Starnum Logic Engine
System Model Card
This document transparently describes the design principles, knowledge sources, applicable scope, and known limitations of the starnum.com.tw astrology analysis system. Last updated:
System Overview
| Item | Description |
|---|---|
| System Name | Starnum Logic Engine v5.0 |
| Purpose | Zi Wei Dou Shu and Numerology content generation and analysis assistance |
| Core School | Lu Binzhao (Zhongzhou) Zi Wei Dou Shu + Pythagorean Numerology |
| Chart Engine | iztro (open-source JavaScript, most actively maintained version on GitHub) |
| Knowledge Base | 366 files, 193,000+ lines of structured astrology text |
| Languages Supported | 10 languages (zh-TW, zh-CN, en, ja, ko, ms, th, id, vi, es) |
| Analysis Standards | 22 standard analysis blocks, 127 hard astrology rules auto-validated |
| Review Mechanism | Machine-readable quality gates, bounded AI verification, and human operator release authority |
| Document Version | v5.0, released 2026-04-12 |
Applicable Scope
This system is designed for
- Plain-language interpretation of Zi Wei Dou Shu charts (analysis of all 12 palaces including Life, Wealth, Spouse, Children, etc.)
- Numerology readings (Life Path, Birthday Number, Personal Year, Peak Number, Challenge Number, 9-grid arrow lines)
- Learning astrology and using it as a tool for self-exploration
- Generating and reviewing educational content related to Zi Wei Dou Shu and Numerology
This system is NOT designed for
- Replacing professional medical, psychological, legal, or financial advice
- Predicting specific events with certainty or precise timing
- Any form of fate judgment for minors
- Chart analysis of political figures or public figures (without their consent)
Important Disclaimer: All content generated by this system is for personal exploration and learning reference only. It does not constitute professional advice, nor is it a divination service. Life decisions ultimately remain yours to make. Astrology is a thinking tool, not a constraint on your destiny.
Knowledge Sources
The astrology knowledge base was built from cross-referencing 8 primary sources, totaling approximately 229 documents and 60,000+ lines of structured content. The Lu Binzhao (Zhongzhou) school serves as the unified standard.
- Grade A (directly citable): Lu Binzhao school texts, iztro open-source chart engine
- Grade B (citable, cross-reference recommended): Curated public astrology resources from multiple sources, 3 supplementary research databases
- Grade C (requires A/B corroboration): Forum and blog sources
Full source list and citation rules are in Research and AI Data Governance.
Known Limitations
- Cannot predict absolute events — Astrology analysis provides tendency descriptions and cycle references; it does not mean that something "will" or "will not" happen
- School differences — This system uses the Lu Binzhao school as its standard; viewpoints from other schools are annotated "⚠️ Non-Lu Binzhao school"
- No birth time limitation — Charts without birth time cannot accurately calculate the time palace; analysis depth is relatively limited
- Numerology scope limitation — Only covers numerology items calculable from birth date; does not include name numerology
- Annual forecast validity — The knowledge base only contains evergreen content; predictions for specific years are out of scope
- Cultural context — The system primarily uses Taiwan context; some interpretations may differ from conventions in other regions
Version History
Related Resources
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.
- data/state-machine/i18n-parity.json: 8,036 parent URLs, 7,976 articles.
- data/kb-machine-audit.json: 3,238 source files, 0 missing coverage, 0 orphan chunks.
- data/discovery-surface-audit.json: 0 errors, 0 warnings.
- data/sla-report.json: critical / 3 critical, 1 warnings.
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 ID | Verifiable value | Status | Owner | Source and verification |
|---|---|---|---|---|
| claim.public-url-manifest.indexable-count Public URL and canonical inventory |
39,104 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 / 4 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":"f154fc87139b42098b02567fc93582c30addafc406420b3aea8bae79b6f4ac93"} | verified | sitewide | node scripts/update-transparency-current-data.js |
| claim.release-integrity.gpg-signing GPG signing status |
GPG signing active locally; checked GitHub commit verification is valid | verified | sitewide | gpg --list-secret-keys --keyid-format=long && git log -1 --show-signature |
| claim.model-card.current-version Model card version and stale check |
{"current_version":"4.0.2","staleness_check":{"last_checked":"2026-04-16T14:25:40.228Z","is_stale":false,"stale_since":null}} | verified | model-card | node scripts/verify-public-evidence.js --check |
| claim.model-card.skill-pack-inventory Skill-pack and SOP version inventory |
keys: components | verified | model-card | node scripts/verify-public-evidence.js --check |
| claim.model-card.answer-readiness AI answer readiness audit |
{"articles":7976,"aiAnswerReady":7976,"riskBoundaryArticles":2239,"failures":0} | verified | model-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 Workers, R2/D1/KV, 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 / 3 critical, 1 warnings as-is.
Data traceability
Knowledge base 32,724 chunks, TM 512,152 entries, AI answer-ready 7,976/7,976. Public metrics trace to data/state-machine/*, data/*audit*.json, and transparency reports.
| Governance area | OpenAI | Anthropic | Google Gemini | Starnum implementation evidence |
|---|---|---|---|---|
| Model/system-card disclosure | OpenAI models + safety docs | Claude model docs + system/model cards | Gemini model docs + safety settings | system-card, model-card, methodology, benchmark, transparency-log |
| Safety evaluation and use boundaries | Safety best practices / deployment checklist | Responsible Scaling / safety policy | Gemini safety controls / policy | AI safety, acceptable-use, ethics, risk-boundary copy, crawler policy audit |
| Data governance | Data controls / privacy controls | privacy and data handling docs | Gemini API data governance references | privacy, ai-data-governance, KB/TM source tracking, SHA-256 hashes |
| Monitoring and release | production checklist / eval discipline | system-card transparency discipline | model/version documentation discipline | deploy.js, status.html, SLA report, trust-pages-machine-audit, sitemap/hreflang audits |
- Sources: data/state-machine/model-card.json, public-bench.json, trust-pages.json, security-headers.json.
- Sources: data/trust-pages-machine-audit.json, data/discovery-surface-audit.json, data/ai-answer-readiness-audit.json.
- Sources: data/kb-machine-audit.json, data/tm/quality-audit-report.json, data/sla-report.json.
- Official benchmark docs checked: 2026-08-20; links are listed in the OpenAI / Anthropic / Google Gemini alignment table.
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 active. signingkey=0934DFA0EDA6363A. Checked GitHub commit verification is valid.
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: 2026-08-20
| Provider | Governance focus | Starnum disclosure | Official source |
|---|---|---|---|
| OpenAI | Model 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 |
| Anthropic | Claude 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 Gemini | Gemini 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 |