feat: réduction FP + gazetteers adresses FINESS + batch parallèle + corrections multi-axes

- Token min length relevé de 2-3 → 4 chars (élimine FP EPO, IRC, SIB...)
- Stop-words enrichis : acronymes médicaux 3 lettres, termes pharma, soins infirmiers
- BDPM stop-words : ~7300 noms commerciaux + DCI/substances actives
- Gazetteers adresses FINESS : 63K patterns Aho-Corasick (position-preserving normalization)
- Filtre contextuel anatomique pour FINESS établissements
- Nouvelles regex : RE_CIVILITE_COMMA_LIST, RE_EXTRACT_NOM_UTILISE, RE_EXTRACT_PRENOM,
  RE_NUM_EXAMEN_PATIENT, RE_ADRESSE_LIEU_DIT, RE_CIVILITE_INITIALE, Dr X.NOM
- URLs complètes (RE_URL) + détection multiline
- N° venue inversé (layout-aware) + EPISODE/NDA dans _CRITICAL_PII_TYPES
- HospitalFilter désactivé pour ADRESSE/TEL/VILLE/EPISODE (identifient le patient)
- Batch silver export parallélisé (multiprocessing spawn, N workers)
- Seuil sur-masquage relevé à 8%, server.py enrichi (source regex/ner)
- Blacklist villes : COURANT, PARIS ; contexte villes étendu (UHCD, spécialités)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

evaluation/baseline_scores.json

@@ -1,18 +1,18 @@
 {
-  "date": "2026-03-12T10:24:59.261417",
+  "date": "2026-03-12T17:16:25.993851",
   "scores": {
     "global_score": 97.0,
     "leak_score": 100.0,
     "fp_score": 90,
     "totals": {
       "documents": 29,
-      "audit_hits": 2797,
-      "name_tokens_known": 461,
+      "audit_hits": 3186,
+      "name_tokens_known": 457,
       "leak_audit": 0,
       "leak_occurrences": 0,
       "leak_regex": 0,
       "leak_insee_high": 0,
-      "leak_insee_medium": 569,
+      "leak_insee_medium": 570,
       "fp_medical": 0,
       "fp_overmasking": 2
     }
@@ -110,7 +110,7 @@
       "leak_audit": 0,
       "leak_regex": 0,
       "leak_insee_high": 0,
-      "leak_insee_medium": 23,
+      "leak_insee_medium": 24,
       "fp_medical": 0,
       "fp_overmasking": 0
     },
@@ -206,7 +206,7 @@
       "leak_audit": 0,
       "leak_regex": 0,
       "leak_insee_high": 0,
-      "leak_insee_medium": 32,
+      "leak_insee_medium": 33,
       "fp_medical": 0,
       "fp_overmasking": 0
     },
@@ -222,7 +222,7 @@
       "leak_audit": 0,
       "leak_regex": 0,
       "leak_insee_high": 0,
-      "leak_insee_medium": 34,
+      "leak_insee_medium": 32,
       "fp_medical": 0,
       "fp_overmasking": 0
     },
@@ -246,7 +246,7 @@
       "leak_audit": 0,
       "leak_regex": 0,
       "leak_insee_high": 0,
-      "leak_insee_medium": 26,
+      "leak_insee_medium": 27,
       "fp_medical": 0,
       "fp_overmasking": 0
     }