starnum.com.tw Content Production Methodology
Last updated: (v5.0) | Next scheduled update: | Maintained by: mychenan
TL;DR: Starnum uses AI-assisted content workflows grounded in the Lu Binzhao School knowledge base and the iztro open-source chart engine. Drafts pass a six-dimensional automated quality framework, editorial-standard modules, astrology-logic checks, and SHA-256 integrity verification before release. A human operator retains release authority; automated checks support judgment rather than replace it.
Knowledge Sources
Lu Binzhao School (陸斌兆派) literature forms the core. The knowledge base totals 366 files with approximately 193,000 lines of structured text, covering both Zi Wei Dou Shu and numerology systems, sourced from 8 major astrology research databases with cross-reference validation.
Lu Binzhao School vs. Wang Tingzhi School — Four Transformations differences:
| Heavenly Stem | Lu Binzhao School | Wang Tingzhi School |
|---|---|---|
| Wu (戊) | You Bi (右弼) — Science | Tian Ji (天機) — Science |
| Geng (庚) | Tai Yin (太陰) — Science | Tian Tong (天同) — Science |
| Ren (壬) | Zuo Fu (左輔) — Prosperity | Tian Liang (天梁) — Prosperity |
Numerology follows the Pythagorean system, covering Life Path Number, Birthday Number, Personal Year, Peak Numbers, Challenge Numbers, and the Arrow Grid.
Chart Engine
We use the iztro open-source Zi Wei Dou Shu chart engine (JavaScript), supporting 14 major star placements, auxiliary and malefic star positioning, Four Transformations calculation, and Major/Annual cycle analysis. Open-source code means the calculation logic can be verified by any researcher.
Quality Verification System
Six-Dimensional Automated Quality Framework
Automated checks across six dimensions help identify issues before publication:
- D1 Safety — Forbidden word scanning, copyright compliance, sponsored labeling
- D2 Completeness — 11 hreflang tags, og/twitter/Schema completeness
- D3 Executability — Link reachability, JSON-LD syntax, CSS class definitions
- D4 Maintainability — Template consistency, naming conventions, body class
- D5 Cost-awareness — Word count specs, content substance, semantic deduplication
D1–D3 are executed by automated tools (zero tolerance); D4–D5 are reviewed by senior editors (passing score: 80+).
Astrology Logic Multi-Model Cross-Validation
Astrology logic verification uses a multi-model cross-referencing mechanism across three dimensions: vector semantic search, knowledge graph expansion, and a hard rules engine (over 100 rules). A reasoning skeleton is generated and verified across all dimensions before article writing begins. Multi-model agreement is required — a single tool's judgment alone is never the final word — effectively preventing stars placed in wrong palaces or incorrect pattern judgments.
SHA256 Content Integrity + JSON-LD hasHash
Each article's body text is hashed with SHA256, then injected both at the bottom of the page (human-readable) and into the Article JSON-LD Schema's hasHash property (machine-readable). Search engines and AI crawlers can verify content originality directly from the Schema — no HTML parsing required.
Git Version Control
All changes are tracked via commit in a private GitHub repository — fully traceable and reversible.
Entity Knowledge Graph
80 core astrology entities (14 major stars, 12 palaces, 4 transformations, patterns, numerology concepts, etc.), each with Wikidata sameAs, description, and Five Elements attributes. Article Schema automatically injects mentions and about. All published articles site-wide have publishingPrinciples pointing to this page.
Semantic Internal Linking System
TF-IDF algorithm + co-occurrence weighted analysis of the full article library's semantic similarity automatically builds top-3 bidirectional internal links. Articles within the same Topic Hub get ×1.5 weighting; pillar–cluster links get ×2.0, making the Cluster structure clearly visible to search engines. A cannibalization detection system regularly scans title and description similarity — pairs exceeding 70% are flagged and fixed.
Quality Feedback and Continuous Improvement
Every article that fails a quality check is logged into a structured quality feedback journal, capturing failure type, root cause analysis, and quality scores before and after correction.
- Pattern detection: When the same issue type accumulates ≥3 times, a new quality rule is automatically proposed
- Rule retirement: Rules that haven't triggered in 90 days are candidates for simplification or removal — preventing rule bloat
- Quantified feedback: Score changes from each correction are logged to verify which improvements actually work
This feedback-driven improvement system ensures that quality standards are continuously refined based on empirical evidence rather than manual observation alone.
Editorial Standard Modules (19 Sets)
Editorial standard modules break content and review work into triggerable, composable processes:
- Content quality closed loop (three-stage review: draft, editorial check, final sign-off)
- Hook writing standards (title / sponsored / recommendation card — all three covered)
- SEO six-dimensional evaluation (including GEO citability)
- Quality feedback and rule iteration
- Cross-period knowledge accumulation and transfer
- Quality gate, article audit updates, standards review, standards iteration
Articles may be drafted or revised with AI assistance, then checked against the applicable editorial standards and machine-readable quality gates. Modules have dependency and composition relationships, so each workflow loads only the rules relevant to its task. A human operator retains publication and policy authority.
Technical Specifications
| Component | Specification |
|---|---|
| Chart Engine | iztro (open-source JavaScript) |
| Four Transformations School | Lu Binzhao School (陸斌兆派) |
| Knowledge Base | 193,000+ lines / 366 files (Zi Wei Dou Shu 223 + Numerology 143, 8 sources cross-referenced) |
| Article Volume | zh-TW 1,772 articles (2026 Annual complete + 2025 Annual complete) |
| Quality Checks | 232-item six-dimensional automated checks (Safety/Completeness/Executability/Maintainability/Cost/GEO) |
| Improvement System | Quality feedback–driven rule iteration + 19 editorial standard modules |
| Case Library | 435 Taiwan-localized cases (dual-classification retrieval, including analysis backflow) |
| Terminology Dictionary | 221 terms × 9 languages unified translation reference |
| Work Structure | AI-assisted execution with human operator release authority |
| Quality Management | Quality gate + article audit + standards review + standards iteration — four-layer QA loop |
| Knowledge Management | 7-layer knowledge transfer architecture |
| Entity Graph | 80 entities + Wikidata sameAs + JSON-LD + publishingPrinciples site-wide |
| Internal Linking | TF-IDF + co-occurrence weighted (same hub ×1.5 / pillar ×2.0) |
| Integrity Verification | SHA256 content hash + JSON-LD hasHash (machine-readable) |
| Cannibalization Detection | Title/description/H1 Jaccard > 70% auto-flagged |
| Page Pre-rendering | Speculation Rules API (prerender + prefetch) |
| Frontend Animation | GSAP (Chart page 6 sets + About page 4 sets) |
| Performance Optimization | Blog 39KB / Chart CSS lazy-load 66KB / i18n lazy-load / JS defer + Critical CSS inline + 103 Early Hints + Cache-Control immutable |
| Date Management | Centralized date management tool for datePublished / dateModified |
| Automation Pipeline | multiple automated quality tools (push-triggered + scheduled) |
| Canonical Standard | Trailing slash uniformly removed (Google indexing bottleneck resolved) |
| Knowledge Graph | Neo4j knowledge nodes + Qdrant 15,000+ semantic chunks (writing team reference retrieval) |
| Astrology Logic Validation | over 100 hard rules, multi-model cross-confirmed |
| Experience Accumulation | Chart reading → case auto-backflow (compound knowledge growth for writing team) |
| Quality Review | 52 check presets × multi-tool cross-validation voting system |
| Automation Scripts | multiple automated quality tools |
| Logic Engine | Starnum Logic Engine v5.0 |
| Version Control | Git + GitHub full access |
Knowledge Graph Reference System
A Neo4j knowledge graph and vector-search layer provide a three-layer evidence retrieval architecture. Analysis workflows can look up reference material through semantic search, graph expansion, and the rules engine, keeping evidence paths traceable.
Chart Analysis Quality Assurance
Chart-reading workflows use tier-specific section contracts and draw on the knowledge base and case library. Automated verification checks required sections and the logical consistency of palaces, transformations, and patterns before delivery; human operator authority remains outside the automated writer.
Sanitized Taiwan-localized cases support evidence retrieval and quality comparison. They are supporting references, not substitutes for chart facts or release gates.
Multi-Tool Quality Review
52 preset quality check items are scanned simultaneously by multiple independent review tools, detecting technical errors and formatting issues. Each issue goes through cross-validated voting (FIX/SKIP/DEFER) — a majority vote is required before any fix is made, ensuring only genuine problems are addressed. Multiple rounds of quality scans have resolved more than 200 technical issues, with system quality converging toward zero defects.
Version History
- v5.0 — Quality assurance system fully upgraded: multi-model cross-validation for astrology logic (127 hard rules), knowledge base expanded to 366 files / 193K lines (8 sources cross-referenced), case library grown to 435 entries (all Taiwan-localized), zh-TW articles reach 1,772 (2026 + 2025 complete), semantic vector library 15,000+ chunks, chart analysis 22-section standard + multi-model validation loop
- v4.3 — zh-TW articles reach 1,585 (2025 Annual 305 complete), knowledge graph reference system launched, experience accumulation system launched (chart reading → case auto-backflow), multi-tool quality review round 10 complete (200+ technical issues resolved), editorial standards upgraded to 19 sets, terminology dictionary at 221 terms, case library grown to 192, methodology multilingual versions launched
- v4.2 — zh-TW articles reach 1,195, entity graph expanded to 80, terminology dictionary upgraded to v3.0 (217 terms × 9 languages), case library system launched (140+ anonymized cases), publishingPrinciples added site-wide to 1,726 articles, 9 cannibalization issues resolved, quality checks upgraded to six dimensions (GEO dimension added), English/Japanese AI stopword lists built, automation pipeline continuously optimized
- v4.1 — zh-TW articles reach 1,112, 2026 Annual 299 articles complete, knowledge base expanded to 267 files / 144K lines, editorial standards expanded to 18 sets, divided review mechanism, GSAP animation (Chart 6 + About 4), performance optimization, canonical trailing slash fixed, date management system
- v4.0 — full automation pipeline continuously optimized, co-occurrence internal link weighting, JSON-LD hasHash, Speculation Rules pre-rendering, 103 Early Hints, cannibalization detection, Cloudflare post-deploy auto cache purge, GSC/Bing index tracking, sitemap trailing slash fixed (Google indexing bottleneck resolved)
- v3.0 — Quality feedback–driven improvement system, modular editorial standards, five-dimensional evaluation framework, 7-layer knowledge transfer architecture, auto quality wrap-up at end of session
- v2.0 — Entity knowledge graph launched (60 entities + Wikidata sameAs + Five Elements), automatic internal linking, incremental updates, Content Hash
- v1.5 — Topic Hub page architecture restructured (54 hubs), shared CSS component library built (85+ classes)
- v1.0 — Initial launch: 232-item checklist, astrology logic verification tool
Recent Verification Log
[2026-04-12] zh-TW articles: 1,772 (2026 Annual complete + 2025 Annual complete)[2026-04-12] Knowledge base: 366 files, 193K lines (Zi Wei Dou Shu 223 + Numerology 143, 8 sources cross-referenced)
[2026-04-12] Semantic vector library: 15,000+ chunks
[2026-04-12] Astrology logic hard rules: 127 (Four Transformations 41 + Patterns 49 + Core 17 + Meta-rules 20)
[2026-04-12] Quality review: multiple rounds complete (200+ technical issues resolved, converging to zero defects)
[2026-04-12] Case library: 435 entries (all Taiwan-localized, including analysis backflow)
[2026-04-12] Terminology dictionary: v3.0 (221 terms × 9-language translation reference)
[2026-04-12] Editorial standards: 19 sets
[2026-04-12] Entity graph: 80 entities (14 major stars + 12 palaces + 4 transformations + patterns + numerology)
[2026-04-12] publishingPrinciples: complete site-wide
[2026-04-12] Content signing: site-wide SHA256 + JSON-LD hasHash
Last verified:
Core Principles
- Transparency: open-source engine + traceable knowledge base + content hash verification
- School consistency: Lu Binzhao School used exclusively site-wide — no mixing of schools
- Quality first: 232 checks must pass before publication — we'd rather publish less than publish poorly
- Continuous evolution: quality feedback mechanism automatically proposes new rules; rules untriggered for 90 days are candidates for retirement
- Modular standards: editorial team capabilities broken into composable standardized modules — referenced as needed, improving efficiency
- Multi-model confirmation: astrology logic judgments are cross-validated by multiple tools — no single source is the final word
Each article includes a unique SHA256 cryptographic hash calculated from the raw content. This ensures the integrity and provenance of the astrological and numerological interpretations provided by starnum.com.tw. Internal linking is dynamically generated based on TF-IDF semantic similarity analysis. All content is reviewed by Starnum Logic Engine v5.0 before publication.
Quality Improvement Record
We continuously track and fix all quality issues. Every problem discovered is turned into an automated rule — so it never happens again. Here are some selected examples:
Case 1: Site-wide canonical URL Fix
Problem: 1,089 articles across the site had canonical URLs with trailing slashes, causing search engines to treat them as duplicate pages.
Discovery: Identified during an external technical review.
Fix: Trailing slashes removed site-wide, automated checks added, rule written into editorial standards so it never recurs.
Case 2: Template Residue Prevention
Problem: Incomplete replacement of template content during article writing caused incorrect star information to go live.
Discovery: Caught by the editor-in-chief during file diff review.
Fix: Logged to quality feedback system; editorial standards updated with rule "titles and star content must match after writing"; automated tools now scan for template residue.
Case 3: Multi-Model Astrology Logic Validation Introduced
Problem: Single-tool validation had blind spots — rare patterns or complex Four-Transformation combinations could slip through undetected.
Discovery: Contradictions between earlier and later analyses surfaced during case backflow comparison.
Fix: Multi-model cross-validation introduced. Over 100 hard rules are now checked by multiple tools simultaneously — any tool flagging an anomaly triggers a review hold, significantly reducing edge-case misjudgment rates.
Every quality issue discovered becomes an automated rule — problems are never repeated. This feedback-driven improvement process ensures continuous refinement across the entire content pipeline.
Transparency Resources
We are committed to full transparency in our content production process. The following resources are publicly available:
- System Model Card — Starnum Logic Engine v5.0: knowledge sources, limitations, review process
- Platform System Card — Full system capabilities, KB infrastructure, AI pipeline, limitations (aligned with Anthropic System Card)
- Ethics Statement — Responsible AI commitments, human oversight, bias protection
- Acceptable Use Policy — Prohibited uses: crime prediction, discrimination, replacing professional consultation
- FAQ — Complete answers on Zi Wei Dou Shu, numerology, accuracy, privacy
- Research Blog — School comparisons, methodology analysis, AI-assisted astrology research
- Quality Benchmark — Public evaluation results for 37 fixed chart test cases
- Service Status — Live system health and uptime history
- Governance — 3-tier decision process, AI audit quorum rules, transparency commitments
- Public Roadmap — Q2–Q4 2026 development plans