SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.06130 · ACL · 2022

Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models

Kabir Ahuja, Monojit Choudhury, Sandipan Dandapat, Shanu Kumar

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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 5 have no contract verdict; 0 failures of our instrument; 3 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/2205.06130.json · badge: /api/ran/2205.06130.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
hichamjanati/mutar canonical (classifier label)
classifier basis not recorded on the link
5 ran · 3 no recorded run
FunctionStatusWhere it lives
groundmetric Ran
ran on a synthesized input
hichamjanati/mutar/mutar/utils.py
code served (permissive licence) · get_code("9ef314913156dc20")
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 ndarray, ndim 2, dtype family float, shape (4, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

ARGS = {
    "width": 5,
    "height": 4,
    "p": 2,
    "normed": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 5) — shape (4, 5) as a later run recorded it
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
groundmetric_img Ran
ran on a synthesized input
hichamjanati/mutar/mutar/utils.py
code served (permissive licence) · get_code("8765de0d7fb7f39f")
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 ndarray, ndim 2, dtype family float, shape (4, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

ARGS = {
    "width": 5,
    "height": 4,
    "p": 2,
    "normed": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 5) — shape (4, 5) as a later run recorded it
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
solver_lasso Ran
ran on a synthesized input
hichamjanati/mutar/mutar/solvers.py
code served (permissive licence) · get_code("1931d3414a66c16b")
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 ndarray, ndim 2, dtype family float, shape (4, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np
from sklearn.linear_model import Lasso

# Set random seed for reproducibility
np.random.seed(0)

# Create small test data
n_tasks = 2
n_samples = 5
n_features = 4

# X shape: (n_tasks, n_samples, n_features)
X = np.random.randn(n_tasks, n_samples, n_features)

# y shape: (n_tasks, n_samples)
y = np.random.randn(n_tasks, n_samples)

# Define alpha - one regularization parameter per task
alpha = np.array([0.1, 0.2])

ARGS = {
    "X": X,
    "y": y,
    "alpha": alpha,
    "max_iter": 3000,
    "tol": 0.0001,
    "positive": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 2) — shape (4, 2) as a later run recorded it
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
solver_mll Ran
ran on a synthesized input
hichamjanati/mutar/mutar/solvers.py
code served (permissive licence) · get_code("2cdbb52c4b3faccc")
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. 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 numpy as np
from sklearn.linear_model import Lasso
from sklearn.exceptions import ConvergenceWarning

np.random.seed(0)

# Construct arguments for solver_mll
# X: shape (n_tasks, n_samples, n_features)
# y: shape (n_tasks, n_samples)
# C: shape (n_features,)
# S: shape (n_features, n_tasks)

n_tasks = 2
n_samples = 3
n_features = 4

X = np.random.randn(n_tasks, n_samples, n_features)
y = np.random.randn(n_tasks, n_samples)
C = np.random.randn(n_features)
S = np.random.randn(n_features, n_tasks)

ARGS = {
    'X': X,
    'y': y,
    'C': C,
    'S': S,
    'alpha': 0.1,
    'max_iter': 1000,
    'tol': 0.0001,
    'positive': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
wklobjective_converged Ran
ran on a synthesized input
hichamjanati/mutar/mutar/otfunctions.py
code served (permissive licence) · get_code("70e5e8fff27f3426")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Analyzing the function:
# - qsum: appears to be a scalar or tensor used in arithmetic
# - f0: appears to be a scalar or tensor used in arithmetic
# - plansum: appears to be a scalar or tensor used in arithmetic
# - epsilon: appears to be a scalar used in arithmetic
# - gamma: appears to be a scalar used in arithmetic
# All parameters are combined with basic arithmetic operations (+, -, *)

# Create small scalar tensors or floats for the parameters
qsum = torch.tensor(2.5)
f0 = torch.tensor(1.3)
plansum = torch.tensor(3.7)
epsilon = 0.1
gamma = 0.2

ARGS = {
    "qsum": qsum,
    "f0": f0,
    "plansum": plansum,
    "epsilon": epsilon,
    "gamma": gamma,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
barycenterkl Not yet run
unverified (harvested, no recorded run)
hichamjanati/mutar/mutar/otfunctions.py
code served (permissive licence) · get_code("2225290e7d8cc429")
How it ran

no invocation recorded.

barycenterkl_log Not yet run
unverified (harvested, no recorded run)
hichamjanati/mutar/mutar/otfunctions.py
code served (permissive licence) · get_code("441152b0bb6e215a")
How it ran

no invocation recorded.

residual Not yet run
unverified (harvested, no recorded run)
hichamjanati/mutar/mutar/utils.py
code served (permissive licence) · get_code("b4a8a1feba8a0ec5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from language to language depending on the pivot language(s) used for fine-tuning. In this work, we build upon some of the existing techniques for predicting the zero-shot performance on a task, by modeling it as a multi-task learning problem. We jointly train predictive models for different tasks which helps us build more accurate predictors for tasks where we have test data in very few languages to measure the actual performance of the model. Our approach also lends us the ability to perform a much more robust feature selection, and identify a common set of features that influence zero-shot performance across a variety of tasks.

For agents

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

get_harvested_code_for_paper("2205.06130")
get_code_for_paper("2205.06130")
have("2205.06130")

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

curl https://syntology.ai/api/ran/2205.06130.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.06130.svg)](https://syntology.ai/paper/2205.06130)

Connect an agent — have() is free.