SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.03010 · EMNLP Findings · 2020

Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming

Allyson Ettinger, Kanishka Misra, Julia Rayz

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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 2 have no contract verdict; 0 failures of our instrument; 1 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/2010.03010.json · badge: /api/ran/2010.03010.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
kanishkamisra/emnlp-bert-priming canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
batch_encode Ran
ran on a synthesized input
kanishkamisra/emnlp-bert-priming/python/minicons.py
code served (permissive licence) · get_code("62d2007ba63b3c6c")
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 tuple, ndim 3, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

class MockTokenizer:
    def batch_encode_plus(self, sentences, add_special_tokens=False, pad_to_max_length=True):
        # Return a dict with 'input_ids' and 'attention_mask' keys
        batch_size = len(sentences)
        max_length = 4
        return {
            'input_ids': [[101, 2054, 2003, 102] for _ in range(batch_size)],
            'attention_mask': [[1, 1, 1, 1] for _ in range(batch_size)]
        }

sentences = [
    "Hello world",
    "How are you"
]

tokenizer = MockTokenizer()

device = "cpu"

ARGS = {
    "sentences": sentences,
    "tokenizer": tokenizer,
    "device": device
}
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 tuple, ndim 3, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
mask Ran
ran on a synthesized input
kanishkamisra/emnlp-bert-priming/python/minicons.py
code served (permissive licence) · get_code("1e1fd66009b2b4d8")
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 re

def mask(sentence: str, word: str) -> str:
    replaced = re.sub(f'(?<![\\w\\/-])({word})(?=[^\\w\\/-])', '[MASK]', sentence)
    masked = ['[CLS]'] + [replaced] + ['[SEP]']
    return ' '.join(masked)

ARGS = {
    'sentence': 'The quick brown fox jumps over the lazy dog',
    'word': 'quick'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
calculate_entropy Not yet run
unverified (harvested, no recorded run)
kanishkamisra/emnlp-bert-priming/python/entropy_constraint.py
code served (permissive licence) · get_code("0f24935725a6bbf1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Models trained to estimate word probabilities in context have become ubiquitous in natural language processing. How do these models use lexical cues in context to inform their word probabilities? To answer this question, we present a case study analyzing the pre-trained BERT model with tests informed by semantic priming. Using English lexical stimuli that show priming in humans, we find that BERT too shows "priming," predicting a word with greater probability when the context includes a related word versus an unrelated one. This effect decreases as the amount of information provided by the context increases. Followup analysis shows BERT to be increasingly distracted by related prime words as context becomes more informative, assigning lower probabilities to related words. Our findings highlight the importance of considering contextual constraint effects when studying word prediction in these models, and highlight possible parallels with human processing.

For agents

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

get_harvested_code_for_paper("2010.03010")
get_code_for_paper("2010.03010")
have("2010.03010")

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

curl https://syntology.ai/api/ran/2010.03010.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.03010.svg)](https://syntology.ai/paper/2010.03010)

Connect an agent — have() is free.