SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.02812 · EMNLP · 2020

Intrinsic Probing through Dimension Selection

Ryan Cotterell, Adina Williams, Lucas Hennigen

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 1 has no contract verdict; 1 failure 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/2010.02812.json · badge: /api/ran/2010.02812.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
rycolab/intrinsic-probing canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
load_dimensions_to_features Ran
ran on a synthesized input
rycolab/intrinsic-probing/readers/base.py
code served (permissive licence) · get_code("45171eb33f2a4c30")
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 dict. 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 yaml
import tempfile
import os

# Create a temporary YAML file with the expected structure
temp_dir = tempfile.mkdtemp()
tags_file = os.path.join(temp_dir, "tags.yaml")

# Write a minimal valid YAML file matching the expected structure
yaml_content = {
    'categories': {
        'POS': ['NOUN', 'VERB', 'ADJ'],
        'TENSE': ['PAST', 'PRESENT', 'FUTURE'],
        'MOOD': ['IND', 'SUBJ']
    }
}

with open(tags_file, 'w') as f:
    yaml.dump(yaml_content, f)

ARGS = {
    'tags_path': tags_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
merge_attributes Ran
ran; our contract draft was wrong, not the code
rycolab/intrinsic-probing/preprocess_treebank.py
code served (permissive licence) · get_code("880da7cfdc10270d")
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 dict. 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
import numpy as np
from typing import List, Dict

# Create sample tokens with 'um_feats' dictionaries
tokens = [
    {'um_feats': {'TENSE': 'PST', 'MOOD': 'IND', 'PERSON': '3'}},
    {'um_feats': {'TENSE': 'PST', 'MOOD': 'IND'}},
    {'um_feats': {'NUMBER': 'SG', 'CASE': 'NOM'}},
]

# Create a value_to_attr_dict mapping (required by function signature but not used in body)
value_to_attr_dict = {
    'PST': 'TENSE',
    'IND': 'MOOD',
    '3': 'PERSON',
    'SG': 'NUMBER',
    'NOM': 'CASE',
}

ARGS = {
    'tokens': tokens,
    'value_to_attr_dict': value_to_attr_dict,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
subword_tokenize Not yet run
unverified (harvested, no recorded run)
rycolab/intrinsic-probing/preprocess_treebank.py
code served (permissive licence) · get_code("ac4580febeecca9d")
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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
merge_attributes 1 other paper
1 later
2310.15513 (2023-10)
A Joint Matrix Factorization Analysis of Multilingual Representations

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

Most modern NLP systems make use of pretrained contextual representations that attain astonishingly high performance on a variety of tasks. Such high performance should not be possible unless some form of linguistic structure inheres in these representations, and a wealth of research has sprung up on probing for it. In this paper, we draw a distinction between intrinsic probing, which examines how linguistic information is structured within a representation, and the extrinsic probing popular in prior work, which only argues for the presence of such information by showing that it can be successfully extracted. To enable intrinsic probing, we propose a novel framework based on a decomposable multivariate Gaussian probe that allows us to determine whether the linguistic information in word embeddings is dispersed or focal. We then probe fastText and BERT for various morphosyntactic attributes across 36 languages. We find that most attributes are reliably encoded by only a few neurons, with fastText concentrating its linguistic structure more than BERT. 1

For agents

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

get_harvested_code_for_paper("2010.02812")
get_code_for_paper("2010.02812")
have("2010.02812")

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

curl https://syntology.ai/api/ran/2010.02812.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.02812.svg)](https://syntology.ai/paper/2010.02812)

Connect an agent — have() is free.