SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.15467 · 2026

MasonNLP at MEDIQA-SYNUR 2026: Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction

Özlem Uzuner, Rezaul Karim

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (7 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2605.15467.json · badge: /api/ran/2605.15467.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
AHMRezaul/MEDIQA-SYNUR-2026 community
Papers with Code archive
11 ran · 1 no recorded run
FunctionStatusWhere it lives
ConceptDef Ran
ran on a synthesized input · constructed an object; no result was computed
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("0af02491f1e7d0e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

IDValue Ran
ran on a synthesized input · constructed an object; no result was computed
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("de9ceaed2111c288")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

KBExample Ran
ran on a synthesized input · constructed an object; no result was computed
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("6cc99aeada5b78d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Observation Ran
ran on a synthesized input · constructed an object; no result was computed
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("ac91600ff8087a19")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

RetrievalItem Ran
ran on a synthesized input · constructed an object; no result was computed
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("064c3a9d888ea6a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SchemaIndex Ran
ran on a synthesized input · constructed an object; no result was computed
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("5798fc1c9d80daf2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SentenceTransformerEmbedder Ran
ran on a synthesized input · constructed an object; no result was computed
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("4da38f17f0555bf7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_schema_keyword_hints Ran
ran; our contract draft was wrong, not the code
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("1b587c35ad3aabf8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

jaccard Ran
ran, honoured the contract we drafted
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("4006a412a663df6d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_text Ran
ran; our contract draft was wrong, not the code
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("cf405930dde4f507")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

tokenize Ran
ran; our contract draft was wrong, not the code
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("d3c3053082b8a558")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

HybridConceptAwareRetriever Not yet run
unverified (harvested, no recorded run)
AHMRezaul/MEDIQA-SYNUR-2026/llama/rag.py
pointer only (licence: NONE) · get_code("91976d24b9a5d257")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AHMRezaul/MEDIQA-SYNUR-2026 when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 12 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Conversational nurse-patient transcripts contain actionable observations, but converting these transcripts into structured representations at scale remains challenging. Documentation burden is substantial, with prior studies showing clinicians spend large portions of their workday on documentation and related desk work rather than direct patient care. MEDIQA-SYNUR focuses on observation extraction from conversational nurse-patient transcripts, requiring systems to normalize these narratives into a predefined schema with value-type constraints. We propose a modular retrieval-augmented generation (RAG) pipeline that uses the training set as an exemplar corpus, combines schemaconstrained prompting (full schema vs. pruned candidate schema), deterministic schema-based postprocessing, and a second-pass audit, with two LLM backbones: Llama-4-Scout-17B-16E-Instruct and GPT-5.2 with corresponding embedding models for RAG. Our best configuration uses GPT-5.2 with full schema, RAG, and a second-pass auditing, achieving 80.36% F1 score. Overall, our results show that RAG consistently improves performance, while the optimal degree of schema constraint depends on the model, and second-pass auditing yields modest additional gains by correcting residual schema-adherence errors.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2605.15467")
get_code_for_paper("2605.15467")
have("2605.15467")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2605.15467.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2605.15467.svg)](https://syntology.ai/paper/2605.15467)

Connect an agent — have() is free.