SystemSYS-2026-0203v0.1
RBPM v0.8.5 runner — rounds F2–F4 with a corrected secondary rule
Three rounds in one sealed process with in-memory de-duplication; the F1 rule kept as primary for pooling, and every high-concern class confirmed separately with a seven-line local necessity window as the secondary rule.
Repositories and sites
repository- https://github.com/EveMissLab/apbsc-rbpm
Recorded fields
license- MIT
Relations
| Source | Relation | Target | Status | ID |
|---|---|---|---|---|
SYS-2026-0203 RBPM v0.8.5 runner — rounds F2–F4 with a corrected secondary rule | implements | THY-2026-0207 Researcher-blind privacy measurement | ACTIVE | REL-2026-0562 |
SYS-2026-0203 RBPM v0.8.5 runner — rounds F2–F4 with a corrected secondary rule | extends | SYS-2026-0202 RBPM v0.8.4 fresh runner — surface-balanced sampling (F1) | ACTIVE | REL-2026-0565 |
SYS-2026-0203 RBPM v0.8.5 runner — rounds F2–F4 with a corrected secondary rule | packaged_as | ART-2026-0208 RBPM v0.8.5 protocol (frozen before its rounds fetched anything) artifact://evemisslab/agent-publication-boundary/instruments/rbpm-v0.8.5-fresh/PROTOCOL.md | ACTIVE | REL-2026-0568 |
SYS-2026-0204 RBPM v0.9 runner — individuals with AI-collaboration markers (P1–P2) | extends | SYS-2026-0203 RBPM v0.8.5 runner — rounds F2–F4 with a corrected secondary rule | ACTIVE | REL-2026-0566 |
EXP-2026-0202 Rounds F1–F4 — fresh surface-balanced samples (236 repositories, 2026-10-13) | runs_on | SYS-2026-0203 RBPM v0.8.5 runner — rounds F2–F4 with a corrected secondary rule | ACTIVE | REL-2026-0578 |
History and provenance
- Canonical URL
- https://evemisslab.com/ai/systems/SYS-2026-0203/
- Machine-readable
/ai/systems/SYS-2026-0203/index.json- Snapshot
AI-SNAPSHOT-v0.1-58e716495670- Provenance
source- EveMissLab research collection: AI Agent Publication Boundary and Security Closure (真本體論14)
extracted_by- Splice (Claude Code), reading the open-source release's own manifests, locks and pooled outputs, and the hashes of the internal drafts
extracted_at- 2026-10-13
generator- tools/extract_all.py
claim_boundary- status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports