Give this node a declared benchmark amount in integer minor units, three percentages in basis points, a rationale id and a rounding rule. It recomputes the overall materiality, the performance materiality and the clearly-trivial threshold, and reports whether the ordering between them holds. The performance figure is the tolerable-misstatement input that the sampling node ART-693 takes.
Arithmetic on declared policy. It does not choose the benchmark, does not judge whether the percentage is appropriate, and is not a materiality determination.
Planning materiality starts every engagement, and the arithmetic is the same each time: a benchmark, a percentage, then smaller percentages of that figure. The choice of benchmark and every percentage is policy, so this node carries none. You declare them and the node multiplies.
A clearly-trivial percentage above the performance percentage is flagged CLEARLY_TRIVIAL_ABOVE_PERFORMANCE. The node still reports the figures and never corrects a percentage, because the ordering breach is itself a finding for the reviewer.
The rounding rule, half_up or floor, is a policy parameter and changes the execution hash. All arithmetic is exact integer arithmetic on minor units, with no clock and no randomness, so a verifier can replay it.
ISA 320 and AS 2105 are cited for context only and are never reproduced here.
Refusal codes (compliance_flags ["INPUT_REFUSED"]): BENCHMARK_ID_MISSING, BENCHMARK_AMOUNT_INVALID, OVERALL_BPS_INVALID, PERFORMANCE_BPS_INVALID, TRIVIAL_BPS_INVALID, RATIONALE_ID_MISSING, ROUNDING_RULE_INVALID. A wrong-typed id is refused with the matching MISSING code. A refusal returns no thresholds.
Every benchmark, percentage and id in the conformance fixtures is synthetic and illustrative. None of those values is a recommended percentage.
The performance threshold feeds the tolerable-misstatement input of the monetary-unit sampling node (ART-693) as a separate step you run; nothing is imported. This page and the node are CC BY 4.0.
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 `compute_planning_materiality`. Task: Arithmetic on declared policy: from a declared benchmark amount, three percentages in basis points, a required rationale id and a rounding rule, recomputes overall, performance and clearly-trivial thresholds and flags an ordering violation.
Call it with arguments: {"policy_parameters":{"benchmark_id":"bm-profit-before-tax","benchmark_amount":1234567891,"overall_bps":500,"performance_bps":7500,"trivial_bps":500,"rationale_id":"rat-synthetic-001","rounding_rule":"half_up"}}
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.
Over MCP, the run happens on the AINumbers worker. No AINumbers server stores your inputs.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/841-planning-materiality.html#p=v1.H4sIAAAAAAAA_wG9AEL_eyJiZW5jaG1hcmtfaWQiOiJibS1wcm9maXQtYmVmb3JlLXRheCIsImJlbmNobWFya19hbW91bnQiOjEyMzQ1Njc4OTEsIm92ZXJhbGxfYnBzIjo1MDAsInBlcmZvcm1hbmNlX2JwcyI6NzUwMCwidHJpdmlhbF9icHMiOjUwMCwicmF0aW9uYWxlX2lkIjoicmF0LXN5bnRoZXRpYy0wMDEiLCJyb3VuZGluZ19ydWxlIjoiaGFsZl91cCJ93mRDQb0AAAA