SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1506.03099 · 2015

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 4 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/1506.03099.json · badge: /api/ran/1506.03099.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
oplatek/e2end community (classifier label)
classifier basis not recorded on the link
4 ran · 4 no recorded run
FunctionStatusWhere it lives
get_bleus Ran
ran on a synthesized input
oplatek/e2end/e2end/model/evaluation.py
code served (permissive licence) · get_code("f4350f932bd9743b")
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.translate.bleu_score import corpus_bleu, SmoothingFunction, sentence_bleu

bleu_smoothing = SmoothingFunction(epsilon=0.01).method1

def get_bleus(referencess, wordss):
    """Return bleu using nltk and 0.0 for empty decoded sequnces"""
    return [sentence_bleu([r], s, smoothing_function=bleu_smoothing) if s else 0.0 for r, s in zip(referencess, wordss)]

# Setup code
# referencess: list of reference word sequences (list of lists of strings)
# wordss: list of candidate word sequences (list of lists of strings, some possibly empty)

referencess = [
    ['the', 'cat', 'sat', 'on', 'the', 'mat'],
    ['a', 'dog', 'ran'],
    ['hello', 'world'],
]

wordss = [
    ['the', 'cat', 'sat', 'on', 'the', 'mat'],
    [],  # empty sequence to test the 0.0 case
    ['hello', 'world', 'test'],
]

ARGS = {
    'referencess': referencess,
    'wordss': wordss,
}
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
shuffle Ran
ran on a synthesized input
oplatek/e2end/e2end/utils.py
code served (permissive licence) · get_code("8694c9cd02e9f95c")
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 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 random

def shuffle(l):
    l2 = l[:]
    random.shuffle(l2)
    return l2

# The function takes a single parameter 'l' which should be a list
# It creates a shallow copy and shuffles it
ARGS = {
    'l': [1, 2, 3, 4, 5]
}
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 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
sigmoid Ran
ran on a synthesized input
oplatek/e2end/e2end/utils.py
code served (permissive licence) · get_code("7386793e4883e20c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (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 numpy as np

def sigmoid(x):
    x = np.array(x)
    return np.exp(-np.logaddexp(0, -x))

# The function takes a single parameter 'x' which can be:
# - a scalar
# - a list
# - a numpy array
# - anything that np.array() can convert

# Test with various input types
ARGS = {
    "x": np.array([[-2.0, -1.0, 0.0, 1.0], [2.0, 3.0, -0.5, 0.5]])
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (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
split Ran
ran on a synthesized input
oplatek/e2end/e2end/utils.py
code served (permissive licence) · get_code("e60cce6899e60e6a")
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. 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
import torch.nn as nn

torch.manual_seed(0)

# The split function takes two parameters:
# - a: a sequence (list, tuple, tensor, or anything with len() and slicing)
# - n: an integer representing the number of parts to split into

# Construct a simple list for 'a'
a = list(range(10))  # A list of 10 elements

# Construct an integer for 'n'
n = 3  # Split into 3 parts

ARGS = {
    "a": a,
    "n": n
}
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 — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
attention_decoder Not yet run
unverified (harvested, no recorded run)
oplatek/e2end/e2end/model/decoder.py
code served (permissive licence) · get_code("c0f1bfe2a7139f20")
How it ran

no invocation recorded.

tf_lengths2mask2d Not yet run
unverified (harvested, no recorded run)
oplatek/e2end/e2end/model/evaluation.py
code served (permissive licence) · get_code("460d6c8b80434cd2")
How it ran

no invocation recorded.

tf_trg_word2vocab_id Not yet run
unverified (harvested, no recorded run)
oplatek/e2end/e2end/model/evaluation.py
code served (permissive licence) · get_code("297bf6be5afe88c9")
How it ran

no invocation recorded.

word_db_embed_attention_decoder Not yet run
unverified (harvested, no recorded run)
oplatek/e2end/e2end/model/decoder.py
code served (permissive licence) · get_code("7c61a46975e737a8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Recurrent Neural Networks can be trained to produce sequences of tokens given some input, as exemplified by recent results in machine translation and image captioning. The current approach to training them consists of maximizing the likelihood of each token in the sequence given the current (recurrent) state and the previous token. At inference, the unknown previous token is then replaced by a token generated by the model itself. This discrepancy between training and inference can yield errors that can accumulate quickly along the generated sequence. We propose a curriculum learning strategy to gently change the training process from a fully guided scheme using the true previous token, towards a less guided scheme which mostly uses the generated token instead. Experiments on several sequence prediction tasks show that this approach yields significant improvements. Moreover, it was used successfully in our winning entry to the MSCOCO image captioning challenge, 2015.

For agents

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

get_harvested_code_for_paper("1506.03099")
get_code_for_paper("1506.03099")
have("1506.03099")

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

curl https://syntology.ai/api/ran/1506.03099.json

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

[![Syntology run record](https://syntology.ai/api/ran/1506.03099.svg)](https://syntology.ai/paper/1506.03099)

Connect an agent — have() is free.