SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.00350 · ICML · 2023

POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models

Mingyuan Zhou, Huangjie Zheng, Shujian Zhang, Korawat Tanwisuth, Pengcheng He

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 4 failures of our instrument; 5 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/2305.00350.json · badge: /api/ran/2305.00350.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
korawat-tanwisuth/POUF canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
korawat-tanwisuth/pouf marked official in Papers with Code
Papers with Code archive
1 ran · 5 no recorded run
FunctionStatusWhere it lives
compute_im_loss Ran
ran; our contract draft was wrong, not the code
korawat-tanwisuth/POUF/pouf_lvm/examples/pouf/image_classification/pouf.py
pointer only (licence: NONE) · get_code("dc531b816f4e9e50")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, korawat-tanwisuth/POUF 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.

compute_transport_loss Ran
ran; our contract draft was wrong, not the code
korawat-tanwisuth/POUF/pouf_lvm/examples/pouf/image_classification/pouf.py
pointer only (licence: NONE) · get_code("a14ceda5899bf170")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, korawat-tanwisuth/POUF 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_entropy Ran
ran; our contract draft was wrong, not the code
korawat-tanwisuth/POUF/pouf_lvm/examples/pouf/image_classification/pouf.py
pointer only (licence: NONE) · get_code("a7625322cc9fda06")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, korawat-tanwisuth/POUF 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.

select_neighbors Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
korawat-tanwisuth/pouf/pouf_mlm/src/label_search.py
pointer only (licence: NONE) · get_code("b69b1ad29fd21db5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, korawat-tanwisuth/pouf 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.

eval_pairing_acc Not yet run
unverified (harvested, no recorded run)
korawat-tanwisuth/pouf/pouf_mlm/src/label_search.py
pointer only (licence: NONE) · get_code("47923f36537f5f79")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, korawat-tanwisuth/pouf 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.

eval_pairing_corr Not yet run
unverified (harvested, no recorded run)
korawat-tanwisuth/pouf/pouf_mlm/src/label_search.py
pointer only (licence: NONE) · get_code("b879859f38d15849")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, korawat-tanwisuth/pouf 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.

find_labels Not yet run
unverified (harvested, no recorded run)
korawat-tanwisuth/pouf/pouf_mlm/src/label_search.py
pointer only (licence: NONE) · get_code("c205aef1d855cd3c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, korawat-tanwisuth/pouf 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.

init Not yet run
unverified (harvested, no recorded run)
korawat-tanwisuth/pouf/pouf_mlm/src/label_search.py
pointer only (licence: NONE) · get_code("5fabcb6bbd28aa2f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, korawat-tanwisuth/pouf 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.

select_likely_words Not yet run
unverified (harvested, no recorded run)
korawat-tanwisuth/pouf/pouf_mlm/src/label_search.py
pointer only (licence: NONE) · get_code("be6b57168b0424f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, korawat-tanwisuth/pouf 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, 3 are also present in other papers whose code we hold (3 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.

FunctionAlso present inEarliest-datedOthers named
eval_pairing_acc
brick of this paper's assembly: metric
2 other papers
2 dated earlier
2110.06274 (2021-10)
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners
2205.01308 (2022-05)
Contrastive Learning for Prompt-Based Few-Shot Language Learners
select_likely_words
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2110.06274 (2021-10)
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners
2205.01308 (2022-05)
Contrastive Learning for Prompt-Based Few-Shot Language Learners
select_neighbors
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2110.06274 (2021-10)
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners
2205.01308 (2022-05)
Contrastive Learning for Prompt-Based Few-Shot Language Learners

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

Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot capabilities, in general, labeled data are still required to adapt them to downstream tasks. To overcome this critical limitation, we propose an unsupervised fine-tuning framework to directly fine-tune the model or prompt on the unlabeled target data. We demonstrate how to apply our method to both language-augmented vision and masked-language models by aligning the discrete distributions extracted from the prompts and target data. To verify our approach's applicability, we conduct extensive experiments on image classification, sentiment analysis, and natural language inference tasks. Across 13 image-related tasks and 15 languagerelated ones, the proposed approach achieves consistent improvements over the baselines. PyTorch code is available at https://github.com/ korawat-tanwisuth/POUF.

For agents

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

get_harvested_code_for_paper("2305.00350")
get_code_for_paper("2305.00350")
have("2305.00350")

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

curl https://syntology.ai/api/ran/2305.00350.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.00350.svg)](https://syntology.ai/paper/2305.00350)

Connect an agent — have() is free.