# Desk log ADR-XAT-20260825

**Status:** First-party InfiniSynapse desk log (sanitized composite; not a customer extract)  
**Page:** https://infinisynapse.com/en/blog/explainable-ai-tools  
**Run ID:** `ADR-XAT-20260825`  
**Date:** 2026-08-25 (Tuesday)  
**Operator:** InfiniSynapse Data Team  
**Attestor:** William Zhu, InfiniSynapse cofounder ([GitHub @allwefantasy](https://github.com/allwefantasy))  
**Contact for contradictions:** zhuhl@infinisynapse.com

## What this file is

A downloadable record of asking two products the same monthly refund-rate question: Product A returned a caption with no statement; Product B left a plan, a reopenable statement, and a family table. It is **not** a named-logo customer case, a vendor bake-off, or a BLS / SEC / Stanford / McKinsey / NIST experiment.

## Four-step method (reproducible)

1. Bind a monthly operations-adjacent goal on a read-only orders source plus a one-page remap note locking SKU family. Sanitize first.
2. Ask Product A and Product B the same standing goal. Request a Markdown memo, two charts, and intermediate tables.
3. Score Product A on three checks: statement reopens, family table open, file downloadable.
4. Score Product B on the same three checks. Keep both artifacts side by side.

## Source and goal

| Field | Value |
|---|---|
| Sources | One orders table, about 12,685 fulfilled lines across two complete months, plus a one-page remap note locking SKU family |
| Standing goal | Why did refund rate move last month versus the prior month |
| Contrast | Product A (caption only) vs Product B (plan → statement → file) |

## Results

| Retrieval state | Statement reopens | Family table open | File downloadable |
|---|---|---|---|
| Product A (caption only) | 0 | 0 | 0 |
| Product B (plan → statement → file) | 1 | 1 | 1 |

Fulfilled rows on this run: 6,275 (prior month) vs 6,410 (later month). Product A could not show the remap. Product B opened the family table and named the collision: one SKU remapped mid-month. The reviewer rejected Product A and accepted Product B.

Wall-clock for the successful Product B trail: 10 minutes (warehouse time excluded). The clock started when the operator opened the standing goal and ended when the statement, the family table, and the file sat in one folder.

## What you may cite

- Artifact counts 0/0/0 → 1/1/1, 6,275 vs 6,410 fulfilled rows, ~12,685 lines, ~10 min wall-clock, run ID
- First-party aggregate CSV and verify script next to this log (row check only; not a third-party audit)

## What you may not claim

- Customer uplift %, official EEAT score, named-logo case, or that BLS / SEC / BIS / WHO / PubMed / Stanford / McKinsey / Gartner / NIST / OWASP / WAIC scored this run

## Independent context (not this run)

- [BLS OPUB](https://www.bls.gov/opub/)
- [SEC EDGAR](https://www.sec.gov/edgar)
- [BIS statistics](https://www.bis.org/statistics/index.htm)
- [WHO Data](https://www.who.int/data)
- [PubMed](https://pubmed.ncbi.nlm.nih.gov/)
- [NIST Four Principles of Explainable Artificial Intelligence](https://www.nist.gov/publications/four-principles-explainable-artificial-intelligence)
- [Stanford HAI AI Index](https://hai.stanford.edu/ai-index)
- [McKinsey State of AI](https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai)
- [Gartner Peer Insights — Analytics and BI Platforms](https://www.gartner.com/reviews/market/analytics-business-intelligence-platforms)
- [NIST AI Risk Management Framework](https://www.nist.gov/itl/ai-risk-management-framework)
- [OWASP Top 10 for LLM Applications](https://owasp.org/www-project-top-10-for-large-language-model-applications/)
- [W3C Data Catalog Vocabulary (DCAT)](https://www.w3.org/TR/vocab-dcat-3/)
- [DataCite](https://datacite.org/)
- First-party homepage recognition only: [2026 WAIC Future Tech OPC Excellence Award](https://infinisynapse.com/#recognition) (self-described; not independently verified in this log)