breakpilot-compliance/ai-compliance-sdk/internal/ucca/authority_rerank.go

package ucca

import "sort"

// Re-ranking coefficients (validated in the offline golden harness; Phase A — conservative).
const (
	authorityCoef     = 0.40 // * weight/100
	jurisdictionGain  = 0.05 // binding/guidance from DE or EU
	foreignPenalty    = 0.60 // foreign law on a DE/EU question (demoted, not removed)
	unknownPenalty    = 0.08
	domainMatchGain   = 0.15
	offDomainPenalty  = 0.10 // off-domain binding (demoted, not removed)
	scopePenalty      = 0.25 // BDSG Teil 3 (law enforcement) on a general DP question
	topicGain         = 0.18 // amplifier only
	supersededPenalty = 0.50 // superseded Alt-Quelle (pre-eu-v1): demoted, nicht versteckt
)

// authorityScore computes the normative relevance of a result for a query. It augments the
// semantic score with authority/jurisdiction/domain/scope/topic signals. Exposed for tests.
func authorityScore(query string, r LegalSearchResult, qDomain string, qForeign bool) float64 {
	info := classifyAuthority(r)
	score := r.Score + authorityCoef*float64(info.weight)/100.0

	if r.Superseded {
		// Alt-Quelle (pre-eu-v1): Default-Fragen sollen die eu-v1-Norm sehen. Demoted,
		// nicht entfernt — fuer Historie/Uebergangsfragen bleibt sie auffindbar.
		score -= supersededPenalty
	}

	if info.jurisdiction == "CH" && !qForeign {
		score -= foreignPenalty // Fremdrecht bei DE/EU-Frage: demoted, nicht geloescht
	} else {
		score += jurisdictionGain
	}
	if info.sourceClass == "unknown" {
		score -= unknownPenalty
	}
	if qDomain != "" {
		switch cd := chunkDomain(r); {
		case cd == qDomain:
			score += domainMatchGain
		case cd != "":
			score -= offDomainPenalty // off-domain binding: demoted, nicht geloescht
		}
	}
	if qDomain == "data_protection" && scopeClass(r) == "law_enforcement" {
		score -= scopePenalty
	}
	if resultMatchesTopic(query, r) {
		score += topicGain // Verstaerker, kein Override
	}
	return score
}

// rerankByAuthority re-orders results so binding law from the matching jurisdiction/domain
// ranks above guidance, foreign and off-domain law — WITHOUT dropping anything (guidance is
// kept as interpretation context). The computed score is written back to Score so downstream
// merges (e.g. the multi-collection advisor) preserve this order. Pure + deterministic.
func rerankByAuthority(query string, results []LegalSearchResult) []LegalSearchResult {
	if len(results) < 2 {
		return results
	}
	qDomain := queryDomain(query)
	qForeign := queryIsForeign(query)

	out := make([]LegalSearchResult, len(results))
	copy(out, results)
	for i := range out {
		out[i].Score = authorityScore(query, out[i], qDomain, qForeign)
	}
	sort.SliceStable(out, func(a, b int) bool {
		return out[a].Score > out[b].Score
	})
	return out
}