Article

Same Inputs, Different EDSS: Measuring Specification Drift in Clinical Scoring Pipelines

2026-07-07

Abstract excerpt

Clinical informatics pipelines increasingly compute validated clinical endpoints from upstream NLP outputs. Even when the endpoint is defined by an established rubric, translating that rubric across representations—natural language instructions, program logic, and reference implementations—can introduce specification drift, where ostensibly equivalent calculators yield meaningfully different scores. We study this...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 710630d0-d4d7-533e-bc42-da2a8c0dcec8
DOI: 10.64898/2026.06.25.26356350

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Same Inputs, Different EDSS: Measuring Specification Drift in Clinical Scoring PipelinesDOI 10.64898/2026.06.25.26356350Read

From Output Errors to Workflow Harm: A Practitioner-Audit Method for LLM-Mediated ResearchSemantic proximity Read

Benchmarking large language models for ACMG/AMP variant interpretation and variant callingSemantic proximity Read

Evaluating Large Language Models for Translating Multimodal Phenotype Documentations into Executable EHR Phenotyping AlgorithmsSemantic proximity Read

C-RLM: Schema-Enforced Recursive Synthesis for Auditable, Long-Context Clinical DocumentationSemantic proximity Read

Evaluating Large Language Models for Translating Multimodal Phenotype Documentations into Executable EHR Phenotyping AlgorithmsSemantic proximity Read

The FAIRSCAPE AI-readiness Framework for Biomedical ResearchSemantic proximity Read

Closed-Loop Quality Assurance for Production Clinical AI DocumentationSemantic proximity Read

From Plausible Narrative to Sound Abduction: A Governed Abductive Architecture for Medical Digital Twins in Multiple Sclerosis CareSemantic proximity Read

Algorithmic Versus Expert Rankings of Large Language Models in Peritoneal Dialysis Prescription Review: A Trap-Embedded Synthetic BenchmarkSemantic proximity Read

ECLIPSE v2.0: A Reproducible Scaffold for Severe Confirmatory Testing through Preregistration, Single-Shot Validation, and Static-Analysis ScreeningSemantic proximity Read

A lightweight computational method for monitoring response convergence in LLM-based synthetic populationsSemantic proximity Read

Harm-Conditioned Computational Friction as a Contrastive Diagnostic of Safety Representations in Language Models: A Proof-of-Concept and Control AuditSemantic proximity Read