Ficha del Sistema
System Card v2.0Version 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.
Versión 1.0 · · Referenciada al marco Anthropic System Card
Esta Ficha del Sistema amplía la Ficha del Modelo y describe las capacidades globales, la infraestructura de la base de conocimiento, los pipelines asistidos por IA, los mecanismos de aseguramiento de calidad y las limitaciones conocidas de starnum.com.tw.
1. Vista General del Sistema
| Nombre de Plataforma | Starnum Platform |
| Versión | v5.0 (2026-04-12) |
| Funciones Principales | Análisis de cartas Zi Wei Dou Shu, cálculo de Numerología (Life Path), artículos de la base de conocimiento astrológica |
| Público Objetivo | Entusiastas de la metafísica oriental tradicional; usuarios en chino tradicional y multilingües |
| Sistema de Conocimiento | Zi Wei: escuela Lu Binzhao (Zhongzhou) San-He + Si-Hua; Numerología: sistema pitagórico |
| Motor de Cartas | iztro v3.x (código abierto, verificable en GitHub) |
| Modelo de IA | Claude Sonnet 4.5 (Anthropic) — generación asistida, revisión humana |
| Idiomas Soportados | 10 語言 (zh-TW / zh-CN / en / ja / ko / es / vi / th / ms / id) |
| Infraestructura | Cloudflare Pages + Workers + Supabase (PostgreSQL) |
2. Infraestructura de la Base de Conocimiento
2.1 Escala
| KB Zi Wei Dou Shu | 225+ archivos, 88 índices, estructura de 8 volúmenes (01-fundamentos ~ 09-avanzado) |
| KB Numerología | 141 archivos ~56 544 líneas |
| KB Total | 2,758 檔 ~1,537,711+ líneas de texto estructurado |
| Índice Vectorial | Base de datos vectorial semántica a gran escala (Qdrant) |
| Grafo de Conocimiento | Grafo de conocimiento (Neo4j, estrellas × palacios × Si-Hua) |
2.2 Clasificación por Calidad
- Grado A: fuentes primarias (escuela Lu Binzhao / Pitagórica) — citables directamente
- Grado B: motor abierto iztro / datos públicos web multiorigen (destilados) — citables con verificación cruzada recomendada
- Grado C: foros / blogs — solo citables con verificación cruzada Grado A/B
2.3 Mecanismo de Integridad de Escuelas
Los puntos de vista Si-Hua que no pertenecen a la escuela Lu Binzhao se etiquetan como ⚠️ No Lu Binzhao. La KB mantiene una lista de bloqueo que impide reindexar fuentes detectadas con prompt injection.
3. Pipelines Asistidos por IA
3.1 Pipeline de Análisis de Cartas en Lenguaje Claro
3.2 Pipeline de Producción de Artículos
4. Mecanismos de Aseguramiento de Calidad
4.1 Modelo de Calidad de Bucle Cerrado de Seis Capas
- L1 Capa de Salida: 232 validaciones por artículo; los fallos bloquean la publicación.
- L2 Capa de Errores: registro de fallos → ≥3 recurrencias proponen automáticamente una nueva regla.
- L3 Capa de Rendimiento: retroalimentación de tráfico GA4 + Cloudflare para detectar artículos a refrescar.
- L4 Capa de Meta-Reglas: rule-audit.js audita el propio sistema de reglas y retira las no activadas en 90 días.
- L5 Capa de Entorno: cabeceras de seguridad, vulnerabilidades de dependencias y caducidad de credenciales monitorizadas automáticamente.
- L6 Capa Estratégica: revisión estratégica trimestral frente al panorama competitivo.
4.2 Métricas Clave de Calidad
| Reglas Estrictas Astrológicas | 117 條 (四化 41 + 格局 49 + 核心指標 17 + 元規則 10) |
| Módulos Editoriales | 19 paquetes de habilidades (prompts/skills/) |
| Diccionario Terminológico | 221 términos × 9 idiomas (glossary.json) |
| Biblioteca de Casos | 435 casos astrológicos (anonimizados + verificados) |
| Validación Automática | Checklist de 232 ítems (sop-checklist.md) |
5. Limitaciones y Fronteras Conocidas
5.1 Limitaciones de Conocimiento
- Solo se adopta la escuela Lu Binzhao; otras escuelas (Wang Tingzhi, Zheng Muting, etc.) no están completamente cubiertas.
- La numerología solo calcula números derivables de la fecha de nacimiento; no se admiten sistemas de numerología basados en el nombre.
- Las previsiones anuales expiran con el tiempo; la KB no almacena predicciones que contengan años específicos.
- El análisis de sinastría (compatibilidad relacional) es una función planificada, aún no lanzada.
5.2 Riesgos Conocidos de la Asistencia de IA
- Riesgo de Alucinación: mitigado por 117 條 reglas estrictas + etiquetas de citación de la KB, pero no eliminado por completo.
- Sesgo de Escuela: los datos de entrenamiento se inclinan hacia la escuela Lu Binzhao; otras escuelas se etiquetan sistemáticamente pero no se cubren en profundidad.
- Calidad Lingüística: las traducciones a 10 語言 usan IA revisada por no nativos; la calidad varía.
- Actualidad: el corte de conocimiento del modelo puede quedar por detrás de la investigación más reciente; las actualizaciones manuales de la KB lo compensan.
6. Gobernanza y Actualizaciones
| Supervisor Humano | mychenan (propietario del sitio, investigador astrológico) |
| Colaboradores de IA | Claude Sonnet 4.5 × 20 (Anthropic) |
| Auditoría Conjunta | Por lote: votación de Anthropic + OpenAI + Google Gemini governance benchmarks |
| Ciclo de Actualización | La Ficha del Sistema se actualiza trimestralmente; los cambios mayores de capacidad disparan actualización inmediata. |
| Documentos Públicos | Metodología / Ficha del Modelo / Benchmark / Declaración Ética |
| Documentos de Gobernanza | 治理文件 / 發展路線 |
Contacto: Instagram @mychenan
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: 3,231 source files, 0 missing coverage, 0 orphan chunks.
- data/discovery-surface-audit.json: 0 errors, 0 warnings.
- data/sla-report.json: critical / 2 critical, 0 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 |
27,634 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 / 2 critical, 0 warnings | verified | sitewide | node scripts/generate-status-page.js |
| claim.provider-alignment.openai-anthropic-gemini OpenAI / Anthropic / Google Gemini benchmark alignment |
production evidence: claude-sonnet-4-5-20250514 | verified | sitewide | node scripts/verify-public-evidence.js --check |
| claim.transparency-report.sha256 Transparency report SHA-256 anchor |
{"report":"transparency/report-2026-Q2.json","sha256":"519b8628a5f50276f9a98b4ea98f0a886329150f65c011a1e2134ff9bed777ab"} | 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.system-card.production-model-evidence Production model setting source scan |
{"productionModelEvidence":["claude-sonnet-4-5-20250514"]} | 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":3229,"chunks":32681,"chunked_source_files":3229,"excluded_source_files":0,"missing_chunk_coverage":0,"orphan_chunks":0},"tm":{"total_entries":529820,"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":["claude-sonnet-4-5-20250514"]} | 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/Pagefind, Supabase, 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 / 2 critical, 0 warnings as-is.
Data traceability
Knowledge base 32,690 chunks, TM 529,820 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: 2026-05-26; 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: 2026-05-26
| 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 |