SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.09845 · 2018

Neural Baby Talk

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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 3 have no contract verdict; 3 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/1803.09845.json · badge: /api/ran/1803.09845.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
jiasenlu/NeuralBabyTalk canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
bbox_transform Ran
ran on a synthesized input
jiasenlu/NeuralBabyTalk/misc/bbox_transform.py
code served (permissive licence) · get_code("c40b904771c8885b")
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)

# Bounding boxes are expected to be in format [x1, y1, x2, y2]
# Create small example anchor/exemplar ROIs (batch_size=2, 4 coordinates each)
ex_rois = torch.tensor([
    [10.0, 20.0, 50.0, 80.0],
    [100.0, 120.0, 200.0, 250.0]
], dtype=torch.float32)

# Create small example ground truth ROIs (batch_size=2, 4 coordinates each)
gt_rois = torch.tensor([
    [15.0, 25.0, 55.0, 85.0],
    [105.0, 125.0, 205.0, 255.0]
], dtype=torch.float32)

ARGS = {
    "ex_rois": ex_rois,
    "gt_rois": gt_rois
}
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
bbox_transform_batch Ran
ran on a synthesized input
jiasenlu/NeuralBabyTalk/misc/bbox_transform.py
code served (permissive licence) · get_code("a7445d60b800441b")
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, 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)

# Case 1: ex_rois is 2D, gt_rois is 3D
# ex_rois: (num_rois, 4) - bounding boxes [x1, y1, x2, y2]
# gt_rois: (num_gt, num_rois, 4) - ground truth boxes

ex_rois_2d = torch.tensor([
    [10.0, 20.0, 50.0, 80.0],
    [15.0, 25.0, 60.0, 90.0]
], dtype=torch.float32)

gt_rois_3d = torch.tensor([
    [
        [12.0, 22.0, 52.0, 82.0],
        [17.0, 27.0, 62.0, 92.0]
    ],
    [
        [11.0, 21.0, 51.0, 81.0],
        [16.0, 26.0, 61.0, 91.0]
    ]
], dtype=torch.float32)

ARGS = {
    "ex_rois": ex_rois_2d,
    "gt_rois": gt_rois_3d
}
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, 2, 4) — shape (2, 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
bbox_transform_inv Ran
ran on a synthesized input
jiasenlu/NeuralBabyTalk/misc/bbox_transform.py
code served (permissive licence) · get_code("826e6d34ae25c870")
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, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - boxes: 3D array/tensor with shape (batch_size, num_boxes, 4)
#   Used with indexing [:, :, 0], [:, :, 1], [:, :, 2], [:, :, 3]
#   and .unsqueeze(2) operations
# - deltas: 3D array/tensor with shape (batch_size, num_boxes, 4*k)
#   where k is number of classes. Used with [:, :, 0::4], [:, :, 1::4], etc.
#   and .clone() method
# - batch_size: integer

batch_size = 2
num_boxes = 3
num_classes = 2

# boxes shape: (batch_size, num_boxes, 4)
# Each box is [x1, y1, x2, y2]
boxes = torch.tensor([
    [[10.0, 20.0, 50.0, 60.0],
     [15.0, 25.0, 55.0, 65.0],
     [5.0, 10.0, 45.0, 55.0]],
    [[12.0, 22.0, 52.0, 62.0],
     [18.0, 28.0, 58.0, 68.0],
     [8.0, 12.0, 48.0, 58.0]]
])

# deltas shape: (batch_size, num_boxes, 4*num_classes)
# Contains 4 delta values per class (dx, dy, dw, dh)
deltas = torch.tensor([
    [[0.1, 0.05, 0.02, 0.03, 0.15, 0.08, 0.01, 0.02],
     [0.12, 0.06, 0.025, 0.035, 0.14, 0.07, 0.015, 0.025],
     [0.08, 0.04, 0.018, 0.028, 0.16, 0.09, 0.005, 0.015]],
    [[0.11, 0.055, 0.022, 0.032, 0.145, 0.075, 0.012, 0.022],
     [0.13, 0.065, 0.027, 0.037, 0.135, 0.065, 0.017, 0.027],
     [0.09, 0.045, 0.02, 0.03, 0.155, 0.085, 0.008, 0.018]]
])

ARGS = {
    "boxes": boxes,
    "deltas": deltas,
    "batch_size": batch_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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, 8) — shape (2, 3, 8) 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
jiasenlu/NeuralBabyTalk/misc/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

resnet18 Ran
ran; our contract draft was wrong, not the code
jiasenlu/NeuralBabyTalk/misc/resnet.py
code served (permissive licence) · get_code("6fbbfc8d57192c2c")
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

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 — 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
jiasenlu/NeuralBabyTalk/misc/resnet.py
code served (permissive licence) · get_code("100ec7cb24c5c7c1")
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

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 — 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
language_eval Not yet run
unverified (harvested, no recorded run)
jiasenlu/NeuralBabyTalk/misc/eval_utils.py
code served (permissive licence) · get_code("5b9a79b23faa9bb1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 3 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
conv3x3 686 other papers
37 dated earlier, 8 the same month, 641 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
resnet18 9 other papers
2 dated earlier, 7 later
1605.06409 (2016-05)
R-FCN: Object Detection via Region-based Fully Convolutional Networks
1612.00563 (2016-12)
Self-critical Sequence Training for Image Captioning
1804.09160 (2018-04)
No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
and 6 more not named here
resnet34 9 other papers
2 dated earlier, 7 later
1605.06409 (2016-05)
R-FCN: Object Detection via Region-based Fully Convolutional Networks
1612.00563 (2016-12)
Self-critical Sequence Training for Image Captioning
1804.09160 (2018-04)
No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
and 6 more not named here

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

We introduce a novel framework for image captioning that can produce natural language explicitly grounded in entities that object detectors find in the image. Our approach reconciles classical slot filling approaches (that are generally better grounded in images) with modern neural captioning approaches (that are generally more natural sounding and accurate). Our approach first generates a sentence `template' with slot locations explicitly tied to specific image regions. These slots are then filled in by visual concepts identified in the regions by object detectors. The entire architecture (sentence template generation and slot filling with object detectors) is end-to-end differentiable. We verify the effectiveness of our proposed model on different image captioning tasks. On standard image captioning and novel object captioning, our model reaches state-of-the-art on both COCO and Flickr30k datasets. We also demonstrate that our model has unique advantages when the train and test distributions of scene compositions -- and hence language priors of associated captions -- are different. Code has been made available at: https://github.com/jiasenlu/NeuralBabyTalk

For agents

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

get_harvested_code_for_paper("1803.09845")
get_code_for_paper("1803.09845")
have("1803.09845")

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

curl https://syntology.ai/api/ran/1803.09845.json

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

[![Syntology run record](https://syntology.ai/api/ran/1803.09845.svg)](https://syntology.ai/paper/1803.09845)

Connect an agent — have() is free.