SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.01725 · 2024

DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

10 of 13 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 8 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/2407.01725.json · badge: /api/ran/2407.01725.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
allenai/discoverybench canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
FunctionStatusWhere it lives
extract_bracket_substrings Ran
ran; our contract draft was wrong, not the code
allenai/discoverybench/utils/helpers.py
pointer only (licence: NOASSERTION) · get_code("61d2078e13864a0c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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_variable Ran
ran; our contract draft was wrong, not the code
allenai/discoverybench/utils/helpers.py
pointer only (licence: NOASSERTION) · get_code("1fe5884664281ae3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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_dv_query_for_real Ran
ran; our contract draft was wrong, not the code
allenai/discoverybench/utils/autonomous_single_agent.py
pointer only (licence: NOASSERTION) · get_code("11d5942be3ac53d7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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_dv_query_for_synth Ran
ran; our contract draft was wrong, not the code
allenai/discoverybench/utils/autonomous_single_agent.py
pointer only (licence: NOASSERTION) · get_code("15364ed46134e865")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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_prompt_data Ran
ran; our contract draft was wrong, not the code
allenai/discoverybench/agents/coder_agent.py
pointer only (licence: NOASSERTION) · get_code("2d6ea20e03caf9c0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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_score_from_answer Ran
ran, honoured the contract we drafted
allenai/discoverybench/eval/new_eval.py
pointer only (licence: NOASSERTION) · get_code("3ec3bb849b4f7a1e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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.

prepare_dataset_metadata_json Ran
ran; our contract draft was wrong, not the code
allenai/discoverybench/eval/new_eval.py
pointer only (licence: NOASSERTION) · get_code("1390bd9484a06739")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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.

validate_metadata_options Ran
ran, violated the contract we drafted
allenai/discoverybench/discovery_agent.py
pointer only (licence: NOASSERTION) · get_code("45a21e6fc93948b5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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.

validate_option Ran
ran; our contract draft was wrong, not the code
allenai/discoverybench/discovery_eval.py
pointer only (licence: NOASSERTION) · get_code("335a12a64e9392c2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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.

validate_query Ran
ran; our contract draft was wrong, not the code
allenai/discoverybench/discovery_agent.py
pointer only (licence: NOASSERTION) · get_code("7126075f6b70c064")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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.

deep_get Not yet run
unverified (harvested, no recorded run)
allenai/discoverybench/utils/helpers.py
pointer only (licence: NOASSERTION) · get_code("5ae806d9337d2727")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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.

run_chatgpt_query_multi_turn Not yet run
unverified (harvested, no recorded run)
allenai/discoverybench/eval/lm_utils.py
pointer only (licence: NOASSERTION) · get_code("1bb0f4227816397d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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.

validate_model_name Not yet run
unverified (harvested, no recorded run)
allenai/discoverybench/discovery_agent.py
pointer only (licence: NOASSERTION) · get_code("7ce491b58862e1b9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/discoverybench (NOASSERTION). 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 13 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

Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of provided datasets? To evaluate this question, we present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. The benchmark is designed to systematically assess current model capabilities in discovery tasks and provide a useful resource for improving them. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering, by manually deriving discovery workflows from published papers to approximate the real-world challenges faced by researchers, where each task is defined by a dataset, its metadata, and a discovery goal in natural language. We additionally provide 903 synthetic tasks to conduct controlled evaluations across task complexity. Furthermore, our structured formalism of data-driven discovery enables a facet-based evaluation that provides useful insights into different failure modes. We evaluate several popular LLM-based reasoning frameworks using both open and closed LLMs as baselines on DiscoveryBench and find that even the best system scores only 25%. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.

For agents

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

get_harvested_code_for_paper("2407.01725")
get_code_for_paper("2407.01725")
have("2407.01725")

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

curl https://syntology.ai/api/ran/2407.01725.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.01725.svg)](https://syntology.ai/paper/2407.01725)

Connect an agent — have() is free.