---
language:
- en
- ga
license: apache-2.0
library_name: transformers
tags:
- pii
- token-classification
- healthcare
- de-identification
- ireland
- ppsn
base_model:
- OpenMed/OpenMed-PII-SuperClinical-Large-434M-v1
datasets:
- nvidia/Nemotron-PII
- joelniklaus/mapa
model-index:
- name: OpenMed-PPSN-v5
  results:
  - task:
      type: token-classification
      name: PPSN detection (Irish regression set)
    dataset:
      name: irish_ppsn_regression_v5
      type: custom
    metrics:
    - type: f1
      value: 0.8235
      name: Raw model F1
    - type: f1
      value: 1.0000
      name: Hybrid strict F1
---

# OpenMed PPSN v5

Token classification model derived from `OpenMed/OpenMed-PII-SuperClinical-Large-434M-v1` with added `B-PPSN` / `I-PPSN` support for Irish PPS Number detection.

## What this release contains

- Full model weights (`model.safetensors`) with original OpenMed labels + PPSN labels.
- `label_meta.json` with label mapping and provenance.
- Repro/eval artifacts:
  - `irish_ppsn_regression_v5.jsonl`
  - `eval_manual_irish_v5_raw.json`
  - `eval_hybrid_v5_no_plausible.json`
  - `ab_non_ppsn_v5_baseline.json`

## Key results

On `irish_ppsn_regression_v5`:

- Raw model-only PPSN performance: `P=0.7778 R=0.8750 F1=0.8235`.
- Recommended strict hybrid mode (model + checksum + span normalization, no plausible fallback):
  - `P=1.0000 R=1.0000 F1=1.0000`.

Non-PPSN retention check vs base OpenMed (A/B):

- Real-text behavior agreement F1: `1.0000`.
- Entity density unchanged in the sampled real-text proxy set.

## Recommended production usage

For best PPSN reliability, run this model with a strict hybrid post-processor:

1. Keep model detections for all labels.
2. For PPSN specifically, normalize/expand spans to full PPSN candidates.
3. Validate PPSN with checksum.
4. Disable broad "plausible" fallback in production (`no-plausible-ppsn`).

This repository includes only the model artifacts; hybrid scripts are in the companion codebase used to train/evaluate this release.

## Limitations

- The Irish regression set is small and targeted; additional domain-specific validation is required before regulated deployment.
- PPSN detection in noisy OCR/ASR or heavily malformed text may require extra hardening.

## License and attribution

- This derivative release is distributed under Apache-2.0, consistent with the base model license tag.
- Base model: `OpenMed/OpenMed-PII-SuperClinical-Large-434M-v1`.
- Training/evaluation used synthetic and augmented data sources, including `nvidia/Nemotron-PII` and `joelniklaus/mapa`.
- See `NOTICE` for attribution details.

## QA quick check

- Load this model as a standard `AutoModelForTokenClassification` checkpoint.
- Run against `irish_ppsn_regression_v5.jsonl`.
- Confirm results in `eval_manual_irish_v5_raw.json` (raw) and `eval_hybrid_v5_no_plausible.json` (strict hybrid).