SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.07364 · EMNLP · 2020

An information theoretic view on selecting linguistic probes

Frank Rudzicz, Zining Zhu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 no recorded run), measured 2026-11-22; 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/2009.07364.json · badge: /api/ran/2009.07364.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
SPOClab-ca/InfoProbe canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
run_eval Ran
ran on a synthesized input
SPOClab-ca/InfoProbe/src/pos_probe.py
code served (permissive licence) · get_code("f8435c21eef9039f")
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 1, dtype family float; 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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Create a small probe model
class SimpleProbe(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

probe = SimpleProbe()

# Create a simple dataloader stand-in that tracks iteration state
class SimpleDataLoader:
    def __init__(self, data):
        self.data = data
        self.index = 0
    
    def has_next(self):
        return self.index < len(self.data)
    
    def next(self):
        if self.index >= len(self.data):
            return None, None
        x, y = self.data[self.index]
        self.index += 1
        return x, y
    
    def reset(self):
        self.index = 0

# Create small batch data: batch size 2, input dim 4, num classes 3
x_batch1 = torch.randn(2, 4)
y_batch1 = torch.tensor([0, 2])

x_batch2 = torch.randn(2, 4)
y_batch2 = torch.tensor([1, 0])

# Create dataloader with two batches
data = [(x_batch1, y_batch1), (x_batch2, y_batch2)]
dataloader = SimpleDataLoader(data)

ARGS = {
    "probe": probe,
    "dataloader": dataloader
}
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 tuple, ndim 1, dtype family float — 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 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.

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

There is increasing interest in assessing the linguistic knowledge encoded in neural representations. A popular approach is to attach a diagnostic classifier -or "probe" -to perform supervised classification from internal representations. However, how to select a good probe is in debate. Hewitt and Liang (2019) showed that a high performance on diagnostic classification itself is insufficient, because it can be attributed to either "the representation being rich in knowledge", or "the probe learning the task", which Pimentel et al. ( 2020) challenged. We show this dichotomy is valid informationtheoretically. In addition, we find that the methods to construct and select good probes proposed by the two papers, control task (Hewitt and Liang, 2019) and control function (Pimentel et al., 2020), are equivalent -the errors of their approaches are identical (modulo irrelevant terms). Empirically, these two selection criteria lead to results that highly agree with each other.

For agents

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

get_harvested_code_for_paper("2009.07364")
get_code_for_paper("2009.07364")
have("2009.07364")

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

curl https://syntology.ai/api/ran/2009.07364.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.07364.svg)](https://syntology.ai/paper/2009.07364)

Connect an agent — have() is free.