SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1611.09571 · 2016

Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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; 6 failures of our instrument; 2 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/1611.09571.json · badge: /api/ran/1611.09571.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
chenxy99/ANOC canonical (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
marcellacornia/sam canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
cook_refs Ran
ran; our contract draft was wrong, not the code
chenxy99/ANOC/evaluation/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_refs Ran
ran; our contract draft was wrong, not the code
chenxy99/ANOC/evaluation/cider/cider_scorer.py
code served (permissive licence) · get_code("26e17b0aeb64b34c")
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
import numpy as np
from collections import defaultdict

# Define ARGS dictionary with valid arguments for cook_refs function
ARGS = {
    "refs": [
        "the quick brown fox jumps over the lazy dog",
        "a fast brown fox leaps over a lazy dog",
        "the quick fox jumps over the dog"
    ],
    "n": 4
}
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 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_test Ran
ran; our contract draft was wrong, not the code
chenxy99/ANOC/evaluation/bleu/bleu_scorer.py
pointer only (licence: MIT); the stored copy get_code serves, from div290/capeen, is pointer only (licence: NONE) · get_code("f5741ff28f6cb706")
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 div290/capeen, 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.

cook_test Ran
ran; our contract draft was wrong, not the code
chenxy99/ANOC/evaluation/cider/cider_scorer.py
code served (permissive licence) · get_code("7cb89de9e327ddab")
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 defaultdict. 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 collections import defaultdict

# Set seed for reproducibility
torch.manual_seed(0)

# The function cook_test takes:
# - test: a string (hypothesis sentence)
# - n: int (number of ngrams)

# Analyzing the function body:
# - test is passed to precook()
# - precook() calls test.split(), so test must be a string
# - n is used as an integer in range operations

ARGS = {
    "test": "the quick brown fox jumps over the lazy dog",
    "n": 4
}
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 defaultdict — a defaultdict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a defaultdict 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
padding Ran
ran on a synthesized input
marcellacornia/sam/utilities.py
code served (permissive licence) · get_code("1acb8a8dcd261c91")
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 3, dtype family int, shape (240, 320, 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 cv2
import numpy as np

# Create a small test image
# Using a 3-channel image (RGB-like)
test_img = np.random.randint(0, 256, (120, 160, 3), dtype=np.uint8)

# Define arguments for the padding function
ARGS = {
    'img': test_img,
    'shape_r': 240,
    'shape_c': 320,
    'channels': 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (240, 320, 3) — shape (240, 320, 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
padding_fixation Ran
ran on a synthesized input
marcellacornia/sam/utilities.py
code served (permissive licence) · get_code("0559b73378d917c0")
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 (480, 640) 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

# Create a small test fixation image with some non-zero values
# The image represents fixation points as 1s in a sparse matrix
img = np.zeros((60, 80))  # Smaller original image
img[10, 15] = 1
img[20, 30] = 1
img[40, 50] = 1
img[55, 75] = 1

ARGS = {
    'img': img,
    'shape_r': 480,
    'shape_c': 640
}
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 (480, 640) — shape (480, 640) 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
chenxy99/ANOC/evaluation/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
chenxy99/ANOC/evaluation/cider/cider_scorer.py
code served (permissive licence) · get_code("ca007f4b8a45fbdc")
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 defaultdict. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:14:48Z. 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

ARGS = {
    "s": "The quick brown fox jumps over the lazy dog",
    "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 defaultdict — a defaultdict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a defaultdict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
resize_fixation Ran
ran on a synthesized input
marcellacornia/sam/utilities.py
code served (permissive licence) · get_code("e649b7132806203b")
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 (480, 640) 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

# Create a small fixation map (non-zero entries represent fixation points)
img = np.array([
    [0, 1, 0, 0],
    [1, 0, 0, 1],
    [0, 0, 1, 0]
], dtype=float)

ARGS = {
    "img": img,
    "rows": 480,
    "cols": 640
}
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 (480, 640) — shape (480, 640) 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
repeat Not yet run
unverified (harvested, no recorded run)
marcellacornia/sam/models.py
code served (permissive licence) · get_code("df2a675b7aae0379")
How it ran

no invocation recorded.

repeat_shape Not yet run
unverified (harvested, no recorded run)
marcellacornia/sam/models.py
code served (permissive licence) · get_code("fd941100c3da25aa")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 6 later) and 5 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
5 dated earlier, 20 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
precook 22 other papers
2 dated earlier, 1 the same month, 19 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
1 dated earlier, 1 the same month, 19 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
1806.00807 (2018-06)
Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
and 18 more not named here
precook 4 other papers
4 later
1804.08771 (2018-04)
A Call for Clarity in Reporting BLEU Scores
1912.08226 (2019-12)
Meshed-Memory Transformer for Image Captioning
ijcai2022_0224 (2022 (year only))
S 2 Transformer for Image Captioning
and 1 more not named here
cook_test 3 other papers
3 later
1912.08226 (2019-12)
Meshed-Memory Transformer for Image Captioning
ijcai2022_0224 (2022 (year only))
S 2 Transformer for Image Captioning
2410.04433 (2024-10)
CAPEEN: Image Captioning with Early Exits and Knowledge Distillation
cook_test 2 other papers
2 later
1912.08226 (2019-12)
Meshed-Memory Transformer for Image Captioning
2606.28044 (2026-06)
A Tree-of-Thoughts Hybrid Approach for Legal Case Judgement Summarization using LLMs

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

Data-driven saliency has recently gained a lot of attention thanks to the use of Convolutional Neural Networks for predicting gaze fixations. In this paper we go beyond standard approaches to saliency prediction, in which gaze maps are computed with a feed-forward network, and present a novel model which can predict accurate saliency maps by incorporating neural attentive mechanisms. The core of our solution is a Convolutional LSTM that focuses on the most salient regions of the input image to iteratively refine the predicted saliency map. Additionally, to tackle the center bias typical of human eye fixations, our model can learn a set of prior maps generated with Gaussian functions. We show, through an extensive evaluation, that the proposed architecture outperforms the current state of the art on public saliency prediction datasets. We further study the contribution of each key component to demonstrate their robustness on different scenarios.

For agents

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

get_harvested_code_for_paper("1611.09571")
get_code_for_paper("1611.09571")
have("1611.09571")

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

curl https://syntology.ai/api/ran/1611.09571.json

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

[![Syntology run record](https://syntology.ai/api/ran/1611.09571.svg)](https://syntology.ai/paper/1611.09571)

Connect an agent — have() is free.