Papers › A Closer Look at AUROC and AUPRC under Class Imbalance

A Closer Look at AUROC and AUPRC under Class Imbalance

11 Jan 2024arXiv:2401.06091archive 2025-07-28

Matthew B. A. McDermott, Haoran Zhang, Lasse Hyldig Hansen, Giovanni Angelotti, Jack Gallifant

In machine learning (ML), a widespread claim is that the area under the precision-recall curve (AUPRC) is a superior metric for model comparison to the area under the receiver operating characteristic (AUROC) for tasks with class imbalance. This paper refutes this notion on two fronts. First, we theoretically characterize the behavior of AUROC and AUPRC in the presence of model mistakes, establishing clearly that AUPRC is not generally superior in cases of class imbalance. We further show that AUPRC can be a harmful metric as it can unduly favor model improvements in subpopulations with more frequent positive labels, heightening algorithmic disparities. Next, we empirically support our theory using experiments on both semi-synthetic and real-world fairness datasets. Prompted by these insights, we conduct a review of over 1.5 million scientific papers to understand the origin of this invalid claim, finding that it is often made without citation, misattributed to papers that do not argue this point, and aggressively over-generalized from source arguments. Our findings represent a dual contribution: a significant technical advancement in understanding the relationship between AUROC and AUPRC and a stark warning about unchecked assumptions in the ML community.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 34 code samples harvested from 3 repositories linked to this paper: 25 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 2 repositories, 14 ran (7 with no instrument failure; 7 where Syntology's instrument failed); found in paper text by Syntology: 13 samples from 1 repository, 11 ran (8 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lassehhansen/arxiv-search officialmentioned in papermentioned on GitHubSyntology: 12 samples, 8 ran (4 instrument-failed) · 4 unverified report
hzhang0/auc_bias officialmentioned in paperSyntology: 9 samples, 6 ran (3 instrument-failed) · 3 unverified report
mmcdermott/auc_is_all_you_need officialmentioned in paperSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

34 samples harvested: 25 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
10ran · our draft was wrong
13ran
9unverified

Licence: 21 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

lassehhansen/arxiv-search official repository 12 samples, 8 ran (4 instrument-failed) · 4 unverified
get_grouped_venue_papers openreview_papers/paper.py ran no licence file found · pointer only · 019cb7a55d32fcdd · report fixture: signature client:MockClient/0/?, grouped_venue:list/1/str, only_accepted:bool/0/bool · returned dict · level recorded 2026-09-24
get_papers openreview_papers/paper.py ran no licence file found · pointer only · 449e5f6e8c9560ed · report fixture: signature client:MockClient/0/?, grouped_venues:dict/0/?, only_accepted:bool/0/bool · returned dict · level recorded 2026-09-24
load_papers openreview_papers/utils.py ran · our draft was wrong no licence file found · pointer only · a65cf511fdf4c398 · report fixture: signature fpath:str/0/str · returned dict · level recorded 2026-09-24
papers_to_list openreview_papers/utils.py ran · our draft was wrong no licence file found · pointer only · f193f2c1639e1788 · report fixture: signature papers:dict/0/? · returned list · level recorded 2026-09-24
process_file in 33 papers src/arxiv_search.py ran no licence file found · pointer only · 66ad8fb02e5834bf · report fixture: signature file_path:str/0/str, auroc_pattern:Pattern/0/?, auprc_pattern:Pattern/0/?, metadata_keys:list/1/str, remove_latex:bool/0/bool · returned tuple · level recorded 2026-09-24
process_file in 33 papers src/arxiv_search_regex.py ran no licence file found · pointer only · 5e0a79f969743a5f · report fixture: signature file_path:str/0/str, auroc_regex:Pattern/0/?, auprc_regex:Pattern/0/?, metadata_keys:list/1/str, remove_latex:bool/0/bool · returned tuple · level recorded 2026-09-24
remove_latex_commands src/arxiv_search.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a56f744d089c3d45 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
remove_latex_commands src/arxiv_search_regex.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b93ed8c955f1e9b1 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
create_keyword_pattern src/claim_search_openai.py unverified no licence file found · pointer only · af7bf864cd646a1a · report
get_context_windows src/claim_search_openai.py unverified no licence file found · pointer only · d21c640c6f69c578 · report
jsonl_folder_filtering src/arxiv_search_regex.py unverified no licence file found · pointer only · 20187fbba2f056ae · report
process_with_gpt_with_retries src/claim_search_v3.py unverified no licence file found · pointer only · 56f3d7119ff6c9c6 · report
hzhang0/auc_bias official repository 9 samples, 6 ran (3 instrument-failed) · 3 unverified
binary_metrics auc_biases/metrics.py ran no licence file found · pointer only · da3008f9c1d07696 · report fixture: signature targets:ndarray/1/int, preds:ndarray/1/int, label_set:list/1/int, suffix:str/0/str, return_arrays:bool/0/bool · returned dict · level recorded 2026-09-24
block_until_running in 6 papers command_launchers.py ran · violated contract no licence file found · pointer only · 9d4328ab806dde75 · report fixture: signature n:int/0/int, user:str/0/str · returned bool · level recorded 2026-09-22
combinations_base experiments.py ran · our draft was wrong no licence file found · pointer only · 5a9f7480b832c15a · report fixture: signature grid:dict/0/? · returned list · level recorded 2026-09-24
default_hparams in 10 papers auc_biases/hparams_registry.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5a5be97e16d42730 · report fixture: signature algorithm:str/0/str, dataset:str/0/str · returned dict · level recorded 2026-09-24
get_slurm_jobs command_launchers.py ran · honoured contract fingerprinted no licence file found · pointer only · f2059a864ab0dc16 · report fixture: signature user:str/0/str · returned tuple · level recorded 2026-09-22
random_hparams in 8 papers auc_biases/hparams_registry.py ran · our draft was wrong no licence file found · pointer only · ab9845f95d99f073 · report fixture: signature algorithm:str/0/str, dataset:str/0/str, seed:int/0/int · returned dict · level recorded 2026-09-24
add_scaler auc_biases/models.py unverified no licence file found · pointer only · 0c0d237b93f855a4 · report
combinations in 6 papers experiments.py unverified no licence file found · pointer only · f64641d62dc45aa9 · report
get_hparams in 9 papers experiments.py unverified no licence file found · pointer only · 73d0cb5bbc5c4f0c · report
Lassehhansen/ArxivMLClaimSearch found in paper text by Syntology 13 samples, 11 ran (3 instrument-failed) · 2 unverified
create_keyword_pattern src/arxiv_search.py ran · our draft was wrong MIT (permissive) · 6f934cc1b439e9f8 · report fixture: signature keywords:list/1/str · returned Pattern · level recorded 2026-09-24
extract_context_windows_df src/claim_search_v3.py ran MIT (permissive) · 79c40b375614cc13 · report fixture: signature df:DataFrame/0/?, text_column:str/0/str, compiled_regexes:list/1/Pattern, window_size:int/0/int · returned DataFrame · level recorded 2026-09-24
get_context_windows src/claim_search_openai.py ran MIT (permissive) · 3f8be895e9cf2daa · report fixture: signature text:str/0/str, keywords:list/1/str, window_size:int/0/int · returned list · level recorded 2026-09-24
get_context_windows src/claim_search_v3.py ran MIT (permissive) · 2dbdcd8611f7c89e · report fixture: signature text:str/0/str, compiled_regexes:list/1/Pattern, window_size:int/0/int · returned list · level recorded 2026-09-24
process_all_context_windows src/claim_search_v4.py ran MIT (permissive) · e06e4c3c4735ffbb · report fixture: returned DataFrame · level recorded 2026-09-24
process_file in 33 papers src/arxiv_search.py ran MIT (permissive) · c4d0403439e31706 · report fixture: signature file_path:str/0/str, auroc_pattern:Pattern/0/?, auprc_pattern:Pattern/0/?, metadata_keys:list/1/str, remove_latex:bool/0/bool · returned tuple · level recorded 2026-09-24
process_file in 33 papers src/arxiv_search_regex.py ran MIT (permissive) · 1ba401f99899baa4 · report fixture: signature file_path:str/0/str, auroc_regex:Pattern/0/?, auprc_regex:Pattern/0/?, metadata_keys:list/1/str, remove_latex:bool/0/bool · returned tuple · level recorded 2026-09-24
process_with_gpt_with_retries src/claim_search_v3.py ran MIT (permissive) · 66d9d0c1c6c5bb7d · report fixture: signature context_window:str/0/str, model:str/0/str, system_prompt:str/0/str, openai_api_key:str/0/str, max_retries:int/0/int · returned str · level recorded 2026-09-24
process_with_gpt_with_retries src/claim_search_v4.py ran MIT (permissive) · 85c492fe533d7a74 · report fixture: signature context_window:str/0/str, model:str/0/str, system_prompt:str/0/str, introduction_statement_prompt:str/0/str, end_statement_prompt:str/0/str, openai_api_key:str/0/str, max_retries:int/0/int · returned str · level recorded 2026-09-24
remove_latex_commands src/arxiv_search.py ran · our draft was wrong fingerprinted MIT (permissive) · 5c99e79304386be5 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
remove_latex_commands src/arxiv_search_regex.py ran · our draft was wrong fingerprinted MIT (permissive) · 476852e5a210420b · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
jsonl_folder_filtering src/arxiv_search_regex.py unverified MIT (permissive) · 469bb31279dee5bc · report
process_with_gpt src/claim_search_openai.py unverified MIT (permissive) · 1dfd354e2f7c0776 · report

Tasks

Binary ClassificationFairness

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections