SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.08461 · NeurIPS · 2024

OTTER: Effortless Label Distribution Adaptation of Zero-shot Models

Frederic Sala, Changho Shin, Harit Vishwakarma, Sonia Cromp, Jitian Zhao

arXiv · PDF · Open in the Atlas

Code that ran

6 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2404.08461.json · badge: /api/ran/2404.08461.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
SprocketLab/OTTER canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
sprocketlab/otter canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
get_dirichlet_marginal Ran
ran; our contract draft was wrong, not the code
SprocketLab/OTTER/src/label_shift_utils.py
pointer only (licence: NONE) · get_code("1cfa2c1ff434c8e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SprocketLab/OTTER 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_pred_proba Ran
ran, honoured the contract we drafted
sprocketlab/otter/src/inference.py
pointer only (licence: NONE) · get_code("906d7af106469e1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sprocketlab/otter 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_uniformly_resampled_indices Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SprocketLab/OTTER/src/label_shift_utils.py
pointer only (licence: NONE) · get_code("cc97ef5fea3909c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SprocketLab/OTTER 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_uniformly_resampled_indices_split Ran
ran; our contract draft was wrong, not the code
SprocketLab/OTTER/src/label_shift_utils.py
pointer only (licence: NONE) · get_code("9a9b5fe4892aeffb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SprocketLab/OTTER 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.

nlh_cost_matrix Ran
ran, honoured the contract we drafted
sprocketlab/otter/src/inference.py
pointer only (licence: NONE) · get_code("4392943c8aa127bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sprocketlab/otter 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.

zs_predict Ran
ran, honoured the contract we drafted
sprocketlab/otter/src/inference.py
pointer only (licence: NONE) · get_code("9edefb19aec9bef9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sprocketlab/otter 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.

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, 1 are also present in other papers whose code we hold (1 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.

FunctionAlso present inEarliest-datedOthers named
get_dirichlet_marginal 1 other paper
1 dated earlier
2302.03020 (2023-02)
RLSbench: Domain Adaptation Under Relaxed Label Shift

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

Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the label distribution are not suitable in zero-shot settings, as they have mismatching requirements, such as needing access to labeled downstream task data or knowledge of the true label balance in the pretraining distribution. We sidestep these challenges and introduce a simple and lightweight approach to adjust pretrained model predictions via optimal transport. Our technique requires only an estimate of the label distribution of a downstream task. Theoretically, we characterize the improvement produced by our procedure under certain mild conditions and provide bounds on the error caused by misspecification. Empirically, we validate our method in a wide array of zero-shot image and text classification tasks, improving accuracy by 4.8% and 15.9% on average, and beating baselines like prior matching-often by significant margins-in 17 out of 21 datasets.

For agents

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

get_harvested_code_for_paper("2404.08461")
get_code_for_paper("2404.08461")
have("2404.08461")

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

curl https://syntology.ai/api/ran/2404.08461.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.08461.svg)](https://syntology.ai/paper/2404.08461)

Connect an agent — have() is free.