SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.03416 · 2023

ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization

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/2301.03416.json · badge: /api/ran/2301.03416.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
PaddlePaddle/PaddleNLP canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
cell_div Ran
ran on a synthesized input
PaddlePaddle/PaddleNLP/paddlenlp/experimental/model_utils.py
code served (permissive licence) · get_code("5bab2794a9fc339f")
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 int, ndim 0, dtype family int, 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)

# The function cell_div(x, y) performs ceiling division: (x + y - 1) // y
# It takes two parameters that support addition, subtraction, and integer division
# These can be integers, floats, or tensors

x = 10
y = 3

ARGS = {
    "x": x,
    "y": y,
}
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 int, ndim 0, dtype family int, 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
sequence_mask Ran
ran; our contract draft was wrong, not the code
PaddlePaddle/PaddleNLP/paddlenlp/layers/sequence.py
code served (permissive licence) · get_code("6db7f5c4fd955cff")
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 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# seq_ids: shape [batch_size, sequence_length]
# valid_lengths: shape [batch_size]

batch_size = 2
sequence_length = 4

seq_ids = torch.arange(sequence_length).unsqueeze(0).expand(batch_size, -1)
# seq_ids will be:
# [[0, 1, 2, 3],
#  [0, 1, 2, 3]]

valid_lengths = torch.tensor([2, 3])
# First sequence is valid up to index 2, second up to index 3

ARGS = {
    "seq_ids": seq_ids,
    "valid_lengths": valid_lengths,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
load_vocabulary Not yet run
unverified (harvested, no recorded run)
PaddlePaddle/PaddleNLP/paddlenlp/experimental/model_utils.py
code served (permissive licence) · get_code("7667c4274e1b357d")
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, 2 are also present in other papers whose code we hold (2 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.

FunctionAlso present inEarliest-datedOthers named
load_vocabulary 1 other paper
1 dated earlier
2105.13626 (2021-05)
ByT5: Towards a token-free future with pre-trained byte-to-byte models
sequence_mask 1 other paper
1 dated earlier
2105.13626 (2021-05)
ByT5: Towards a token-free future with pre-trained byte-to-byte models

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

Task-agnostic knowledge distillation attempts to address the problem of deploying large pretrained language model in resource-constrained scenarios by compressing a large pretrained model called teacher into a smaller one called student such that the student can be directly finetuned on downstream tasks and retains comparable performance. However, we empirically find that there is a generalization gap between the student and the teacher in existing methods. In this work, we show that we can leverage multi-task learning in task-agnostic distillation to advance the generalization of the resulted student. In particular, we propose Multi-task Infused Task-agnostic Knowledge Distillation (MITKD). We first enhance the teacher by multi-task training it on multiple downstream tasks and then perform distillation to produce the student. Experimental results demonstrate that our method yields a student with much better generalization, significantly outperforms existing baselines, and establishes a new state-of-the-art result on in-domain, out-domain, and low-resource datasets in the setting of task-agnostic distillation. Moreover, our method even exceeds an 8x larger BERT$_{\text{Base}}$ on SQuAD and four GLUE tasks. In addition, by combining ERNIE 3.0, our method achieves state-of-the-art results on 10 Chinese datasets.

For agents

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

get_harvested_code_for_paper("2301.03416")
get_code_for_paper("2301.03416")
have("2301.03416")

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

curl https://syntology.ai/api/ran/2301.03416.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.03416.svg)](https://syntology.ai/paper/2301.03416)

Connect an agent — have() is free.