SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.07890 · ICLR · 2025

Training on the Test Task Confounds Evaluation and Emergence

Moritz Hardt, Ricardo Dominguez-Olmedo, Florian Dorner

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 3 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/2407.07890.json · badge: /api/ran/2407.07890.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
socialfoundations/training-on-the-test-task canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
gsm8k_rows_to_qa Ran
ran; our contract draft was wrong, not the code
socialfoundations/training-on-the-test-task/experiments/data_utils.py
pointer only (licence: NONE) · get_code("d13b737925c23199")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, socialfoundations/training-on-the-test-task 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.

mmluaux_row_to_qa Ran
ran; our contract draft was wrong, not the code
socialfoundations/training-on-the-test-task/experiments/data_utils.py
pointer only (licence: NONE) · get_code("0730cf1097662eb1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, socialfoundations/training-on-the-test-task 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_dataset Ran
ran; our contract draft was wrong, not the code
socialfoundations/training-on-the-test-task/experiments/data_utils.py
pointer only (licence: NONE) · get_code("f067ba5db73dc40a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, socialfoundations/training-on-the-test-task 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.

get_job_memory Not yet run
unverified (harvested, no recorded run)
socialfoundations/training-on-the-test-task/experiments/model_utils.py
pointer only (licence: NONE) · get_code("0eac4ba9658efdb5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, socialfoundations/training-on-the-test-task 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.

get_model_name Not yet run
unverified (harvested, no recorded run)
socialfoundations/training-on-the-test-task/experiments/model_utils.py
pointer only (licence: NONE) · get_code("3b85469ad66d264c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, socialfoundations/training-on-the-test-task 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.

get_n_gpus Not yet run
unverified (harvested, no recorded run)
socialfoundations/training-on-the-test-task/experiments/model_utils.py
pointer only (licence: NONE) · get_code("ab5c0b21bd0dceef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, socialfoundations/training-on-the-test-task 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

We study a fundamental problem in the evaluation of large language models that we call training on the test task. Unlike wrongful practices like training on the test data, leakage, or data contamination, training on the test task is not a malpractice. Rather, the term describes a growing set of practices that utilize knowledge about evaluation tasks at training time. We demonstrate that training on the test task confounds both relative model evaluations and claims about emergent capabilities. We argue that the seeming superiority of one model family over another may be explained by a different degree of training on the test task. To this end, we propose an effective method to adjust for the effect of training on the test task on benchmark evaluations. Put simply, to fine-tune each model under comparison on the same task-relevant data prior to evaluation. We then show that instances of emergent behavior disappear gradually as models train on the test task. Our work promotes a new perspective on the evaluation of large language models, with broad implications for benchmarking and the study of emergent capabilities. †

For agents

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

get_harvested_code_for_paper("2407.07890")
get_code_for_paper("2407.07890")
have("2407.07890")

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

curl https://syntology.ai/api/ran/2407.07890.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.07890.svg)](https://syntology.ai/paper/2407.07890)

Connect an agent — have() is free.