SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.15744 · EMNLP · 2024

On the Fragility of Active Learners for Text Classification

Abhishek Ghose, Emma Nguyen

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 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, 1 violated it and 0 have no contract verdict; 9 failures of our instrument; 5 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/2403.15744.json · badge: /api/ran/2403.15744.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
ThuongTNguyen/ALchemist canonical (classifier label)
classifier basis: census
10 ran · 5 no recorded run
FunctionStatusWhere it lives
flatten_param_grid Ran
ran; our contract draft was wrong, not the code
ThuongTNguyen/ALchemist/core/model_selection.py
pointer only (licence: NONE) · get_code("a21592fe7dca71e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ThuongTNguyen/ALchemist 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_formatter Ran
ran; our contract draft was wrong, not the code
ThuongTNguyen/ALchemist/run_expts_nonBERT.py
pointer only (licence: NONE) · get_code("bfc0d8240d6b72ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ThuongTNguyen/ALchemist 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_plot_template Ran
ran; our contract draft was wrong, not the code
ThuongTNguyen/ALchemist/results_utils.py
pointer only (licence: NONE) · get_code("cb6c23a57e56be7a")
How it ran

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

is_al_file_complete Ran
ran, violated the contract we drafted
ThuongTNguyen/ALchemist/run_expts_nonBERT.py
pointer only (licence: NONE) · get_code("14356eed8e0fc4e9")
How it ran

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

load_dataset Ran
ran; our contract draft was wrong, not the code
ThuongTNguyen/ALchemist/run_expts_nonBERT.py
pointer only (licence: NONE) · get_code("b83afb52b80f22d6")
How it ran

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

move_elements Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ThuongTNguyen/ALchemist/core/al.py
pointer only (licence: NONE) · get_code("de3bfb9775413c1b")
How it ran

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

multiple_splits Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ThuongTNguyen/ALchemist/core/data_utils.py
pointer only (licence: NONE) · get_code("32f6c8de16c55c70")
How it ran

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

prepare_train_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ThuongTNguyen/ALchemist/core/hf_model_selection.py
pointer only (licence: NONE) · get_code("3f9f2d92317ece14")
How it ran

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

rel_improv_plot_template Ran
ran; our contract draft was wrong, not the code
ThuongTNguyen/ALchemist/results_utils.py
pointer only (licence: NONE) · get_code("37086e0324c9aa23")
How it ran

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

tokenize_text Ran
ran; our contract draft was wrong, not the code
ThuongTNguyen/ALchemist/core/hf_model_selection.py
pointer only (licence: NONE) · get_code("9f8877b9d156b548")
How it ran

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

avg_friedman Not yet run
unverified (harvested, no recorded run)
ThuongTNguyen/ALchemist/process_results.py
pointer only (licence: NONE) · get_code("d80a8704bae88de7")
How it ran

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

collate_data Not yet run
unverified (harvested, no recorded run)
ThuongTNguyen/ALchemist/process_results.py
pointer only (licence: NONE) · get_code("1a0572c9c271a498")
How it ran

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

dirname_parse Not yet run
unverified (harvested, no recorded run)
ThuongTNguyen/ALchemist/process_results.py
pointer only (licence: NONE) · get_code("9d75a3f4c68b30a6")
How it ran

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

load_data Not yet run
unverified (harvested, no recorded run)
ThuongTNguyen/ALchemist/core/data_utils.py
pointer only (licence: NONE) · get_code("cbc9a2d7314e9cf1")
How it ran

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

select_model Not yet run
unverified (harvested, no recorded run)
ThuongTNguyen/ALchemist/core/model_selection.py
pointer only (licence: NONE) · get_code("142b553f00dd3941")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ThuongTNguyen/ALchemist 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 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 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 15 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

Active learning (AL) techniques optimally utilize a labeling budget by iteratively selecting instances that are most valuable for learning. However, they lack "prerequisite checks", i.e., there are no prescribed criteria to pick an AL algorithm best suited for a dataset. A practitioner must pick a technique they trust would beat random sampling, based on prior reported results, and hope that it is resilient to the many variables in their environment: dataset, labeling budget and prediction pipelines. The important questions then are: how often on average, do we expect any AL technique to reliably beat the computationally cheap and easy-to-implement strategy of random sampling? Does it at least make sense to use AL in an "Always ON" mode in a prediction pipeline, so that while it might not always help, it never under-performs random sampling? How much of a role does the prediction pipeline play in AL's success? We examine these questions in detail for the task of text classification using pre-trained representations, which are ubiquitous today. Our primary contribution here is a rigorous evaluation of AL techniques, old and new, across setups that vary wrt datasets, text representations and classifiers. This unlocks multiple insights around warm-up times, i.e., number of labels before gains from AL are seen, viability of an "Always ON" mode and the relative significance of different factors. Additionally, we release a framework for rigorous benchmarking of AL techniques for text classification.

For agents

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

get_harvested_code_for_paper("2403.15744")
get_code_for_paper("2403.15744")
have("2403.15744")

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

curl https://syntology.ai/api/ran/2403.15744.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.15744.svg)](https://syntology.ai/paper/2403.15744)

Connect an agent — have() is free.