Import inspection

# Meat, poultry, and egg imports to inspect first

Not every imported lot of meat, poultry, or eggs can be opened. This model reads every record in the Food Safety and Inspection Service's public import data since fiscal 2014 and ranks them twice: first by the chance of refusal for public health, and separately by the chance of refusal for the product's condition.

Lots and outcomes from [FSIS Import and Export Data](https://www.fsis.usda.gov/inspection/import-export/international-reports/import-and-export-data), fiscal years 2014 to 2026. Every figure on this page is measured on lots the model was not trained on. Model `fsis-import-risk 0.2.0`.

Review workflow prototype

## Seven cases. Different reasons to ask for a human look.

This case library demonstrates how a future uncertainty queue could route more than new establishments. Examples come from the February 2026 point-in-time snapshot; outcomes were not used to select or explain them. They use a separate exploratory documentation/damage ranking, not the capture-curve model above.

Research-only demo. Rank percentiles are not probabilities. The 207-row formal support-review lane is still homogeneous; the other profiles below are candidate routing signals, not validated uncertainty bands or inspection directives. No live scorer or Haiku call is connected.

- [Case Q01 — No establishment history — Beef · raw intact cuts — Documentation 99.41th · Damage 87.06th](https://blackgrove.ai/fsis-risk-playground?tier=t1&opened=7.5&review_case=q01)
- [Case Q02 — First route at an established plant — Beef · manufacturing trimmings — Documentation 99.76th · Damage 83.59th](https://blackgrove.ai/fsis-risk-playground?tier=t1&opened=7.5&review_case=q02)
- [Case Q03 — New product and route at known plant — Beef · manufacturing trimmings — Documentation 99.71th · Damage 86.62th](https://blackgrove.ai/fsis-risk-playground?tier=t1&opened=7.5&review_case=q03)
- [Case Q04 — Reactivated establishment — Beef · raw intact cuts — Documentation 99.71th · Damage 74.85th](https://blackgrove.ai/fsis-risk-playground?tier=t1&opened=7.5&review_case=q04)
- [Case Q05 — Recent-failure history proxy — Beef · manufacturing trimmings — Documentation 100.00th · Damage 85.55th](https://blackgrove.ai/fsis-risk-playground?tier=t1&opened=7.5&review_case=q05)
- [Case Q06 — Unusual recent volume — Beef · manufacturing trimmings — Documentation 100.00th · Damage 98.68th](https://blackgrove.ai/fsis-risk-playground?tier=t1&opened=7.5&review_case=q06)
- [Case Q07 — Unusual lot size — Beef · raw intact primals/subprimals — Documentation 100.00th · Damage 98.88th](https://blackgrove.ai/fsis-risk-playground?tier=t1&opened=7.5&review_case=q07)

Selected case · February 2026

### No establishment history

Beef · raw intact cuts · No prior establishment history is available.

Documentation rank percentile

99.41

Damage rank percentile

87.06

Severity assessment

INDETERMINATE · no direct defect evidence in this payload

#### Offline LLM-style reasoning

Novelty is a support gap, not a defect. The available fields show no certificate discrepancy, mark issue, or physical finding.

#### Evidence to request / verify

Confirm establishment identity and inspect the routine certificate and marking records. Grade severity only if a concrete discrepancy is found.

This is an authored dry-run, not model-generated advice. Required FSIS checks remain unchanged. An unflagged lot is not cleared or established as safe.

Public health is a failed laboratory test, a pathogen, or a recall: 70 refused lots in fiscal 2025 and 2026. Condition is what an inspector finds on the product, such as pathology, extraneous material, a failed product exam, or compromised packaging: 984 refused lots. Plant history only ranks a lot by its plant's refusals in the previous year. A random draw catches the share it opens. 7.5% is a share we chose so the methods compare on equal terms.
