SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1612.00563 · 2016

Self-critical Sequence Training for Image Captioning

arXiv · PDF · Open in the Atlas

Code that ran

12 of 13 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, 1 violated it and 1 has no contract verdict; 10 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1612.00563.json · badge: /api/ran/1612.00563.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
husthuaan/AAT community (classifier label)
classifier basis: plan_row
7 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
ruotianluo/GoogleConceptualCaptioning reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
attention Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from ruotianluo/Transformer_Captioning
pointer only; the stored copy get_code serves, from ruotianluo/Transformer_Captioning, is pointer only (licence: NONE) · get_code("20bb0ff4a2d77a03")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

build_vocab Ran
ran; our contract draft was wrong, not the code
ruotianluo/GoogleConceptualCaptioning/scripts/prepro_labels.py
code served (permissive licence) · get_code("41b9ec0c269d8a91")
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 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
import numpy as np

torch.manual_seed(0)

# Build sample image data with sentences and tokens
imgs = [
    {
        'sentences': [
            {'tokens': ['a', 'cat', 'sits', 'on', 'the', 'mat']},
            {'tokens': ['the', 'cat', 'is', 'black']},
            {'tokens': ['a', 'dog', 'runs', 'in', 'the', 'park']}
        ]
    },
    {
        'sentences': [
            {'tokens': ['the', 'dog', 'is', 'brown']},
            {'tokens': ['a', 'bird', 'flies', 'in', 'the', 'sky']},
            {'tokens': ['the', 'mat', 'is', 'red']}
        ]
    },
    {
        'sentences': [
            {'tokens': ['cat', 'and', 'dog', 'play']},
            {'tokens': ['the', 'park', 'is', 'green']},
            {'tokens': ['a', 'rare', 'word', 'appears', 'once']}
        ]
    }
]

params = {
    'word_count_threshold': 1
}

ARGS = {
    'imgs': imgs,
    'params': params
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, 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
clones Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from dilab-ustcsz/cmust
pointer only · get_code("a3722169bbc81569")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

count_bad Ran
ran on a synthesized input
husthuaan/AAT/eval_utils.py
code served (permissive licence) · get_code("0a4de8f498e3e70c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    'sen': 'the quick brown fox jumps over the dog'
}
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 int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
encode_captions Ran
ran; our contract draft was wrong, not the code
ruotianluo/GoogleConceptualCaptioning/scripts/prepro_labels.py
code served (permissive licence) · get_code("4aad8242843ac47b")
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. 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 numpy as np

# Create sample images with captions
imgs = [
    {
        'final_captions': [
            ['hello', 'world', 'this', 'is', 'caption', 'one'],
            ['another', 'caption', 'here'],
            ['third', 'caption', 'for', 'image', 'one']
        ]
    },
    {
        'final_captions': [
            ['first', 'caption', 'image', 'two'],
            ['second', 'caption', 'different', 'words']
        ]
    }
]

# Create params dict
params = {
    'max_length': 10
}

# Create word to index mapping
wtoi = {
    'hello': 1,
    'world': 2,
    'this': 3,
    'is': 4,
    'caption': 5,
    'one': 6,
    'another': 7,
    'here': 8,
    'third': 9,
    'for': 10,
    'image': 11,
    'first': 12,
    'two': 13,
    'second': 14,
    'different': 15,
    'words': 16
}

ARGS = {
    'imgs': imgs,
    'params': params,
    'wtoi': wtoi
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
pack_wrapper Ran
ran; our contract draft was wrong, not the code
husthuaan/AAT/models/AttModel.py
code served (permissive licence) · get_code("d2379d710eedc4ae")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 5, 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
import torch.nn as nn
from torch.nn.utils.rnn import PackedSequence, pack_padded_sequence, pad_packed_sequence

torch.manual_seed(0)

# Create a simple module that processes packed sequences
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        # x is the data from a PackedSequence
        return self.linear(x)

# Create test data
batch_size = 2
feature_dim = 4
max_seq_len = 5

# att_feats: (batch_size, max_seq_len, feature_dim)
att_feats = torch.randn(batch_size, max_seq_len, feature_dim)

# att_masks: (batch_size, max_seq_len) with 1s for valid positions, 0s for padding
# Different lengths for each sample: first has 5 valid, second has 3 valid
att_masks = torch.tensor([
    [1, 1, 1, 1, 1],
    [1, 1, 1, 0, 0]
], dtype=torch.float32)

# Create module
module = SimpleModule()

ARGS = {
    "module": module,
    "att_feats": att_feats,
    "att_masks": att_masks
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 5, 4) — shape (2, 5, 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
pad_unsort_packed_sequence Ran
ran; our contract draft was wrong, not the code
husthuaan/AAT/models/AttModel.py
code served (permissive licence) · get_code("bfac58a04b6835f5")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 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
from torch.nn.utils.rnn import pack_padded_sequence

torch.manual_seed(0)

# Create a simple packed sequence
# We need: batch_size=2, sequence_length=4, input_size=3
batch_size = 2
seq_length = 4
input_size = 3

# Create input tensor (seq_length, batch_size, input_size)
data = torch.randn(seq_length, batch_size, input_size)

# Create lengths for each sequence in the batch
lengths = torch.tensor([4, 3], dtype=torch.long)

# Pack the sequence
packed_input = pack_padded_sequence(data, lengths, enforce_sorted=False)

# Create inverse indices for unsorting
# pack_padded_sequence with enforce_sorted=False returns sorted_indices
# We need the inverse permutation to unsort
sorted_indices = packed_input.sorted_indices
inv_ix = torch.argsort(sorted_indices)

ARGS = {
    "input": packed_input,
    "inv_ix": inv_ix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 4, 3) — shape (2, 4, 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
resnet18 Ran
ran; our contract draft was wrong, not the code
husthuaan/AAT/misc/resnet.py
code served (permissive licence) · get_code("2b17380e9938d559")
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 ResNet. 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
from torchvision.models.resnet import BasicBlock

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet34 Ran
ran; our contract draft was wrong, not the code
husthuaan/AAT/misc/resnet.py
code served (permissive licence) · get_code("d206d964368eeb24")
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 ResNet. 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
import torchvision.models.resnet
from torchvision.models.resnet import BasicBlock

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet50 Ran
ran; our contract draft was wrong, not the code
husthuaan/AAT/misc/resnet.py
code served (permissive licence) · get_code("fade30a7dab7a039")
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 ResNet. 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
from torchvision.models.resnet import Bottleneck
import torchvision.models.resnet

torch.manual_seed(0)

ARGS = {
    'pretrained': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
sort_pack_padded_sequence Ran
ran; our contract draft was wrong, not the code
husthuaan/AAT/models/AttModel.py
code served (permissive licence) · get_code("e56d2f9cbd9cb8b1")
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) and returned tuple. 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
from torch.nn.utils.rnn import pack_padded_sequence

torch.manual_seed(0)

# Create a small batch of padded sequences
# batch_size=2, max_seq_length=3, embedding_dim=4
batch_size = 2
max_seq_length = 3
embedding_dim = 4

input_tensor = torch.randn(batch_size, max_seq_length, embedding_dim)
lengths = torch.tensor([3, 2], dtype=torch.long)

ARGS = {
    "input": input_tensor,
    "lengths": lengths,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
subsequent_mask Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from ruotianluo/Transformer_Captioning
pointer only; the stored copy get_code serves, from ruotianluo/Transformer_Captioning, is pointer only (licence: NONE) · get_code("dd03765c7da9ca51")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

language_eval Not yet run
unverified (harvested, no recorded run)
husthuaan/AAT/eval_utils.py
code served (permissive licence) · get_code("06b72839dcd7433f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 11 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 11 later) and 2 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
clones 79 other papers
1 dated earlier, 78 later · 11 only as an assembly brick
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1706.03762 (2017-06)
Attention Is All You Need
1707.07998 (2017-07)
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
and 76 more not named here
attention 27 other papers
2 dated earlier, 25 later
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1609.08144 (2016-09)
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
1706.03762 (2017-06)
Attention Is All You Need
and 24 more not named here
subsequent_mask 21 other papers
1 dated earlier, 20 later
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1707.07998 (2017-07)
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
1905.12926 (2019-05)
Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
and 18 more not named here
pad_unsort_packed_sequence 14 other papers
14 later · 2 only as an assembly brick
1707.07998 (2017-07)
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
1906.05963 (2019-06)
Image Captioning: Transforming Objects into Words
1908.06954 (2019-08)
Attention on Attention for Image Captioning
and 11 more not named here
pack_wrapper 13 other papers
13 later · 2 only as an assembly brick
1707.07998 (2017-07)
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
1906.05963 (2019-06)
Image Captioning: Transforming Objects into Words
1908.06954 (2019-08)
Attention on Attention for Image Captioning
and 10 more not named here
sort_pack_padded_sequence 10 other papers
10 later · 2 only as an assembly brick
1707.07998 (2017-07)
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
1906.05963 (2019-06)
Image Captioning: Transforming Objects into Words
1908.06954 (2019-08)
Attention on Attention for Image Captioning
and 7 more not named here
resnet18 9 other papers
1 dated earlier, 8 later
1605.06409 (2016-05)
R-FCN: Object Detection via Region-based Fully Convolutional Networks
1803.09845 (2018-03)
Neural Baby Talk
1804.09160 (2018-04)
No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
and 6 more not named here
resnet34 9 other papers
1 dated earlier, 8 later
1605.06409 (2016-05)
R-FCN: Object Detection via Region-based Fully Convolutional Networks
1803.09845 (2018-03)
Neural Baby Talk
1804.09160 (2018-04)
No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
and 6 more not named here
resnet50 5 other papers
5 later
1906.05963 (2019-06)
Image Captioning: Transforming Objects into Words
1908.06954 (2019-08)
Attention on Attention for Image Captioning
2004.00390 (2020-04)
More Grounded Image Captioning by Distilling Image-Text Matching Model
and 2 more not named here
count_bad 4 other papers
4 later
1908.06954 (2019-08)
Attention on Attention for Image Captioning
2002.12204 (2020-02)
Visual Commonsense R-CNN
2004.00390 (2020-04)
More Grounded Image Captioning by Distilling Image-Text Matching Model
and 1 more not named here
language_eval 3 other papers
3 later
1908.06954 (2019-08)
Attention on Attention for Image Captioning
2002.12204 (2020-02)
Visual Commonsense R-CNN
aaai_29097 (2024 (year only))
Noise-Aware Image Captioning with Progressively Exploring Mismatched Words

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

More are linked than shown here.

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

Abstract

Recently it has been shown that policy-gradient methods for reinforcement learning can be utilized to train deep end-to-end systems directly on non-differentiable metrics for the task at hand. In this paper we consider the problem of optimizing image captioning systems using reinforcement learning, and show that by carefully optimizing our systems using the test metrics of the MSCOCO task, significant gains in performance can be realized. Our systems are built using a new optimization approach that we call self-critical sequence training (SCST). SCST is a form of the popular REINFORCE algorithm that, rather than estimating a "baseline" to normalize the rewards and reduce variance, utilizes the output of its own test-time inference algorithm to normalize the rewards it experiences. Using this approach, estimating the reward signal (as actor-critic methods must do) and estimating normalization (as REINFORCE algorithms typically do) is avoided, while at the same time harmonizing the model with respect to its test-time inference procedure. Empirically we find that directly optimizing the CIDEr metric with SCST and greedy decoding at test-time is highly effective. Our results on the MSCOCO evaluation sever establish a new state-of-the-art on the task, improving the best result in terms of CIDEr from 104.9 to 114.7.

For agents

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

get_harvested_code_for_paper("1612.00563")
get_code_for_paper("1612.00563")
have("1612.00563")

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

curl https://syntology.ai/api/ran/1612.00563.json

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

[![Syntology run record](https://syntology.ai/api/ran/1612.00563.svg)](https://syntology.ai/paper/1612.00563)

Connect an agent — have() is free.