SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1505.08075 · 2015

Transition-Based Dependency Parsing with Stack Long Short-Term Memory

arXiv · PDF · Open in the Atlas

Code that ran

7 of 14 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 6 have no contract verdict; 1 failure of our instrument; 7 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/1505.08075.json · badge: /api/ran/1505.08075.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
mstrise/dep2label community (classifier label)
classifier basis not recorded on the link
4 ran · 3 no recorded run
Yusics/bist-parser community (classifier label)
classifier basis not recorded on the link
3 ran · 4 no recorded run
FunctionStatusWhere it lives
check_if_crossing_arcs Ran
ran on a synthesized input
mstrise/dep2label/dep2label/encodings.py
code served (permissive licence) · get_code("a16be92b2801ab44")
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 2, dtype family int; 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 iterates over plane and arc as iterables of tuples
# Each tuple contains two elements (i, j) and (k, l)
# The function compares min/max of these elements
# So plane and arc should be lists of 2-tuples containing comparable values

plane = [
    (1, 5),
    (3, 8),
    (2, 6)
]

arc = [
    (2, 7),
    (4, 9),
    (1, 4)
]

ARGS = {
    "plane": plane,
    "arc": arc
}
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 2, dtype family int — 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
decode_2p_brackets Ran
ran on a synthesized input
mstrise/dep2label/dep2label/encodings.py
code served (permissive licence) · get_code("ccbdc4aeb4b3323f")
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

# Analyzing the function:
# - Takes a 'sentence' parameter which is a list/sequence
# - Iterates through indices starting from 1
# - Each sentence[word_index] is accessed and has indices [0], [1], [2], [3], [4]
# - sentence[word_index][2] and [3] are converted to lists (so strings)
# - sentence[word_index][4] is compared to 'root' (so string)
# - Constructs word dicts with keys 1-6

# Create a valid sentence structure
sentence = [
    None,  # Index 0 - not used (iteration starts at 1)
    ["word1", "pos1", "<L", "[l", "root"],      # Index 1
    ["word2", "pos2", "R>", "r]", "nsubj"],     # Index 2
    ["word3", "pos3", "<", "[", "obj"],         # Index 3
]

ARGS = {
    "sentence": sentence
}
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 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
has_descendants Ran
ran on a synthesized input
mstrise/dep2label/dep2label/encodings.py
code served (permissive licence) · get_code("74c0e5534e18f473")
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 bool, 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

torch.manual_seed(0)

# The function iterates over a buffer (list) and checks if any element
# has a 'head' key matching the word parameter.
# We need to construct a list of dicts with 'head' keys and a word to search for.

word = "token_5"

buffer = [
    {'head': 'token_1', 'dep': 'nsubj'},
    {'head': 'token_5', 'dep': 'obj'},
    {'head': 'token_3', 'dep': 'prep'},
]

ARGS = {
    'word': word,
    'buffer': buffer,
}
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 bool, 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
load_deprel_weights Ran
ran on a synthesized input
Yusics/bist-parser/barchybrid/src/utils/evaluation_script/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
log_sum_exp Ran
ran; our contract draft was wrong, not the code
mstrise/dep2label/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
normalize Ran
ran on a synthesized input
Yusics/bist-parser/bmstparser/src/utils.py
code served (permissive licence) · get_code("a178745e105220aa")
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 re

numberRegex = re.compile('[0-9]+|[0-9]+\\.[0-9]+|[0-9]+[0-9,]+')

def normalize(word):
    return 'NUM' if numberRegex.match(word) else word.lower()

ARGS = {
    'word': '123'
}
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 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
vocab Ran
ran on a synthesized input
Yusics/bist-parser/bmstparser/src/utils.py
code served (permissive licence) · get_code("38346f1c9a8dc86b")
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 tempfile
import os

def normalize(word):
    import re
    numberRegex = re.compile('[0-9]+|[0-9]+\\.[0-9]+|[0-9]+[0-9,]+')
    return 'NUM' if numberRegex.match(word) else word.lower()

class ConllEntry:
    def __init__(self, id, form, lemma, pos, cpos, feats=None, parent_id=None, relation=None, deps=None, misc=None):
        self.id = id
        self.form = form
        self.norm = normalize(form)
        self.cpos = cpos.upper()
        self.pos = pos.upper()
        self.parent_id = parent_id
        self.relation = relation
        self.lemma = lemma
        self.feats = feats
        self.deps = deps
        self.misc = misc
        self.pred_parent_id = None
        self.pred_relation = None

    def __str__(self):
        values = [str(self.id), self.form, self.lemma, self.cpos, self.pos, self.feats, str(self.pred_parent_id) if self.pred_parent_id is not None else None, self.pred_relation, self.deps, self.misc]
        return '\t'.join(['_' if v is None else v for v in values])

# Create a temporary CoNLL file for testing
temp_conll_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.conll')

conll_content = """# sent_id = 1
# text = The dog ran
1	The	the	DET	DT	_	2	det	_	_
2	dog	dog	NOUN	NN	_	3	nsubj	_	_
3	ran	run	VERB	VBD	_	0	root	_	_

# sent_id = 2
# text = She jumps
1	She	she	PRON	PRP	_	2	nsubj	_	_
2	jumps	jump	VERB	VBZ	_	0	root	_	_

"""

temp_conll_file.write(conll_content)
temp_conll_file.close()

ARGS = {
    'conll_path': temp_conll_file.name
}
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 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
evaluate Not yet run
unverified (harvested, no recorded run)
Yusics/bist-parser/barchybrid/src/utils/evaluation_script/conll17_ud_eval.py
code served (permissive licence) · get_code("cb5ea19799e31ba8")
How it ran

no invocation recorded.

evaluate Not yet run
unverified (harvested, no recorded run)
mstrise/dep2label/dep2label/eval_dep/conll18_ud_eval.py
code served (permissive licence) · get_code("245d8f594031798b")
How it ran

no invocation recorded.

load_conllu Not yet run
unverified (harvested, no recorded run)
Yusics/bist-parser/bmstparser/src/utils/evaluation_script/conll17_ud_eval.py
code served (permissive licence) · get_code("6f11534db6a06f8e")
How it ran

no invocation recorded.

load_conllu Not yet run
unverified (harvested, no recorded run)
Yusics/bist-parser/barchybrid/src/utils/evaluation_script/conll17_ud_eval.py
code served (permissive licence) · get_code("6d71b42e4dacd50b")
How it ran

no invocation recorded.

load_conllu Not yet run
unverified (harvested, no recorded run)
mstrise/dep2label/dep2label/eval_dep/conll18_ud_eval.py
code served (permissive licence) · get_code("898a8ab6ccbb4763")
How it ran

no invocation recorded.

load_conllu_file Not yet run
unverified (harvested, no recorded run)
mstrise/dep2label/dep2label/eval_dep/conll18_ud_eval.py
code served (permissive licence) · get_code("4c2a95032787d62c")
How it ran

no invocation recorded.

parse_proj Not yet run
unverified (harvested, no recorded run)
Yusics/bist-parser/bmstparser/src/decoder.py
code served (permissive licence) · get_code("ebd329b222dc781a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 10 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 10 later) and 4 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
log_sum_exp 10 other papers
10 later
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
1906.01378 (2019-06)
Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning
and 7 more not named here
evaluate 2 other papers
2 later
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
2002.01685 (2020-02)
Parsing as Pretraining
load_conllu 2 other papers
2 later
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
2002.01685 (2020-02)
Parsing as Pretraining
load_deprel_weights 2 other papers
2 later
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
2002.01685 (2020-02)
Parsing as Pretraining
evaluate 1 other paper
1 later
1904.02099 (2019-04)
75 Languages, 1 Model: Parsing Universal Dependencies Universally
load_conllu 1 other paper
1 later
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
load_conllu_file 1 other paper
1 later
1904.02099 (2019-04)
75 Languages, 1 Model: Parsing Universal Dependencies Universally
normalize 1 other paper
1 later
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
parse_proj 1 other paper
1 later
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
vocab 1 other paper
1 later
1603.04351 (2016-03)
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations

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

We propose a technique for learning representations of parser states in transition-based dependency parsers. Our primary innovation is a new control structure for sequence-to-sequence neural networks---the stack LSTM. Like the conventional stack data structures used in transition-based parsing, elements can be pushed to or popped from the top of the stack in constant time, but, in addition, an LSTM maintains a continuous space embedding of the stack contents. This lets us formulate an efficient parsing model that captures three facets of a parser's state: (i) unbounded look-ahead into the buffer of incoming words, (ii) the complete history of actions taken by the parser, and (iii) the complete contents of the stack of partially built tree fragments, including their internal structures. Standard backpropagation techniques are used for training and yield state-of-the-art parsing performance.

For agents

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

get_harvested_code_for_paper("1505.08075")
get_code_for_paper("1505.08075")
have("1505.08075")

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

curl https://syntology.ai/api/ran/1505.08075.json

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

[![Syntology run record](https://syntology.ai/api/ran/1505.08075.svg)](https://syntology.ai/paper/1505.08075)

Connect an agent — have() is free.