INDUSTRY FIELD GUIDE
Wood preservation data for AI treatment-tag matching
AWPA explains how a treated-wood end tag records treatment information and intended use.
NAICS 321114 · Wood Preservation
AWPA explains how a treated-wood end tag records treatment information and intended use. A preservation plant can build a focused task around linking that tag to the correct batch evidence. AWPA information for specifiers
Prepare original mock tags and a fictional charge ledger. Give two charges the same species and dimensions but different treatment references. Ask an assistant which tag is supported for each bundle. Include a detached tag photographed beside an unmarked bundle and a later correction changing one ledger identifier. The answer should preserve the uncertainty around the detached tag and use the effective correction only where it applies.
Keep product identity, charge reference, declared treatment and tag version in separate labels. A held-out set can use a different tag layout and bundle split. Score wrong-charge matches and conclusions based solely on wood color as distinct failures. An image can help read a mark while the record relationship establishes which material it concerns.
Use untreated props and fictional treatment values for the first pilot. Actual chemical schedules, customer requirements and inspection-agency material need disclosure authority. Explain the evidence-selection task and reviewer key to a prospective buyer. Acceptance criteria and permitted sources should be agreed before preparing operating records or filming any production process.
Discuss this original manufacturing sample with Fiund
Original Fiund exercise
A replacement tag needs evidence of its scope
Neutral paper tags and a toy ledger represent a fictional treatment batch. Neither real chemicals nor suitability ratings appear.
| Record | Source | What it records |
|---|---|---|
| T1 | Charge ledger | Mock charge C7 lists bundles B12 and B13. |
| T2 | Photo archive | B12 original tag is legible and references C7. |
| T3 | Repack note | B13 tag replaced; new tag says B13 without a charge identifier. |
| T4 | Request | Distinguish physical tag evidence from ledger-derived charge linkage. |
Question for the model
How should the two bundle records differ?
Show the reference answer and checks
B12 has both a ledger link in T1 and a visible C7 mark in T2. B13 has the ledger link through T1 but the replacement tag in T3 does not visibly corroborate it. Preserve these as separate evidence statuses instead of copying B12's image proof.
- Assuming a blank field on a replacement tag revokes the ledger
- Using a sibling bundle's tag as proof of B13's marking
Fields to preserve
- charge_reference
- Links bundles to the fictional ledger
- tag_version
- Identifies which physical tag was observed
- corroboration_status
- Separates a recorded link from a verified visible one
Test another case
Introduce a conflicting visible charge on B13 and ask the model to record both rather than silently selecting either.
No actual treatment chemistry, certified uses, chemical application guidance or authentic tags.
Discuss a contribution
Describe the sources you control, the task they could support and what has already been checked. Use the existing-data assessment for an archive or the collection brief for a new recording project. The contributor agreement defines Fiund’s licensing authority and compensation. A guide or fictional exercise does not establish an accepted collection or a sale.