Example record

This is a real (de-identified) MedLog record generated during the SEP-1 abstraction pilot at UC San Diego Health. It captures one LLM call within a multi-step sepsis quality-reporting workflow — note the shared run_id linking it to the other calls in the same abstraction run.

{
  "header": {
    "medlog_version": "0.0.1",
    "event_id": "551b1676-1837-4278-988d-59ba3166b83e",
    "timestamp": "2026-01-10T05:31:19.805482+00:00",
    "system_info": "SEP-1 Abstraction AI",
    "run_id": "492dac48-dd7d-485e-8991-1325e814e73e"
  },
  "model_instance": {
    "model_id": "Llama-3.1-8B-Instruct",
    "model_version": "2024-07-18"
  },
  "user_identity": {
    "process_id": 3023
  },
  "target_identity": {
    "MRN": "XXXXXXXX",
    "CSN": "XXXXXXXX"
  },
  "inputs": {
    "prompt": "You are a CMS quality abstractor. Your task is to review patient's medical note and answer the given sepsis compliance question following the abstraction instructions. Generate clear rationale to your answer by thinking step-by-step. [...] QUESTION: Does the note contain an explicit mention that the patient has already been discharged? Do not infer under any circumstances. [...]"
  },
  "internal_artifacts": {
    "chain_of_thought": "The note does not explicitly mention that the patient has already been discharged. The note only mentions that the patient left the ICU at 0000, which implies they were transferred to another location, but does not confirm discharge.",
    "extracts": [
      "Pt left ICU at 0000"
    ]
  },
  "outputs": {
    "option": "N"
  },
  "outcomes": {
    "category": "E - In-Numerator Population"
  },
  "user_feedback": {
    "qps_analyst": "Agree, case passes."
  }
}

Field-by-field

header

The Header: the protocol version, a stable event_id, the invocation timestamp, system info, and a run_id that links this call to the other LLM calls in the same SEP-1 abstraction run.

model_instance

The Model instance: Llama-3.1-8B-Instruct, version 2024-07-18.

user_identity

The User identity. Here the caller is an automated process (process_id: 3023) — the abstraction pipeline, not a human.

target_identity

The Target identity: the patient, referenced by de-identified EHR identifiers (MRN, CSN).

inputs

The Inputs: the full prompt, including the abstraction instructions and the specific SEP-1 compliance question posed to the model.

internal_artifacts

The Internal artifacts: the model’s chain-of-thought and the supporting extracts it pulled from the note. Trace-level analysis of this field is what revealed the model’s confusion between intra-hospital transfers and true discharges.

outputs

The Output shown downstream: the answer N to the discharge question.

outcomes

The Outcome: the resulting SEP-1 population category for this case.

user_feedback

The User feedback: the quality-and-patient-safety (QPS) analyst’s adjudication — “Agree, case passes.”

This record uses the protocol’s conceptual field names. The API reference defines the concrete event payloads a collector accepts (for example, system_metadata, caller_type/caller_id, and the typed artifact / output / outcome objects). The conceptual model and the wire format describe the same nine fields.

Protocol

Fields at invocation

Fields appended later

Examples

Example record

Field-by-field

​Field-by-field

Field-by-field