SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.00948 · ACL · 2021

Unsupervised Out-of-Domain Detection via Pre-trained Transformers

Caiming Xiong, Yihao Feng, Tongzheng Ren, Shikun Zhang, Keyang Xu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 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 1 has no contract verdict; 0 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/2106.00948.json · badge: /api/ran/2106.00948.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
rivercold/BERT-unsupervised-OOD canonical (classifier label)
classifier basis: census
1 ran · 3 no recorded run
FunctionStatusWhere it lives
load_dataset Ran
ran on a synthesized input
rivercold/BERT-unsupervised-OOD/ood_main.py
code served (permissive licence) · get_code("23ff5786b5b41648")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataFrame. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import json
import pandas as pd
import tempfile
import os

# Create a temporary directory and JSON file for the dataset
temp_dir = tempfile.mkdtemp()
dataset_dir = os.path.join(temp_dir, 'dataset', 'CLINIC150')
os.makedirs(dataset_dir, exist_ok=True)

# Create sample data matching the expected structure
sample_data = {
    'intent_class': [
        {'text': 'hello world', 'labels': 0},
        {'text': 'goodbye world', 'labels': 1}
    ]
}

json_path = os.path.join(dataset_dir, 'data_full.json')
with open(json_path, 'w') as f:
    json.dump(sample_data, f)

# Change working directory to temp_dir so relative path works
original_cwd = os.getcwd()
os.chdir(temp_dir)

ARGS = {
    'data_name': 'domain_intent_class',
    'data_type': 'full'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_metric Not yet run
unverified (harvested, no recorded run)
rivercold/BERT-unsupervised-OOD/calculate_log.py
pointer only (licence: MIT); the stored copy get_code serves, from VectorInstitute/gram-ood-detection, is pointer only (licence: NONE) · get_code("160824dee7076cd5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from VectorInstitute/gram-ood-detection, and GitHub detected no licence in that repository 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_curve Not yet run
unverified (harvested, no recorded run)
rivercold/BERT-unsupervised-OOD/calculate_log.py
pointer only (licence: MIT); the stored copy get_code serves, from VectorInstitute/gram-ood-detection, is pointer only (licence: NONE) · get_code("749638f4131be5e5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from VectorInstitute/gram-ood-detection, and GitHub detected no licence in that repository 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.

metric Not yet run
unverified (harvested, no recorded run)
rivercold/BERT-unsupervised-OOD/calculate_log.py
pointer only (licence: MIT); the stored copy get_code serves, from VectorInstitute/gram-ood-detection, is pointer only (licence: NONE) · get_code("511013ffe412491c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from VectorInstitute/gram-ood-detection, and GitHub detected no licence in that repository 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 1 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
metric 2 other papers
2 dated earlier
1912.12510 (2019-12)
Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
2105.14399 (2021-05)
Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss
compute_metric 1 other paper
1 dated earlier
1912.12510 (2019-12)
Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
get_curve 1 other paper
1 dated earlier
1912.12510 (2019-12)
Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices

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

Deployed real-world machine learning applications are often subject to uncontrolled and even potentially malicious inputs. Those outof-domain inputs can lead to unpredictable outputs and sometimes catastrophic safety issues. Prior studies on out-of-domain detection require in-domain task labels and are limited to supervised classification scenarios. Our work tackles the problem of detecting out-ofdomain samples with only unsupervised indomain data. We utilize the latent representations of pre-trained transformers and propose a simple yet effective method to transform features across all layers to construct outof-domain detectors efficiently. Two domainspecific fine-tuning approaches are further proposed to boost detection accuracy. Our empirical evaluations of related methods on two datasets validate that our method greatly improves out-of-domain detection ability in a more general scenario. 1

For agents

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

get_harvested_code_for_paper("2106.00948")
get_code_for_paper("2106.00948")
have("2106.00948")

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

curl https://syntology.ai/api/ran/2106.00948.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.00948.svg)](https://syntology.ai/paper/2106.00948)

Connect an agent — have() is free.