SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.12298 · EMNLP · 2020

Information-Theoretic Probing with Minimum Description Length

Ivan Titov, Elena Voita

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 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; 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/2003.12298.json · badge: /api/ran/2003.12298.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
lena-voita/description-length-probing marked official in Papers with Code
Papers with Code archive
2 ran · 2 no recorded run
willwhitney/reprieve community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Probe Ran
ran on a synthesized input
lena-voita/description-length-probing/control_tasks/control_tasks/probe.py
pointer only (licence: NONE) · get_code("f5f58450c18992a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lena-voita/description-length-probing 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.

reparametrize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lena-voita/description-length-probing/control_tasks/control_tasks/probe.py
pointer only (licence: NONE) · get_code("2466d861eece0826")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lena-voita/description-length-probing 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.

LinearGroupNJ Not yet run
unverified (harvested, no recorded run)
lena-voita/description-length-probing/control_tasks/control_tasks/probe.py
pointer only (licence: NONE) · get_code("850fa1698390a72a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lena-voita/description-length-probing 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.

LossDataEstimator Not yet run
unverified (harvested, no recorded run)
willwhitney/reprieve/reprieve/api.py
pointer only (licence: NONE) · get_code("0e3860a096fe4f95")
How it ran

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

OneWordNNLabelProbeBayesCompression Not yet run
unverified (harvested, no recorded run)
lena-voita/description-length-probing/control_tasks/control_tasks/probe.py
pointer only (licence: NONE) · get_code("2d967d1afb007373")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lena-voita/description-length-probing 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 4 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
reparametrize
brick of this paper's assembly: helper
1 other paper
1 later
2023.findings-emnlp.879 (2023 (year only))
Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training

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

To measure how well pretrained representations encode some linguistic property, it is common to use accuracy of a probe, i.e. a classifier trained to predict the property from the representations. Despite widespread adoption of probes, differences in their accuracy fail to adequately reflect differences in representations. For example, they do not substantially favour pretrained representations over randomly initialized ones. Analogously, their accuracy can be similar when probing for genuine linguistic labels and probing for random synthetic tasks. To see reasonable differences in accuracy with respect to these random baselines, previous work had to constrain either the amount of probe training data or its model size. Instead, we propose an alternative to the standard probes, information-theoretic probing with minimum description length (MDL). With MDL probing, training a probe to predict labels is recast as teaching it to effectively transmit the data. Therefore, the measure of interest changes from probe accuracy to the description length of labels given representations. In addition to probe quality, the description length evaluates 'the amount of effort' needed to achieve the quality. This amount of effort characterizes either (i) size of a probing model, or (ii) the amount of data needed to achieve the high quality. We consider two methods for estimating MDL which can be easily implemented on top of the standard probing pipelines: variational coding and online coding. We show that these methods agree in results and are more informative and stable than the standard probes. 1

For agents

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

get_harvested_code_for_paper("2003.12298")
get_code_for_paper("2003.12298")
have("2003.12298")

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

curl https://syntology.ai/api/ran/2003.12298.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.12298.svg)](https://syntology.ai/paper/2003.12298)

Connect an agent — have() is free.