Institutional small language model
Maintained by PointSav Digital Systems. Each revision is content-addressed by its commit hash.
- fix(frontmatter): correct references: YAML indentation across 72 documentation articles
- fix(editorial): strip leaked claim-comment markers (22 files); tier-nomenclature lede rewrite (§16.C Mode 2)
- feat(documentation): add how-to cross-links to 7 parent TOPIC articles — Phase 3b wikilink gap fill (EN+ES)
- feat(media-knowledge-documentation): add content_type field to all TOPIC + GUIDE files
- enrich wikilinks: documentation services body (EN+ES) batch 2
- editorial(A2.7): rewrite service-slm (EN+ES) — Bloomberg lede, Gate-0, claim markup; retire Yo-Yo term
- editorial: Phase A2+A3 — title normalisation (169 files) + wikilink backslash fix (20 files)
- docs: resolve 42 broken wikilinks — ADR slugs → architecture-decisions; delink 13 missing/internal slugs
- docs(2g): corpus-wide Doctrine claim vocabulary removal (227 files)
- docs(services): add external references to four services articles (EN+ES)
- topic(services): service-slm — four operations, OLMo model selection, Doorman boundary, small-model rationale
- chore(services): convert bare concept references to wikilinks
- merge: integrate origin/main (taxonomy ratification + category-balance + schema-scrub commits) before project-knowledge Stage 6 promote
- docs wiki Step 5: services batch — 3 EN+ES pairs register-corrected
- wikipedia-parity: remove inline copyright, trademark, and Provenance blocks from article bodies
- content-wiki-documentation: body H1 batch remediation (106 files)
- Phase E: bcsc_class + status sweep — services/, systems/, infrastructure/, reference/, design-system/
- IP footer sweep — re-apply five-mark trademarks workspace-wide
- Diffuse Leapfrog 2030 Doctrine and Glossary formatting
- PL.7: Batch normalization — remove legacy topic- prefix from all files and links