SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.03955 · 2020

Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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; 5 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 2 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/2006.03955.json · badge: /api/ran/2006.03955.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
weiguowilliam/CEAT canonical (classifier label)
classifier basis: classifier_2025
6 ran · 0 no recorded run
groovychoons/GlobalBias community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
associate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
weiguowilliam/CEAT/code/ceat.py
pointer only (licence: NONE) · get_code("9e4c0649a2c023c5")
How it ran

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

create_input Ran
ran on a synthesized input
groovychoons/GlobalBias/code/0_build_globalbias.py
code served (permissive licence) · get_code("30e23b25e68353f5")
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 str. 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 torch

torch.manual_seed(0)

row = {
    'firstname': 'Alice'
}

ARGS = {
    'row': row,
    'template_number': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 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
create_template Ran
ran on a synthesized input
groovychoons/GlobalBias/code/0_build_globalbias.py
code served (permissive licence) · get_code("c81d826bf783431f")
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 str. 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 torch

torch.manual_seed(0)

# Create a minimal row dict with the required keys
row = {
    'firstname': 'Alice',
    'partial_1': 'am learning Python',
    'partial_2': 'is a programmer',
    'partial_3': 'enjoys coding'
}

ARGS = {
    'row': row,
    'template_number': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 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
difference Ran
ran, honoured the contract we drafted
weiguowilliam/CEAT/code/ceat.py
pointer only (licence: NONE) · get_code("aaaba9612fb1366d")
How it ran

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

effect_size Ran
ran, honoured the contract we drafted
weiguowilliam/CEAT/code/ceat.py
pointer only (licence: NONE) · get_code("5f710f0507c571ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weiguowilliam/CEAT 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_effectsize Ran
ran, honoured the contract we drafted
weiguowilliam/CEAT/code/ibd.py
pointer only (licence: NONE) · get_code("3068f02dfd82fdac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weiguowilliam/CEAT 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_mtx Ran
ran, honoured the contract we drafted
weiguowilliam/CEAT/code/ibd.py
pointer only (licence: NONE) · get_code("f48b1f5b3b2f5ec3")
How it ran

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

inner_ibd Ran
ran, honoured the contract we drafted
weiguowilliam/CEAT/code/ibd.py
pointer only (licence: NONE) · get_code("5887833d6f7bd203")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weiguowilliam/CEAT 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_encdec_perplexity Not yet run
unverified (harvested, no recorded run)
groovychoons/GlobalBias/code/5_perplexity_script.py
code served (permissive licence) · get_code("a30a6e35725f3df9")
How it ran

no invocation recorded.

get_perplexity Not yet run
unverified (harvested, no recorded run)
groovychoons/GlobalBias/code/5_perplexity_script.py
code served (permissive licence) · get_code("f9bb0b820898e338")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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

With the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. State-of-the-art neural language models generate dynamic word embeddings dependent on the context in which the word appears. Current methods measure pre-defined social and intersectional biases that appear in particular contexts defined by sentence templates. Dispensing with templates, we introduce the Contextualized Embedding Association Test (CEAT), that can summarize the magnitude of overall bias in neural language models by incorporating a random-effects model. Experiments on social and intersectional biases show that CEAT finds evidence of all tested biases and provides comprehensive information on the variance of effect magnitudes of the same bias in different contexts. All the models trained on English corpora that we study contain biased representations. Furthermore, we develop two methods, Intersectional Bias Detection (IBD) and Emergent Intersectional Bias Detection (EIBD), to automatically identify the intersectional biases and emergent intersectional biases from static word embeddings in addition to measuring them in contextualized word embeddings. We present the first algorithmic bias detection findings on how intersectional group members are strongly associated with unique emergent biases that do not overlap with the biases of their constituent minority identities. IBD and EIBD achieve high accuracy when detecting the intersectional and emergent biases of African American females and Mexican American females. Our results indicate that biases at the intersection of race and gender associated with members of multiple minority groups, such as African American females and Mexican American females, have the highest magnitude across all neural language models.

For agents

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

get_harvested_code_for_paper("2006.03955")
get_code_for_paper("2006.03955")
have("2006.03955")

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

curl https://syntology.ai/api/ran/2006.03955.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.03955.svg)](https://syntology.ai/paper/2006.03955)

Connect an agent — have() is free.