SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.01685 · AAAI · 2020

Parsing as Pretraining

Anders Søgaard, David Vilares, Carlos Gómez-Rodríguez, Michalina Strzyz

arXiv · PDF · Open in the Atlas

Code that ran

16 of 30 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 15 have no contract verdict; 1 failure of our instrument; 14 no recorded run), measured 2026-11-21; 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/2002.01685.json · badge: /api/ran/2002.01685.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
huggingface/pytorch-pretrained-BERT canonical (classifier label)
classifier basis: census
8 ran · 9 no recorded run
aghie/parsing-as-pretraining canonical (classifier label)
classifier basis: census
8 ran · 5 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
aghie/parsing-as-pretraining/run_token_classifier.py
code served (permissive licence) · get_code("b53cb159746bdff2")
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 float, 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
from sklearn.metrics import accuracy_score

torch.manual_seed(0)

# Create small tensors for testing
# out: output predictions that will be multiplied by mask
out = torch.tensor([[1.0, 2.0, 3.0, 0.0],
                     [0.0, 1.0, 2.0, 3.0]], dtype=torch.float32)

# labels: gold labels that will be multiplied by mask
labels = torch.tensor([[1, 2, 3, 0],
                       [0, 1, 2, 3]], dtype=torch.float32)

# mask: binary mask to filter out certain positions (0 means ignore)
mask = torch.tensor([[1, 1, 1, 0],
                     [0, 1, 1, 1]], dtype=torch.float32)

ARGS = {
    "out": out,
    "labels": labels,
    "mask": mask
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
convert_old_keys_to_new_keys Ran
ran on a synthesized input
huggingface/pytorch-pretrained-BERT/src/transformers/models/aimv2/convert_aimv2_original_pytorch_to_hf.py
pointer only (licence: Apache-2.0) · get_code("4d50cf32a98739b3")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

create_rename_keys Ran
ran on a synthesized input
huggingface/pytorch-pretrained-BERT/src/transformers/models/beit/convert_beit_unilm_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("c968c3df370ea581")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

dependency_displacements Ran
ran on a synthesized input
aghie/parsing-as-pretraining/evaluate_dependencies.py
code served (permissive licence) · get_code("afa29dda7e74e00a")
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 list, 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.

class Word:
    def __init__(self, idx, head, deprel):
        self.idx = idx
        self.head = head
        self.deprel = deprel

class Tree:
    def __init__(self, words):
        self.words = words
    
    def __getitem__(self, index):
        return self.words[index]

# Create word instances with distinct indices and heads
word1 = Word(idx=1, head=3, deprel='nsubj')
word2 = Word(idx=2, head=2, deprel='det')
word3 = Word(idx=3, head=0, deprel='root')
word4 = Word(idx=4, head=3, deprel='obj')

# Create a tree with a root node (None) at index 0
tree = Tree([None, word1, word2, word3, word4])

ARGS = {
    'tree': tree,
    'unlabeled': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
get_tree_spans Ran
ran on a synthesized input
aghie/parsing-as-pretraining/evaluate_spans.py
code served (permissive licence) · get_code("de7ea09d38e57ab9")
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 list, 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.

from nltk.tree import Tree

# Create a simple tree structure for testing
# The function expects a tree with:
# - type() checking to distinguish strings from tree nodes
# - .leaves() method to get leaf nodes
# - .label() method to get the tree label
# - iteration over children

# Build a tree like:
#       S
#      / \
#     NP  VP
#    /     /
#   N    V
#  /      /
# dog   runs

leaf_dog = "dog"
leaf_runs = "runs"

n_tree = Tree('N', [leaf_dog])
np_tree = Tree('NP', [n_tree])

v_tree = Tree('V', [leaf_runs])
vp_tree = Tree('VP', [v_tree])

root_tree = Tree('S', [np_tree, vp_tree])

# Also test with @ symbol in label
leaf_x = "x"
special_tree = Tree('NP@', [leaf_x])

ARGS = {
    'tree': root_tree,
    'root': True,
    'ignore_non_terminal': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
nltk — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
load_deprel_weights Ran
ran on a synthesized input
aghie/parsing-as-pretraining/dep2labels/conll17_ud_eval.py
code served (permissive licence) · get_code("ce63212f8cdd9a1a")
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 dict. 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 io

# Create a file-like object with valid UD Relations weights format
weights_content = """# Comment line should be ignored
acl 1.5
nsubj 2.0
obj 1.8

advmod 0.9
"""

weights_file = io.StringIO(weights_content)

ARGS = {
    "weights_file": weights_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
load_state_dict Ran
ran on a synthesized input
huggingface/pytorch-pretrained-BERT/src/transformers/models/visual_bert/convert_visual_bert_original_pytorch_checkpoint_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("766143fdc27ade86")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

log_sum_exp Ran
ran; our contract draft was wrong, not the code
aghie/parsing-as-pretraining/NCRFpp/model/crf.py
code served (permissive licence) · get_code("8e960fbb64668568")
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)

# Construct arguments for log_sum_exp
# Parameters: vec (batch_size, vanishing_dim, hidden_dim), m_size (hidden_dim)

batch_size = 2
vanishing_dim = 3
hidden_dim = 4

# Create a random tensor of shape (batch_size, vanishing_dim, hidden_dim)
vec = torch.randn(batch_size, vanishing_dim, hidden_dim)

# m_size should be the hidden_dim
m_size = hidden_dim

ARGS = {
    "vec": vec,
    "m_size": m_size
}
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
make_linear_from_emb Ran
ran on a synthesized input
huggingface/pytorch-pretrained-BERT/src/transformers/models/bart/convert_bart_original_pytorch_checkpoint_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("5301174099bfa9fb")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

model2legends Ran
ran on a synthesized input
aghie/parsing-as-pretraining/evaluate_dependencies.py
code served (permissive licence) · get_code("f22a4a58bed5e5c4")
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 str. 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 torch

torch.manual_seed(0)

ARGS = {
    'model_name': 'bert-base-uncased'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
posprocess_labels Ran
ran on a synthesized input
aghie/parsing-as-pretraining/run_token_classifier.py
code served (permissive licence) · get_code("633d6d0e2a2bc67b")
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 list, 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

torch.manual_seed(0)

# The function posprocess_labels takes a list/sequence of strings (preds)
# and modifies it in place, returning the modified list.
# It performs various string replacements and checks on the elements.

preds = ['-BOS-', 'ROOT', 'NONE', 'NONE', '-EOS-']

ARGS = {
    'preds': preds
}
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 list, ndim 1, dtype family float — a list 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
prune_linear_layer Ran
ran on a synthesized input
huggingface/pytorch-pretrained-BERT/src/transformers/pytorch_utils.py
pointer only (licence: Apache-2.0) · get_code("24ece331635f4b38")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

rename_key Ran
ran on a synthesized input
huggingface/pytorch-pretrained-BERT/src/transformers/models/audio_spectrogram_transformer/convert_audio_spectrogram_transformer_original_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("a34730fcf1a8bed8")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

softmax_backward_data Ran
ran on a synthesized input
huggingface/pytorch-pretrained-BERT/src/transformers/pytorch_utils.py
pointer only (licence: Apache-2.0) · get_code("be3bebdd7de293b6")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

split_qkv_tensor Ran
ran on a synthesized input
huggingface/pytorch-pretrained-BERT/src/transformers/models/aimv2/convert_aimv2_original_pytorch_to_hf.py
pointer only (licence: Apache-2.0) · get_code("71fbe82c279aa0ed")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

word_relations Ran
ran on a synthesized input
aghie/parsing-as-pretraining/evaluate_dependencies.py
code served (permissive licence) · get_code("2d5c6bba2d4b0bfc")
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 list, 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.

class Word:
    def __init__(self, head, deprel):
        self.head = head
        self.deprel = deprel

tree = [
    None,  # index 0 (root placeholder)
    Word(head=0, deprel='root'),
    Word(head=1, deprel='nsubj'),
    Word(head=1, deprel='verb'),
    Word(head=2, deprel='det'),
]

ARGS = {
    'tree': tree,
    'unlabeled': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
apply_chunking_to_forward Not yet run
unverified (harvested, no recorded run)
huggingface/pytorch-pretrained-BERT/src/transformers/pytorch_utils.py
pointer only (licence: Apache-2.0) · get_code("6921551bf74e9179")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

convert_checkpoint_to_pytorch Not yet run
unverified (harvested, no recorded run)
huggingface/pytorch-pretrained-BERT/src/transformers/models/bert/convert_bert_token_dropping_original_tf2_checkpoint_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("5667539047103cbb")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

convert_examples_to_features Not yet run
unverified (harvested, no recorded run)
aghie/parsing-as-pretraining/run_token_classifier.py
code served (permissive licence) · get_code("20541be1e49e8caf")
How it ran

no invocation recorded.

convert_state_dict Not yet run
unverified (harvested, no recorded run)
huggingface/pytorch-pretrained-BERT/src/transformers/models/audio_spectrogram_transformer/convert_audio_spectrogram_transformer_original_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("4855bdca41688f99")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

evaluate Not yet run
unverified (harvested, no recorded run)
aghie/parsing-as-pretraining/dep2labels/conll17_ud_eval.py
code served (permissive licence) · get_code("cb5ea19799e31ba8")
How it ran

no invocation recorded.

get_audio_spectrogram_transformer_config Not yet run
unverified (harvested, no recorded run)
huggingface/pytorch-pretrained-BERT/src/transformers/models/audio_spectrogram_transformer/convert_audio_spectrogram_transformer_original_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("12e92107dcde382b")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_new_dict Not yet run
unverified (harvested, no recorded run)
huggingface/pytorch-pretrained-BERT/src/transformers/models/visual_bert/convert_visual_bert_original_pytorch_checkpoint_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("c79f0bd00e55eba0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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_conllu Not yet run
unverified (harvested, no recorded run)
aghie/parsing-as-pretraining/dep2labels/conll17_ud_eval.py
code served (permissive licence) · get_code("6f11534db6a06f8e")
How it ran

no invocation recorded.

load_original_state_dict Not yet run
unverified (harvested, no recorded run)
huggingface/pytorch-pretrained-BERT/src/transformers/models/aimv2/convert_aimv2_original_pytorch_to_hf.py
pointer only (licence: Apache-2.0) · get_code("90fd642869f21de7")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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_tf2_weights_in_bert Not yet run
unverified (harvested, no recorded run)
huggingface/pytorch-pretrained-BERT/src/transformers/models/bert/convert_bert_original_tf2_checkpoint_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("1a208abd5c3cf8fe")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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_xsum_checkpoint Not yet run
unverified (harvested, no recorded run)
huggingface/pytorch-pretrained-BERT/src/transformers/models/bart/convert_bart_original_pytorch_checkpoint_to_pytorch.py
pointer only (licence: Apache-2.0) · get_code("5ef841f72417ff20")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, huggingface/pytorch-pretrained-BERT, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

performance_on_non_terminals Not yet run
unverified (harvested, no recorded run)
aghie/parsing-as-pretraining/evaluate_spans.py
code served (permissive licence) · get_code("3f7b95f09ac99a1c")
How it ran

no invocation recorded.

performance_on_span_len Not yet run
unverified (harvested, no recorded run)
aghie/parsing-as-pretraining/evaluate_spans.py
code served (permissive licence) · get_code("f97940275212bbdd")
How it ran

no invocation recorded.

read_field Not yet run
unverified (harvested, no recorded run)
huggingface/pytorch-pretrained-BERT/src/transformers/modeling_gguf_pytorch_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from shen8424/CORE, is pointer only (licence: NONE) · get_code("9aeec6efae4fb215")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shen8424/CORE, and GitHub detected no licence in that repository 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 30 samples lifted from this paper's linked repositories, 30 carry a function identity and 0 do not. Of the 30 distinct functions with an identity, 19 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 16 later) and 11 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
apply_chunking_to_forward 21 other papers
21 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
2302.04181 (2023-02)
Attending to Graph Transformers
2302.08647 (2023-02)
Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures
and 18 more not named here
log_sum_exp 10 other papers
5 dated earlier, 5 later
1505.08075 (2015-05)
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
1806.05626 (2018-06)
NCRF++: An Open-source Neural Sequence Labeling Toolkit
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 7 more not named here
evaluate 2 other papers
2 dated earlier
1505.08075 (2015-05)
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
load_conllu 2 other papers
2 dated earlier
1505.08075 (2015-05)
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
load_deprel_weights 2 other papers
2 dated earlier
1505.08075 (2015-05)
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
read_field 2 other papers
2 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
2606.03066 (2026-06)
CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection
accuracy 1 other paper
1 later
2010.00633 (2020-10)
Discontinuous Constituent Parsing as Sequence Labeling
convert_checkpoint_to_pytorch 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
convert_old_keys_to_new_keys 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
convert_state_dict 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
create_rename_keys 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
load_original_state_dict 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
load_tf2_weights_in_bert 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
load_xsum_checkpoint 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
make_linear_from_emb 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
prune_linear_layer 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
rename_key 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
softmax_backward_data 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models
split_qkv_tensor 1 other paper
1 later
2210.09545 (2022-10)
Fine-mixing: Mitigating Backdoors in Fine-tuned Language 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent analyses suggest that encoders pretrained for language modeling capture certain morpho-syntactic structure. However, probing frameworks for word vectors still do not report results on standard setups such as constituent and dependency parsing. This paper addresses this problem and does full parsing (on English) relying only on pretraining architectures -and no decoding. We first cast constituent and dependency parsing as sequence tagging. We then use a single feed-forward layer to directly map word vectors to labels that encode a linearized tree. This is used to: (i) see how far we can reach on syntax modelling with just pretrained encoders, and (ii) shed some light about the syntax-sensitivity of different word vectors (by freezing the weights of the pretraining network during training). For evaluation, we use bracketing F1score and LAS, and analyze in-depth differences across representations for span lengths and dependency displacements. The overall results surpass existing sequence tagging parsers on the PTB (93.5%) and end-to-end EN-EWT UD (78.8%).

For agents

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

get_harvested_code_for_paper("2002.01685")
get_code_for_paper("2002.01685")
have("2002.01685")

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

curl https://syntology.ai/api/ran/2002.01685.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.01685.svg)](https://syntology.ai/paper/2002.01685)

Connect an agent — have() is free.