SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.04067 · 2024

Does Biomedical Training Lead to Better Medical Performance?

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2404.04067.json · badge: /api/ran/2404.04067.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
tio-ikim/clue canonical (classifier label)
classifier basis: classifier_2025
5 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_metrics Ran
ran, violated the contract we drafted
tio-ikim/clue/eval/eval_LongHealth.py
code served (permissive licence) · get_code("0c7db73dea0a25ae")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re

def parse_model_choice(pred):
    pred = re.findall('The correct answer is (\\w):', pred)
    if pred:
        return pred[0]
    return ''

def compute_metrics(model_prediction, correct_answer, task3=False):
    model_choice = parse_model_choice(model_prediction)
    if not model_choice:
        return False
    if model_choice != correct_answer and (not task3):
        return False
    if task3:
        return model_choice == 'F'
    return True

ARGS = {
    'model_prediction': 'The correct answer is A: some explanation text here',
    'correct_answer': 'A',
    'task3': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_correct_answer Ran
ran; our contract draft was wrong, not the code
tio-ikim/clue/eval/eval_LongHealth.py
code served (permissive licence) · get_code("92987fdeaa63d462")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

def get_correct_answer(sample):
    for answer in sample:
        if not answer.startswith('answer') or answer.endswith('location'):
            continue
        if sample['correct'] in sample[answer]:
            return answer[-1].upper()

sample = {
    'correct': 'Paris',
    'answer1': ['Paris', 'London', 'Berlin'],
    'answer2': ['Rome', 'Madrid', 'Athens'],
    'answer3_location': ['France', 'Italy'],
    'answer4': ['Dublin', 'Amsterdam', 'Vienna']
}

ARGS = {
    'sample': sample
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
parse_model_choice Ran
ran; our contract draft was wrong, not the code
tio-ikim/clue/eval/eval_LongHealth.py
code served (permissive licence) · get_code("70cb661f76d88166")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re

def parse_model_choice(pred):
    pred = re.findall('The correct answer is (\\w):', pred)
    if pred:
        return pred[0]
    return ''

# The function takes a single parameter 'pred' which is a string
# It uses re.findall to extract a pattern from the string
# The pattern looks for "The correct answer is X:" where X is a word character

# Valid test inputs
pred_with_match = "The correct answer is A: This is correct"
pred_without_match = "No pattern here"
pred_multiple_matches = "The correct answer is B: First, The correct answer is C: Second"

ARGS = {
    'pred': pred_with_match
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
postprocess_llm_results Ran
ran; our contract draft was wrong, not the code
tio-ikim/clue/data/MeDiSumQA/generate_qas.py
code served (permissive licence) · get_code("b80a70a12a04cb9d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Analyze the function: postprocess_llm_results takes a 'result' parameter
# and calls .split('\n') on it, then processes lines with string operations.
# The parameter must be a string.

result_string = """Some header line
* First item
- Second item
___ separator line
* Third item
  - Fourth item  
Regular text line"""

ARGS = {
    "result": result_string
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
postprocess_qas Ran
ran; our contract draft was wrong, not the code
tio-ikim/clue/data/MeDiSumQA/generate_qas.py
code served (permissive licence) · get_code("72277b101129d205")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re

def postprocess_qas(statements, model_generation):
    statements = [s.strip() for s in statements]
    pattern = 'Question: (.*?)\\nAnswer: (.*?)\\n'
    qas = re.findall(pattern, model_generation)
    qas_filtered = []
    for q, a in qas:
        if a.strip() in statements:
            qas_filtered.append((q.strip(), a.strip()))
    return qas_filtered


# Setup code
statements = [
    "Paris is the capital of France",
    "The sky is blue",
    "Water boils at 100 degrees"
]

model_generation = """Question: What is the capital of France?
Answer: Paris is the capital of France
Question: What color is the sky?
Answer: The sky is blue
Question: At what temperature does water boil?
Answer: Water boils at 100 degrees
Question: What is 2+2?
Answer: The answer is 4
"""

ARGS = {
    "statements": statements,
    "model_generation": model_generation
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Large Language Models (LLMs) are expected to significantly contribute to patient care, diagnostics, and administrative processes. Emerging biomedical LLMs aim to address healthcare-specific challenges, including privacy demands and computational constraints. Assessing the models' suitability for this sensitive application area is of the utmost importance. However, biomedical training has not been systematically evaluated on medical tasks. This study investigates the effect of biomedical training in the context of six practical medical tasks evaluating $25$ models. In contrast to previous evaluations, our results reveal a performance decline in nine out of twelve biomedical models after fine-tuning, particularly on tasks involving hallucinations, ICD10 coding, and instruction adherence. General-domain models like Meta-Llama-3.1-70B-Instruct outperformed their biomedical counterparts, indicating a trade-off between domain-specific fine-tuning and general medical task performance. We open-source all evaluation scripts and datasets at https://github.com/TIO-IKIM/CLUE to support further research in this critical area.

For agents

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

get_harvested_code_for_paper("2404.04067")
get_code_for_paper("2404.04067")
have("2404.04067")

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

curl https://syntology.ai/api/ran/2404.04067.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.04067.svg)](https://syntology.ai/paper/2404.04067)

Connect an agent — have() is free.