SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.01931 · ACL · 2024

VARIERR NLI: Separating Annotation Error from Human Label Variation

Barbara Plank, Siyao Peng, Marie-Catherine De Marneffe, Leon Weber-Genzel

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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; 5 failures of our instrument; 4 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/2403.01931.json · badge: /api/ran/2403.01931.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
mainlp/VariErr-NLI canonical (classifier label)
classifier basis: census
5 ran · 4 no recorded run
FunctionStatusWhere it lives
compute_metrics Ran
ran; our contract draft was wrong, not the code
mainlp/VariErr-NLI/build_score_table.py
pointer only (licence: NONE) · get_code("81217cf08fe12d42")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mainlp/VariErr-NLI 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_reason_to_score Ran
ran; our contract draft was wrong, not the code
mainlp/VariErr-NLI/predict_llms.py
pointer only (licence: NONE) · get_code("dca3f599335ed6d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mainlp/VariErr-NLI 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.

instance_to_starting_prompt Ran
ran; our contract draft was wrong, not the code
mainlp/VariErr-NLI/eval_llms.py
pointer only (licence: NONE) · get_code("1726b2eaa67e19ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mainlp/VariErr-NLI 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.

precision_at_k Ran
ran; our contract draft was wrong, not the code
mainlp/VariErr-NLI/build_score_table.py
pointer only (licence: NONE) · get_code("04aa42119c9d143f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mainlp/VariErr-NLI 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.

recall_at_k Ran
ran; our contract draft was wrong, not the code
mainlp/VariErr-NLI/build_score_table.py
pointer only (licence: NONE) · get_code("d72b6a140ff417e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mainlp/VariErr-NLI 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.

aggregate_scores Not yet run
unverified (harvested, no recorded run)
mainlp/VariErr-NLI/predict_llms.py
pointer only (licence: NONE) · get_code("184bba6c793855a8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mainlp/VariErr-NLI 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_logits_per_epoch Not yet run
unverified (harvested, no recorded run)
mainlp/VariErr-NLI/predict_scorers.py
pointer only (licence: NONE) · get_code("f1ddd1d063b9b7a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mainlp/VariErr-NLI 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_probs_per_epoch Not yet run
unverified (harvested, no recorded run)
mainlp/VariErr-NLI/predict_scorers.py
pointer only (licence: NONE) · get_code("1e7a15f18668ad1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mainlp/VariErr-NLI 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.

predict_datamap_means Not yet run
unverified (harvested, no recorded run)
mainlp/VariErr-NLI/predict_scorers.py
pointer only (licence: NONE) · get_code("f5c93c97adfd0c96")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mainlp/VariErr-NLI 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Human label variation arises when annotators assign different labels to the same item for valid reasons, while annotation errors occur when labels are assigned for invalid reasons. These two issues are prevalent in NLP benchmarks, yet existing research has studied them in isolation. To the best of our knowledge, there exists no prior work that focuses on teasing apart error from signal, especially in cases where signal is beyond black-and-white. To fill this gap, we introduce a systematic methodology and a new dataset, VARIERR (variation versus error), focusing on the NLI task in English. We propose a 2-round annotation procedure with annotators explaining each label and subsequently judging the validity of label-explanation pairs. VARIERR contains 7,732 validity judgments on 1,933 explanations for 500 re-annotated MNLI items. We assess the effectiveness of various automatic error detection (AED) methods and GPTs in uncovering errors versus human label variation. We find that state-of-the-art AED methods significantly underperform GPTs and humans. While GPT-4 is the best system, it still falls short of human performance. Our methodology is applicable beyond NLI, offering fertile ground for future research on error versus plausible variation, which in turn can yield better and more trustworthy NLP systems.

For agents

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

get_harvested_code_for_paper("2403.01931")
get_code_for_paper("2403.01931")
have("2403.01931")

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

curl https://syntology.ai/api/ran/2403.01931.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.01931.svg)](https://syntology.ai/paper/2403.01931)

Connect an agent — have() is free.