feat(ai-sdk): control-intent result diversity + standard-name classifier override
CI / detect-changes (push) Successful in 7s
CI / branch-name (push) Has been skipped
CI / guardrail-integrity (push) Has been skipped
CI / secret-scan (push) Has been skipped
CI / dep-audit (push) Has been skipped
CI / sbom-scan (push) Has been skipped
CI / build-sha-integrity (push) Successful in 5s
CI / validate-canonical-controls (push) Successful in 8s
CI / loc-budget (push) Successful in 19s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / nodejs-build (push) Has been skipped
CI / test-go (push) Successful in 58s
CI / iace-gt-coverage (push) Successful in 17s
CI / test-python-backend (push) Has been skipped
CI / test-python-document-crawler (push) Has been skipped
CI / test-python-dsms-gateway (push) Has been skipped

On an implementation question impl_guidance (ENISA) keeps its earned semantic
Top-1, but the top-K now surfaces the best operational_requirement and
control_standard from the pool (ensureControlDiversity) — so different source
roles are visible instead of one role flooding the list, without forcing the
binding sources to Top-1.

A recognised standard NAME (NIST/OWASP/ISO 27001/CIS/CSA CCM/Grundschutz) now
overrides a mis-applied supervisory_guidance source_class in classifyAuthority,
so those standards classify and rank as technical_standard (control_standard
role). The corpus tags many standards as guidance (weight 70); the name wins.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-06-25 01:54:36 +02:00
parent d9d04deb00
commit 31222885b3
5 changed files with 124 additions and 1 deletions
+8 -1
View File
@@ -40,6 +40,14 @@ func classifyAuthority(r LegalSearchResult) authorityInfo {
if jur == "" {
jur = inferJurisdiction(r)
}
hay := r.ArticleLabel + " " + r.RegulationShort + " " + r.RegulationName + " " + r.RegulationCode
// A recognised standard NAME (NIST/OWASP/ISO 27001/CIS/CSA CCM/Grundschutz) is authoritative
// even when the corpus mis-tagged the chunk as supervisory_guidance (weight 70) — many
// standards were ingested with a generic guidance source_class. The name wins, so they
// classify (and rank) as technical_standard / control_standard. binding_law is preserved.
if r.SourceClass != "binding_law" && containsAny(hay, standardMarkers) {
return authorityInfo{weight: 80, sourceClass: "technical_standard", jurisdiction: jur}
}
if r.SourceClass != "" {
w := r.AuthorityWeight
if w == 0 && r.SourceClass == "binding_law" {
@@ -50,7 +58,6 @@ func classifyAuthority(r LegalSearchResult) authorityInfo {
if r.AuthorityWeight > 0 {
return authorityInfo{weight: r.AuthorityWeight, sourceClass: sourceClassFromWeight(r.AuthorityWeight), jurisdiction: jur}
}
hay := r.ArticleLabel + " " + r.RegulationShort + " " + r.RegulationName + " " + r.RegulationCode
switch {
case containsAny(hay, foreignMarkers):
return authorityInfo{weight: 0, sourceClass: "foreign_law", jurisdiction: "CH"}