SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.00807 · 2018

Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator

arXiv · PDF · Open in the Atlas

Code that ran

14 of 17 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 9 have no contract verdict; 5 failures of our instrument; 3 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/1806.00807.json · badge: /api/ran/1806.00807.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
dev-chauhan/PQG-pytorch community (classifier label)
classifier basis not recorded on the link
14 ran · 0 no recorded run
vinodkkurmi/PQG community (classifier label)
classifier basis not recorded on the link
0 ran · 3 no recorded run
FunctionStatusWhere it lives
JointEmbeddingLoss Ran
ran on a synthesized input
dev-chauhan/PQG-pytorch/misc/net_utils.py
code served (permissive licence) · get_code("8f0322f2e3938c98")
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

torch.manual_seed(0)

# Create two embedding tensors
# batch_size = 2, embedding_dim = 4
feature_emb1 = torch.randn(2, 4)
feature_emb2 = torch.randn(2, 4)

ARGS = {
    "feature_emb1": feature_emb1,
    "feature_emb2": feature_emb2,
}
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 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
cook_refs Ran
ran; our contract draft was wrong, not the code
dev-chauhan/PQG-pytorch/pycocoevalcap/cider/cider_scorer.py
pointer only (licence: MIT); the stored copy get_code serves, from wenhuchen/data-to-text-evaluation-metric, is pointer only (licence: NOASSERTION) · get_code("4c1b107103b7c856")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from wenhuchen/data-to-text-evaluation-metric, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

cook_refs Ran
ran; our contract draft was wrong, not the code
dev-chauhan/PQG-pytorch/pycocoevalcap/bleu/bleu_scorer.py
code served (permissive licence) · get_code("7586e1d32f7325f7")
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.

from collections import defaultdict

ARGS = {
    'refs': [
        'the quick brown fox jumps over the lazy dog',
        'a quick brown fox leaps over a lazy dog'
    ],
    'eff': 'shortest',
    'n': 4
}
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
cook_test Ran
ran; our contract draft was wrong, not the code
dev-chauhan/PQG-pytorch/pycocoevalcap/cider/cider_scorer.py
pointer only (licence: MIT); the stored copy get_code serves, from wenhuchen/data-to-text-evaluation-metric, is pointer only (licence: NOASSERTION) · get_code("3573c4bc85f65dfd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from wenhuchen/data-to-text-evaluation-metric, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

cook_test Ran
ran on a synthesized input
dev-chauhan/PQG-pytorch/pycocoevalcap/bleu/bleu_scorer.py
code served (permissive licence) · get_code("99e54843980299e2")
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.

from collections import defaultdict

def precook(s, n=4, out=False):
    """Takes a string as input and returns an object that can be given to
    either cook_refs or cook_test. This is optional: cook_refs and cook_test
    can take string arguments as well."""
    words = s.split()
    counts = defaultdict(int)
    for k in range(1, n + 1):
        for i in range(len(words) - k + 1):
            ngram = tuple(words[i:i + k])
            counts[ngram] += 1
    return (len(words), counts)

def cook_test(test, refs, eff=None, n=4):
    """Takes a test sentence and returns an object that
    encapsulates everything that BLEU needs to know about it."""
    reflen, refmaxcounts = refs
    testlen, counts = precook(test, n, True)
    result = {}
    if eff == 'closest':
        result['reflen'] = min(((abs(l - testlen), l) for l in reflen))[1]
    else:
        result['reflen'] = reflen
    result['testlen'] = testlen
    result['guess'] = [max(0, testlen - k + 1) for k in range(1, n + 1)]
    result['correct'] = [0] * n
    for ngram, count in counts.items():
        result['correct'][len(ngram) - 1] += min(refmaxcounts.get(ngram, 0), count)
    return result

# Build test arguments
test_string = "the quick brown fox jumps over the lazy dog"

# Create reference data using precook
ref_string_1 = "the quick brown fox jumps over the lazy dog"
ref_string_2 = "a fast brown fox leaps over the lazy dog"
reflen_1, refcounts_1 = precook(ref_string_1, n=4)
reflen_2, refcounts_2 = precook(ref_string_2, n=4)

# Merge reference counts (take max for each ngram)
refmaxcounts = defaultdict(int)
for ngram, count in refcounts_1.items():
    refmaxcounts[ngram] = max(refmaxcounts[ngram], count)
for ngram, count in refcounts_2.items():
    refmaxcounts[ngram] = max(refmaxcounts[ngram], count)

# Create refs tuple
refs = ([reflen_1, reflen_2], refmaxcounts)

ARGS = {
    'test': test_string,
    'refs': refs,
    'eff': None,
    'n': 4
}
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
decode_sequence Ran
ran on a synthesized input
dev-chauhan/PQG-pytorch/misc/net_utils.py
code served (permissive licence) · get_code("0fd52e308ba7327b")
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)

# ix_to_word: a dictionary mapping integer indices to word strings
# The function accesses ix_to_word[index] to get words
# It also checks if an index is in ix_to_word
# It accesses ix_to_word[len(ix_to_word) - 1] for unknown tokens
ix_to_word = {
    0: '<SOS>',
    1: 'hello',
    2: 'world',
    3: 'test',
    4: '<EOS>',  # This is the last entry, used for unknown tokens
}

# seq: a 2D tensor of shape (N, D) where N is batch size and D is sequence length
# The function indexes it as seq[i, j] and calls .item() on individual elements
# Using shape (2, 4) for batch_size=2, sequence_length=4
seq = torch.tensor([
    [0, 1, 2, 4],  # First sequence: <SOS> hello world <EOS>
    [0, 3, 2, 4],  # Second sequence: <SOS> test world <EOS>
], dtype=torch.long)

ARGS = {
    'ix_to_word': ix_to_word,
    'seq': seq,
}
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
getObjsForScores Ran
ran on a synthesized input
dev-chauhan/PQG-pytorch/misc/train_util.py
code served (permissive licence) · get_code("2d0a07f54afa1681")
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

torch.manual_seed(0)

# Based on the function signature and body:
# - real_sents: a list/sequence of sentences (strings)
# - pred_sents: a list/sequence of sentences (strings)
# The function creates coco objects from these sentence lists
# The coco class expects iterables with len() support

real_sents = [
    "the cat sat on the mat",
    "a dog ran in the park"
]

pred_sents = [
    "the cat is sitting on a mat",
    "a dog was running in the park"
]

ARGS = {
    "real_sents": real_sents,
    "pred_sents": pred_sents
}
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
one_hot Ran
ran on a synthesized input
dev-chauhan/PQG-pytorch/misc/utils.py
code served (permissive licence) · get_code("aa2c3c11f48386d7")
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 3, dtype family float, shape (2, 3, 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)

# The function one_hot takes:
# - t: a tensor of indices (will be scattered into one-hot encoding)
# - c: number of classes (the one-hot dimension size)

# Create a small tensor of class indices
t = torch.tensor([[0, 1, 2], [1, 2, 0]], dtype=torch.long)  # shape (2, 3)

# Number of classes
c = 4

ARGS = {
    "t": t,
    "c": c,
}
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 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 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
precook Ran
ran; our contract draft was wrong, not the code
dev-chauhan/PQG-pytorch/pycocoevalcap/bleu/bleu_scorer.py
code served (permissive licence) · get_code("ec4448373d72d636")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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.

ARGS = {
    "s": "the quick brown fox jumps over the lazy dog",
    "n": 4,
    "out": False
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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
precook Ran
ran; our contract draft was wrong, not the code
dev-chauhan/PQG-pytorch/pycocoevalcap/cider/cider_scorer.py
pointer only (licence: MIT); the stored copy get_code serves, from wenhuchen/data-to-text-evaluation-metric, is pointer only (licence: NOASSERTION) · get_code("9560e3e3e41bc1b2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from wenhuchen/data-to-text-evaluation-metric, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

prepro_question Ran
ran on a synthesized input
dev-chauhan/PQG-pytorch/prepro/prepro_quora.py
code served (permissive licence) · get_code("4e1b9fbb554f4958")
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 sys
from nltk.tokenize import word_tokenize
import re

def tokenize(sentence):
    return [i for i in re.split('([-.\\"\',:? !\\$#@~()*&\\^%;\\[\\]/\\\\\\+<>\\n=])', sentence) if i != '' and i != ' ' and (i != '\n')]

def prepro_question(imgs, params):
    print('example processed tokens:')
    for i, img in enumerate(imgs):
        s = img['question']
        if params['token_method'] == 'nltk':
            txt = word_tokenize(s)
        else:
            txt = tokenize(s)
        img['processed_tokens'] = txt
        if i < 10:
            print(txt)
        if i % 1000 == 0:
            sys.stdout.write('processing %d/%d (%.2f%% done)   \r' % (i, len(imgs), i * 100.0 / len(imgs)))
            sys.stdout.flush()
    return imgs

# Create test data
imgs = [
    {'question': 'What is this?'},
    {'question': 'How many dogs are there?'},
    {'question': 'Where is the cat, and what color is it?'},
    {'question': 'Can you describe the scene?'},
    {'question': 'What time is it?'},
    {'question': 'Is this a bird or a plane?'},
    {'question': 'Who is standing there?'},
    {'question': 'Why is the sky blue?'},
    {'question': 'How much does it cost?'},
    {'question': 'Tell me about this place.'},
    {'question': 'What do you see here?'},
    {'question': 'Is it raining outside?'},
]

params = {
    'token_method': 'regex'
}

ARGS = {
    'imgs': imgs,
    'params': params
}
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
prepro_question1 Ran
ran on a synthesized input
dev-chauhan/PQG-pytorch/prepro/prepro_quora.py
code served (permissive licence) · get_code("d32850b743977c57")
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 sys
from nltk.tokenize import word_tokenize
import re

def tokenize(sentence):
    return [i for i in re.split('([-.\\"\',:? !\\$#@~()*&\\^%;\\[\\]/\\\\\\+<>\\n=])', sentence) if i != '' and i != ' ' and (i != '\n')]

def prepro_question1(imgs, params):
    print('example processed tokens:')
    for i, img in enumerate(imgs):
        s = img['question1']
        if params['token_method'] == 'nltk':
            txt_c = word_tokenize(s)
        else:
            txt_c = tokenize(s)
        img['processed_tokens_caption'] = txt_c
        if i < 10:
            print(txt_c)
        if i % 1000 == 0:
            sys.stdout.write('processing %d/%d (%.2f%% done)   \r' % (i, len(imgs), i * 100.0 / len(imgs)))
            sys.stdout.flush()
    return imgs

# Build test data
imgs = [
    {'question1': 'What is this?'},
    {'question1': 'Where are the dogs?'},
    {'question1': 'How many cats are there?'},
    {'question1': 'Is this a bird?'},
    {'question1': 'What color is the sky?'},
]

params = {
    'token_method': 'regex',
}

ARGS = {
    'imgs': imgs,
    'params': params,
}
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
prob2pred Ran
ran on a synthesized input
dev-chauhan/PQG-pytorch/misc/net_utils.py
code served (permissive licence) · get_code("5634e65606c0b231")
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 int, shape (2, 3) 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)

# prob should be a tensor of log probabilities
# The function reshapes it to (-1, prob.size(-1)), so it expects at least 2D
# Then it calls torch.multinomial which expects probabilities (not log)
# torch.exp converts log probs to probs
# multinomial samples 1 index per row
# Finally reshape back to (batch, seq_len) shape

# Create a tensor with shape (batch=2, seq_len=3, vocab=4)
# This will be reshaped to (6, 4) for multinomial, then back to (2, 3)
prob = torch.randn(2, 3, 4)  # log probabilities

ARGS = {
    "prob": prob
}
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 int, shape (2, 3) — shape (2, 3) 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
tokenize Ran
ran on a synthesized input
dev-chauhan/PQG-pytorch/prepro/prepro_quora.py
code served (permissive licence) · get_code("88ff7954b60fad9c")
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 re

def tokenize(sentence):
    return [i for i in re.split('([-.\\"\',:? !\\$#@~()*&\\^%;\\[\\]/\\\\\\+<>\\n=])', sentence) if i != '' and i != ' ' and (i != '\n')]

ARGS = {
    "sentence": "Hello, world! This is a test sentence."
}
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
cook_refs Not yet run
unverified (harvested, no recorded run)
vinodkkurmi/PQG/coco-caption/pycocoevalcap/cider/cider_scorer.py
pointer only (licence: MIT); the stored copy get_code serves, from vrama91/coco-caption, is pointer only (licence: NOASSERTION) · get_code("5172aba957a32d9e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from vrama91/coco-caption, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

cook_test Not yet run
unverified (harvested, no recorded run)
vinodkkurmi/PQG/coco-caption/pycocoevalcap/cider/cider_scorer.py
pointer only (licence: MIT); the stored copy get_code serves, from vrama91/coco-caption, is pointer only (licence: NOASSERTION) · get_code("90a4bcbf05586ff3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from vrama91/coco-caption, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

precook Not yet run
unverified (harvested, no recorded run)
vinodkkurmi/PQG/coco-caption/pycocoevalcap/cider/cider_scorer.py
pointer only (licence: MIT); the stored copy get_code serves, from vrama91/coco-caption, is pointer only (licence: NOASSERTION) · get_code("422c41f5b22cf9c3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from vrama91/coco-caption, and GitHub could not classify the licence of that repository (NOASSERTION). 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 8 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 8 later) and 7 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
cook_refs 25 other papers
7 dated earlier, 18 later
1411.5726 (2014-11)
CIDEr: Consensus-based Image Description Evaluation
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1503.01817 (2015-03)
YFCC100M: The New Data in Multimedia Research
and 22 more not named here
cook_test 22 other papers
6 dated earlier, 16 later
1411.5726 (2014-11)
CIDEr: Consensus-based Image Description Evaluation
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1503.01817 (2015-03)
YFCC100M: The New Data in Multimedia Research
and 19 more not named here
precook 22 other papers
4 dated earlier, 18 later
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1611.09268 (2016-11)
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
and 19 more not named here
cook_refs 21 other papers
3 dated earlier, 18 later
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1611.09268 (2016-11)
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
1611.09571 (2016-11)
Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model
and 18 more not named here
precook 14 other papers
2 dated earlier, 12 later
1411.5726 (2014-11)
CIDEr: Consensus-based Image Description Evaluation
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1809.01797 (2018-09)
Describing a Knowledge Base
and 11 more not named here
precook 8 other papers
6 dated earlier, 2 later
1411.5726 (2014-11)
CIDEr: Consensus-based Image Description Evaluation
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1503.01817 (2015-03)
YFCC100M: The New Data in Multimedia Research
and 5 more not named here
cook_test 2 other papers
1 dated earlier, 1 later
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
2111.12085 (2021-11)
UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
tokenize 1 other paper
1 later
1902.00038 (2019-02)
BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection

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

In this paper, we propose a method for obtaining sentence-level embeddings. While the problem of securing word-level embeddings is very well studied, we propose a novel method for obtaining sentence-level embeddings. This is obtained by a simple method in the context of solving the paraphrase generation task. If we use a sequential encoder-decoder model for generating paraphrase, we would like the generated paraphrase to be semantically close to the original sentence. One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far. This is ensured by using a sequential pair-wise discriminator that shares weights with the encoder that is trained with a suitable loss function. Our loss function penalizes paraphrase sentence embedding distances from being too large. This loss is used in combination with a sequential encoder-decoder network. We also validated our method by evaluating the obtained embeddings for a sentiment analysis task. The proposed method results in semantic embeddings and outperforms the state-of-the-art on the paraphrase generation and sentiment analysis task on standard datasets. These results are also shown to be statistically significant.

For agents

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

get_harvested_code_for_paper("1806.00807")
get_code_for_paper("1806.00807")
have("1806.00807")

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

curl https://syntology.ai/api/ran/1806.00807.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.00807.svg)](https://syntology.ai/paper/1806.00807)

Connect an agent — have() is free.