rate
Trust page machine audit
180/180 pass verified sitewide node scripts/verify-trust-pages.js --check
claim.discovery-surface.zero-errors
AI discovery surface audit
{"errors":0,"warnings":0} verified sitewide node scripts/verify-discovery-surface.js
claim.structured-data.jsonld-errors
JSON-LD / structured data audit
{"structured_data_invalid_files":0,"breadcrumb_count":28274,"faq_count":27506,"dataset_count":30,"article_count":27406} verified sitewide node scripts/site-machine-audit.js
claim.status.sla-state
Status page SLA source
critical / 5 critical, 0 warnings verified sitewide node scripts/generate-status-page.js
claim.provider-alignment.openai-anthropic-gemini
OpenAI / Anthropic / Google Gemini benchmark alignment
benchmark alignment only unless code/config evidence exists verified sitewide node scripts/verify-public-evidence.js --check
claim.transparency-report.sha256
Transparency report SHA-256 anchor
{"report":"transparency/report-2026-Q3.json","sha256":"47b09e2ca4e8b8fe9dffdfaccef3b11212de9ee3a8a14badca8044e2481203c5"} verified sitewide node scripts/update-transparency-current-data.js
claim.release-integrity.gpg-signing
GPG signing status
GPG signing configured locally; GitHub verification pending github_verification_pending sitewide gpg --list-secret-keys --keyid-format=long && git log -1 --show-signature
claim.system-card.production-model-evidence
Production model setting source scan
{"productionModelEvidence":[]} verified system-card node scripts/verify-public-evidence.js --check
claim.system-card.quality-gates
System card machine quality gates
{"trustPages":{"pages":180,"pass":180,"fail":0},"discovery":{"errors":0,"warnings":0},"structuredData":{"structured_data_invalid_files":0,"breadcrumb_count":28274,"faq_count":27506 verified system-card node scripts/verify-trust-pages.js --check && node scripts/verify-discovery-surface.js
claim.system-card.kb-tm-lineage
KB / TM source lineage
{"kb":{"source_files":3238,"chunks":32724,"chunked_source_files":3238,"excluded_source_files":0,"missing_chunk_coverage":0,"orphan_chunks":0},"tm":{"total_entries":789031,"counts": verified system-card node scripts/verify-public-evidence.js --check
claim.system-card.provider-benchmark-scope
Provider benchmark scope separated from production usage
{"benchmarkProviders":["OpenAI","Anthropic","Google Gemini"],"productionModelEvidence":[]} verified system-card node scripts/verify-public-evidence.js --check

System Card V2.0: Technical Transparency Layer

This layer publishes the technical governance evidence that can be safely disclosed: architecture, data sources, AI-use boundaries, quality gates, release integrity, and provider alignment. Source code, secrets, exploitable attack details, and private data remain out of scope.

Public architecture

Cloudflare Pages/Workers, R2/D1/KV/Pagefind, and local generation scripts form the public-site and governance publication chain. Public pages disclose behavior, state, and traceable sources, not secrets or internal permissions.

AI-use disclosure

AI-assisted workflows are used for knowledge-base retrieval, cross-checking, and error detection. Governance documents are benchmarked against OpenAI, Anthropic, and Google Gemini public frameworks. Production model usage is disclosed only when code/config evidence exists.

Quality and safety gates

Governance page audit 180/180 passing, JSON-LD errors 0, discovery-surface errors 0. Status pages report critical / 5 critical, 0 warnings as-is.

Data traceability

Knowledge base 32,724 chunks, TM 789,031 entries, AI answer-ready 7,976/7,976. Public metrics trace to data/state-machine/*, data/*audit*.json, and transparency reports.

Governance areaOpenAIAnthropicGoogle GeminiStarnum implementation evidence
Model/system-card disclosureOpenAI models + safety docsClaude model docs + system/model cardsGemini model docs + safety settingssystem-card, model-card, methodology, benchmark, transparency-log
Safety evaluation and use boundariesSafety best practices / deployment checklistResponsible Scaling / safety policyGemini safety controls / policyAI safety, acceptable-use, ethics, risk-boundary copy, crawler policy audit
Data governanceData controls / privacy controlsprivacy and data handling docsGemini API data governance referencesprivacy, ai-data-governance, KB/TM source tracking, SHA-256 hashes
Monitoring and releaseproduction checklist / eval disciplinesystem-card transparency disciplinemodel/version documentation disciplinedeploy.js, status.html, SLA report, trust-pages-machine-audit, sitemap/hreflang audits

The V2.0 goal is not more claims; it separates implemented controls from planned controls. Production usage, benchmark alignment, status exceptions, GPG signing, and SLA breaches are disclosed from source data.

Release Integrity And GPG

GPG signing configured locally. signingkey=0934DFA0EDA6363A. GitHub verification pending until the public key upload and Verified badge are confirmed.

OpenAI / Anthropic / Google Gemini Alignment

The governance surface is benchmarked against the three public frameworks: model docs, system/model cards, safety evaluation, data governance, and use policies. This is benchmark alignment, not a claim that every provider is active in production inference. Official docs checked: 2026-07-30

ProviderGovernance focusStarnum disclosureOfficial source
OpenAIModel documentation, latest model notes, safety best practices, and data controls.No verifiable production model setting was found in the production code scan; providers are listed as governance benchmarks.https://platform.openai.com/docs/models
AnthropicClaude model documentation, system/model cards, Responsible Scaling, and safety policy.No verifiable production model setting was found in the production code scan; providers are listed as governance benchmarks.https://docs.anthropic.com/en/docs/about-claude/models
Google GeminiGemini API model documentation, safety settings, data governance, and platform policy.No verifiable production model setting was found in the production code scan; providers are listed as governance benchmarks.https://ai.google.dev/gemini-api/docs/models