ART-485 · Regulatory Reporting Analytics

Regulatory Report Period-over-Period Variance Explainer

Computes absolute and relative movement per line item across your instance pair (prior vs current), ranks by contribution (largest absolute movement first), and flags which movements exceed your policy-supplied materiality threshold with no explanation on file. Emits a hash-anchored OpenChainGraph v0.4 artifact. Final step of the Regulatory Report Submission Cycle, where filing release is a §27 dual_control(2) gate satisfied by a preparer and a distinct signing-officer approver.

Flags variance, doesn't judge explanations
Not legal or audit advice
🔒 All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Scope limits, read before use: materiality thresholds are policy input you supply, never baked into this tool; refresh them each cycle. This tool does not judge whether a supplied explanation is adequate; a flagged, unexplained variance is a routing signal for human review (RGEC-K-2's downstream gate), not a verdict. Pairs with ART-484 RegRpt Edit-Check Runner, which runs rule pass/fail edit checks rather than variance analytics.
Each: line_item, value.
RankLine itemAbs changePct changeMaterialExplained
OpenChainGraph v0.4 artifact · execution_hash:

    
    
  
Related

Pairs with ART-484 RegRpt Edit-Check Runner: that tool runs rule pass/fail edit checks against a published rule set; this tool computes period-over-period materiality-flagged variance. Both feed RGEC-K-2's downstream submission gate (not built here).

Ask your agent

Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.

Run the AINumbers MCP tool `explain_regrpt_variance`. Task: Compute period-over-period variance across a regulatory report instance pair -- absolute and relative movement per line item against a policy-supplied materiality threshold (default plus per-line overrides), ranked by contribution (largest absolute movement first) -- and flags which movements require a written explanation, i.e.
Call it with arguments: {"policy_parameters":{"instance_pair":{"prior":{"as_of":"2026-03-31","cells":[{"line_item":"total_loans","value":10000},{"line_item":"total_deposits","value":9000}]},"current":{"as_of":"2026-06-30","cells":[{"line_item":"total_loans","value":11500},{"line_item":"total_deposits","value":9050},{"line_item":"other_real_estate_owned","value":200}]}},"materiality_policy":{"version":"FFIEC-MATERIALITY-2026-Q2","default_threshold_abs":100,"default_threshold_pct":0.05,"per_line_overrides":{"other_real_estate_owned":{"abs":50,"pct":0}}},"explanations":[{"line_item":"total_loans","text":"Growth from a Q2 syndicated-loan participation purchase."}]}}
Verify before trusting: call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with the parameter `claimed_hash` set to the returned `execution_hash`, passing the full artifact the run returned (the object containing `policy_parameters` + `output_payload` + `execution_hash`; equivalently `policy_parameters` + `output_payload` with `claimed_hash`), not the bare hash string.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/art-485-regrpt-variance-explainer.html#p=v1.H4sIAAAAAAAA_wFwAo_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