chore(hf): bake audit-p2p + supply-chain-ocel recipes; align all data-card READMEs

configs/examples/hf/audit_p2p.yaml

@@ -0,0 +1,144 @@
+# VynFi Audit P2P (vynfi-audit-p2p) — HF dataset regeneration recipe
+#
+# Document Flow with Fraud Labels.  Showcases the P2P (purchase
+# order → goods receipt → vendor invoice → payment) and O2C
+# (sales order → delivery → customer invoice → customer receipt)
+# document chains, with line-level fraud labels and the v5.8.0+
+# `predecessor_line_id` chain context surfaced both on JE lines
+# and via the `je_network.csv` flat edge list.
+#
+# Volumes target ≈230 documents across the four core P2P document
+# types — small enough for quick prototyping, large enough to
+# show realistic fraud-injection patterns at the document level.
+# Manufacturing industry, 10 entities, 6 fiscal periods.
+#
+# Reproducibility:
+# - global.seed pinned for byte-stable regeneration on the
+#   v5.9.0 release binary;
+# - graph_export.je_network.method: a (Method A from
+#   Ivertowski 2024 — exactly one edge per 2-line journal entry,
+#   no Cartesian-product blow-up on multi-line consolidations);
+# - cost-centers / profit-centers / employees masters generated so
+#   `cost_center` / `profit_center` / `created_by` join cleanly to
+#   their respective master tables (closes the v5.9.0 linkage gap).
+
+global:
+  industry: manufacturing
+  start_date: "2024-01-01"
+  period_months: 6
+  seed: 20260509
+  group_currency: USD
+  parallel: true
+  worker_threads: 4
+  memory_limit_mb: 4096
+
+companies:
+  - { code: "1000", name: "VynFi Mfg HQ",       currency: USD, country: US, annual_transaction_volume: ten_k, volume_weight: 0.18, fiscal_year_variant: K4 }
+  - { code: "1100", name: "VynFi Mfg Plant 1",  currency: USD, country: US, annual_transaction_volume: ten_k, volume_weight: 0.14, fiscal_year_variant: K4 }
+  - { code: "1200", name: "VynFi Mfg Plant 2",  currency: USD, country: US, annual_transaction_volume: ten_k, volume_weight: 0.12, fiscal_year_variant: K4 }
+  - { code: "1300", name: "VynFi Mfg Plant 3",  currency: USD, country: US, annual_transaction_volume: ten_k, volume_weight: 0.10, fiscal_year_variant: K4 }
+  - { code: "2000", name: "VynFi Mfg EU GmbH",  currency: EUR, country: DE, annual_transaction_volume: ten_k, volume_weight: 0.10, fiscal_year_variant: K4 }
+  - { code: "2100", name: "VynFi Mfg UK Ltd",   currency: GBP, country: GB, annual_transaction_volume: ten_k, volume_weight: 0.08, fiscal_year_variant: K4 }
+  - { code: "2200", name: "VynFi Mfg FR SAS",   currency: EUR, country: FR, annual_transaction_volume: ten_k, volume_weight: 0.08, fiscal_year_variant: K4 }
+  - { code: "3000", name: "VynFi Mfg APAC SG",  currency: SGD, country: SG, annual_transaction_volume: ten_k, volume_weight: 0.08, fiscal_year_variant: K4 }
+  - { code: "3100", name: "VynFi Mfg AU Pty",   currency: AUD, country: AU, annual_transaction_volume: ten_k, volume_weight: 0.06, fiscal_year_variant: K4 }
+  - { code: "4000", name: "VynFi Mfg CA Inc",   currency: CAD, country: CA, annual_transaction_volume: ten_k, volume_weight: 0.06, fiscal_year_variant: K4 }
+
+chart_of_accounts:
+  complexity: small
+  industry_specific: true
+
+master_data:
+  vendors:    { count: 50, intercompany_percent: 0.10 }
+  customers:  { count: 60, intercompany_percent: 0.05 }
+  materials:  { count: 100, bom_enabled: true, average_bom_depth: 2 }
+  fixed_assets: { count: 30 }
+  employees:  { count: 50 }
+
+# Document flows are the headline content for this dataset.
+# Volumes tuned so each of PO / GR / Invoice / Payment lands in the
+# 50-80 range across the 6-month / 10-company horizon (≈ 1 chain
+# per company per month for both P2P and O2C).
+document_flows:
+  p2p:
+    enabled: true
+    chains_per_month: 1
+    three_way_match_rate: 0.92
+    partial_delivery_rate: 0.12
+    gr_ir_clearing_enabled: true
+  o2c:
+    enabled: true
+    chains_per_month: 1
+    credit_check_failure_rate: 0.04
+    partial_shipment_rate: 0.10
+    return_rate: 0.025
+
+balance:
+  generate_opening_balances: true
+  generate_trial_balances: true
+  reconcile_subledgers: true
+  validate_balance_equation: true
+  target_gross_margin: 0.32
+  target_dso_days: 45
+  target_dpo_days: 30
+
+period_close:
+  enabled: true
+
+financial_reporting:
+  enabled: true
+
+# 3 % document-level fraud (matches the published 3 % rate).
+fraud:
+  enabled: true
+  fraud_rate: 0.02
+  document_fraud_rate: 0.03
+  propagate_to_lines: true
+
+internal_controls:
+  enabled: true
+  coso_enabled: true
+  include_entity_level_controls: true
+  target_maturity_level: managed
+  exception_rate: 0.02
+  sod_violation_rate: 0.01
+
+distributions:
+  enabled: true
+  industry_profile: manufacturing
+  amounts:
+    enabled: true
+    distribution_type: log_normal
+    components:
+      - { weight: 0.65, mu: 5.5, sigma: 1.3, label: "routine" }
+      - { weight: 0.28, mu: 7.8, sigma: 0.9, label: "significant" }
+      - { weight: 0.07, mu: 9.5, sigma: 0.6, label: "major" }
+    benford_compliance: true
+
+temporal_patterns:
+  enabled: true
+  business_days:
+    enabled: true
+    half_day_policy: half_day
+    month_end_convention: modified_following
+  calendars:
+    regions: [US, DE, GB, SG]
+  period_end:
+    model: exponential
+    month_end:   { start_day: -10, base_multiplier: 1.0, peak_multiplier: 3.5, decay_rate: 0.3 }
+    quarter_end: { inherit_from: month_end, additional_multiplier: 1.5 }
+
+audit:
+  enabled: false  # Audit data has its own dataset
+
+# Method A flat edge-list for the accounting network.  Provides a
+# bonus artefact alongside the document-flow tables — every
+# 2-line JE in this dataset gets one edge, joinable back to the
+# row-level JE table via from_line_id / to_line_id.
+graph_export:
+  je_network:
+    method: a
+
+output:
+  output_directory: "./output"
+  formats: [csv, json]

configs/examples/hf/supply_chain_ocel.yaml

@@ -0,0 +1,159 @@
+# VynFi Supply Chain OCEL (vynfi-supply-chain-ocel) — HF dataset
+# regeneration recipe.
+#
+# Native OCEL 2.0 event log from a manufacturing supply chain.
+# Process types covered: P2P, O2C, manufacturing operations.  Event
+# log is the primary artefact, with object-level data
+# (orders / invoices / shipments / receipts) and anomaly labels
+# alongside.
+#
+# Volumes (post-v5.9.0 refresh): targeting ~100k events for
+# usability — the v0.x dataset shipped 20 010 events which was
+# quick to prototype against but tight for any serious process
+# mining.  Scaling: 5 companies × 12 months × ~120 chains for
+# each of P2P and O2C (≈14 k chains × ~7 events per chain) puts
+# the event log in the 90 k–110 k range, with proportional
+# growth in objects and anomaly labels.  Per-company JE volume
+# kept at `ten_k` to bound the in-memory orchestrator footprint
+# during OCPM event-log construction (`hundred_k` × 5 × 12
+# producing ~700 k JEs alongside ~14 k chains pushed peak heap
+# past 8 GB during native-OCEL graph assembly).
+#
+# Reproducibility:
+# - global.seed pinned;
+# - 3 % document-level fraud injection (matches the published
+#   3 % rate);
+# - ChaCha8 PRNG output is platform-stable.
+
+global:
+  industry: manufacturing
+  start_date: "2024-01-01"
+  period_months: 12
+  seed: 20260509
+  group_currency: USD
+  parallel: true
+  worker_threads: 4
+  memory_limit_mb: 8192
+
+# Five subsidiaries: one HQ, three plants, one international
+# entity.  Big enough to exercise multi-company joins on objects;
+# small enough to keep event counts focused on supply-chain
+# behaviour rather than entity proliferation.
+companies:
+  - { code: "1000", name: "VynFi Mfg HQ",       currency: USD, country: US, annual_transaction_volume: ten_k, volume_weight: 0.30, fiscal_year_variant: K4 }
+  - { code: "1100", name: "VynFi Mfg Plant 1",  currency: USD, country: US, annual_transaction_volume: ten_k, volume_weight: 0.22, fiscal_year_variant: K4 }
+  - { code: "1200", name: "VynFi Mfg Plant 2",  currency: USD, country: US, annual_transaction_volume: ten_k, volume_weight: 0.18, fiscal_year_variant: K4 }
+  - { code: "2000", name: "VynFi Mfg EU GmbH",  currency: EUR, country: DE, annual_transaction_volume: ten_k, volume_weight: 0.18, fiscal_year_variant: K4 }
+  - { code: "3000", name: "VynFi Mfg APAC SG",  currency: SGD, country: SG, annual_transaction_volume: ten_k, volume_weight: 0.12, fiscal_year_variant: K4 }
+
+chart_of_accounts:
+  complexity: medium
+  industry_specific: true
+
+master_data:
+  vendors:    { count: 100, intercompany_percent: 0.10 }
+  customers:  { count: 120, intercompany_percent: 0.05 }
+  materials:  { count: 400, bom_enabled: true, average_bom_depth: 3 }
+  fixed_assets: { count: 50 }
+  employees:  { count: 100 }
+
+# Chain volume is the primary driver of event count — each
+# P2P / O2C chain produces ~6-8 OCEL events (PO created →
+# released → GR posted → invoice received → invoice posted →
+# payment posted → payment cleared).  14 k chains × ~7 events
+# ≈ 100 k events.
+document_flows:
+  p2p:
+    enabled: true
+    chains_per_month: 360
+    three_way_match_rate: 0.92
+    partial_delivery_rate: 0.12
+    gr_ir_clearing_enabled: true
+  o2c:
+    enabled: true
+    chains_per_month: 360
+    credit_check_failure_rate: 0.04
+    partial_shipment_rate: 0.10
+    return_rate: 0.025
+
+balance:
+  generate_opening_balances: true
+  generate_trial_balances: true
+  reconcile_subledgers: true
+  validate_balance_equation: true
+
+period_close:
+  enabled: true
+
+# 3 % document-level fraud (matches the published rate of the
+# previous dataset version).  Anomaly labels are produced for
+# every fraudulent + selected non-fraudulent events in the
+# OCEL log, joinable to events via `event_id`.
+fraud:
+  enabled: true
+  fraud_rate: 0.02
+  document_fraud_rate: 0.03
+  propagate_to_lines: true
+
+internal_controls:
+  enabled: true
+  coso_enabled: true
+  include_entity_level_controls: true
+  target_maturity_level: managed
+  exception_rate: 0.02
+  sod_violation_rate: 0.01
+
+distributions:
+  enabled: true
+  industry_profile: manufacturing
+  amounts:
+    enabled: true
+    distribution_type: log_normal
+    components:
+      - { weight: 0.65, mu: 5.5, sigma: 1.3, label: "routine" }
+      - { weight: 0.28, mu: 7.8, sigma: 0.9, label: "significant" }
+      - { weight: 0.07, mu: 9.5, sigma: 0.6, label: "major" }
+    benford_compliance: true
+
+temporal_patterns:
+  enabled: true
+  business_days:
+    enabled: true
+    half_day_policy: half_day
+    month_end_convention: modified_following
+  calendars:
+    regions: [US, DE, SG]
+  period_end:
+    model: exponential
+    month_end:   { start_day: -10, base_multiplier: 1.0, peak_multiplier: 3.5, decay_rate: 0.3 }
+    quarter_end: { inherit_from: month_end, additional_multiplier: 1.5 }
+
+# OCPM event log: native OCEL 2.0 generation with all relevant
+# output formats.  `compute_variants: true` plus
+# `include_object_relationships: true` mirror the v0.x dataset's
+# `events`, `objects`, `anomaly_labels`, `document_events` tables.
+ocpm:
+  enabled: true
+  generate_lifecycle_events: true
+  include_object_relationships: true
+  compute_variants: true
+  max_variants: 0  # unlimited
+  output:
+    ocel_json: true
+    flattened_csv: true
+    event_object_csv: true
+    object_relationship_csv: true
+    variants_csv: true
+
+audit:
+  enabled: false  # Audit data has its own dataset
+
+# Method-A flat edge-list provided for completeness — joinable to
+# the OCEL events via shared document_id + entry_date.
+graph_export:
+  je_network:
+    method: a
+
+output:
+  output_directory: "./output"
+  formats: [csv, json]