12-2 · Crisis prevention · 2026-11-14

Suicide Prevention Research for Bereaved People and Attempt Survivors

Cohort and simulationSynthetic checks matchedEvaluation data partly established

Use synthetic replay to check the flow of a safety plan and transitions to designated responses.

This is a research record, not a help service. If you are in Korea and need to talk to someone now, the suicide prevention counselling line 109 can be reached by phone. Elsewhere, contact your local emergency number.

Research question and target

Evaluate events and transition rules in synthetic follow-up timelines. Verify that constrained responses stay within the designated state machine.

Internal target: Zero clinically disallowed response events on the fixed test
Programme: Crisis prevention
Evidence on this record: Synthetic harness (prevent12)Common synthetic checks

Evaluation data

NIMH NDA ED-SAFE Trial
Collection 2191, 10.15154/wrp2-mq67
Split rule locked
Danish linked-register bereavement study
Pitman et al. 2023, 10.1017/S2045796023000653
Blocked
ED-SAFE Table 2, JAMA Psychiatry
Miller et al. 2017, 10.1001/jamapsychiatry.2017.0678
Manifest locked
APOSTOLUS protocol replay with C-SSRS reference
APOSTOLUS controls v1
Manifest locked

Evaluation registry · Labels and split definitions (KR)

Synthetic harness · prevent12

Risk trajectory and rule-constrained safety-plan support

Disallowed output events on the synthetic test: 0 of 30,190, against a target of zero. The value holds within the closed template space, on the assumption that the approved wording has passed clinical review.

State transitions checked: 156
Release combinations: 190
Escalations without the generator: 128

Limits

Templates hold placeholders, not wording. The approved wording is kept outside this repository and compared by hash.
Policy conditions appear only as abstract codes; the specification, code and fixtures contain no example sentences.

Synthetic inputs only (synthetic_only). These are virtual metrics on synthetic inputs. No real cohort has been evaluated, clinical validity has not been assessed and no auditor has signed the result. A separate audit program passed 4 of 4 gates.

G1 · Frozen inputs and submission structureG2 · Schema, policy rules and transition completenessG3 · Independent recalculation of thresholds and metricsG4 · Virtual metric verdict and result hash

Audit record (JSON) · Run output (JSON) · 12-2 design specification: risk trajectory and safety-plan engine (KR) · 12-1 to 12-4 replay record (KR)

python3 -B -m prevent12.orchestrate --output evidence/prevent12-run.json
python3 -B -m prevent12.audit --run evidence/prevent12-run.json --output evidence/prevent12-audit.json
python3 -B -m unittest discover -s tests -p 'test_prevent12.py' -v

Sources and eligibility

Columbia Lighthouse Project C-SSRS
Instrument documentation
Documents a public research assessment instrument. Deidentified emergency-department follow-up and subsequent attempt labels require separate data.

Boundary cases

Transition to the predefined pathway after an out-of-scope request
Withholding or switching a response when records are incomplete or conflicting
Separate denominators for follow-up scenarios involving bereaved people and attempt survivors

Common synthetic checks

Constrained response transitions in synthetic event streams · 4/4 matched

Expected and observed values for these cases

What the official call asks

Bereaved families and people who have survived an attempt are separate areas, with field validation of at least 100 and 200 participants respectively and four or more institutions in each.

Proposal requirements, printed pages 57–59 · All twelve requirements

Interpretation and next evaluation

Transition behaviour and prevention after discharge require different follow-up evidence. The source and access terms for the follow-up cohort remain unverified.

Next check: Lock the synthetic transition table and denominator. Define the independent outcomes required for further follow-up.

← All twelve projects