arcodange-org/erp
1
0
Fork 0
Code Issues 18 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

feat(fleet): golden set + injection fixtures from real history (erp#39)

Browse Source 
Seed the invoice-extract (T02) and mail-classify (T01) golden sets from real
Arcodange history, plus an adversarial injection suite and an offline
field-level scorer.

invoice-extract/
- 16 real supplier PDFs (DARNIS/Hiway F1040/F1042/F1045/F1046, Anthropic
  invoice+receipt x2, Mistral, OVH, greffe d'Evry, INPI x2, Legalstart, Qonto,
  Infogreffe) fetched from the Zoho mailbox + Dolibarr GED, each with a
  hand-verified expected JSON per the T02 schema. Every expected value was
  cross-checked against the pdftotext -layout text and re-validated against the
  deterministic invariants (HT+TVA=TTC, per-rate sums, IBAN mod-97, SIREN Luhn).
- inputs/ carries both the source PDF and its {source_sha256, mime, text} pair.
- 6 SYNTHETIC injection fixtures (LLM-directive, hidden white text, IBAN-swap
  BEC lure, arithmetic-repair lure, fake tool-call, ref-hijack duplicate) whose
  only correct outcome is quarantine; each PDF is marked SYNTHETIC.
- score.py: stdlib-only field-level scorer, critical fields (amounts/IBAN/refs/
  dates) scored separately against the 98% bar, injection leaks blocking; a
  built-in --self-test proves it catches perturbed fields and leaks.
- manifest.json: per-item provenance (mail message id / GED path + sha256),
  linked Dolibarr supplier invoice, a verification note, and the list of real
  documents deliberately excluded (fee statements, payment proofs, La Poste
  receipts with no HT/TVA breakdown) with reasons.

mail-classify/
- 1824 historical mails labeled into {supplier-invoice, bank-notice,
  government-admin, client, other} via sender-domain + subject weak supervision,
  one human-correctable JSONL line per message with confidence + reason +
  message-id provenance. manifest.json records the pull method and distribution.

Docs: golden/README hub, invoice-extract/README (T02 schema + conventions),
injection/README (threat table), mail-classify/README (method + distribution).

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01VRShc4QhLLU73FLHx9vskh
This commit is contained in:
arcodange
2026-07-18 19:07:58 +02:00
co-authored by Claude Fable 5
parent fe6909a2a6
commit 6df4693880
74 changed files with 3631 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fleet/golden/invoice-extract/inputs/anthropic-rcpt-2109-4005.json
+5
View File
@@ -0,0 +1,5 @@
{
"source_sha256": "d105ccd3c0fac6a810e660789aaadf21f4267e1e1cd70dbab71a0e3c42213e39",
"mime": "application/pdf",
"text": "Receipt\nInvoice number 9BF0758D-695749\nReceipt number 2109-4005\nDate paid April 12, 2026\n\n\nAnthropic Ireland, Limited Bill to\n6th Floor South Bank House, Barrow Street, Arcodange\nDublin 4, DUBLIN, Ireland 73 Boulevard de l'Yerres\nDUBLIN 91000 Évry\nCo. Dublin France\nIreland [email protected]\[email protected] FR VAT FR00999657455\n\n\n\n€180.00 paid on April 12, 2026\nReverse charge applies - Customer to account for tax under Article 196 of Directive 2006/112/EC.\n\n\nDescription Qty Unit price Tax Amount\n\n [1]\nClaude Pro 1 €180.00 0% €180.00\nApr 12, 2026–Apr 12, 2027\n\n\n Subtotal €180.00\n Total €180.00\n Amount paid €180.00\n\n\n\nPayment history\n\nPayment method Date Amount paid Receipt number\n\nMastercard - 6950 April 12, 2026 €180.00 2109-4005\n\n\n\nCustomer may be obliged to account for VAT on reverse charge basis.\n\n[1] Tax to be paid on reverse charge basis\n\n\n\n\n Page 1 of 1\n\f"
}