SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.14310 · 2020

Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure 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/2005.14310.json · badge: /api/ran/2005.14310.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
cvlab-stonybrook/Scanpath_Prediction canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
calcangle Ran
ran; our contract draft was wrong, not the code
cvlab-stonybrook/Scanpath_Prediction/irl_dcb/multimatch.py
pointer only (licence: MIT); the stored copy get_code serves, from hkust-nisl/oat_eccv24, is pointer only (licence: NONE) · get_code("f495c083c4b62415")
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 hkust-nisl/oat_eccv24, 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.

cart2pol Ran
ran, honoured the contract we drafted
cvlab-stonybrook/Scanpath_Prediction/irl_dcb/multimatch.py
pointer only (licence: MIT); the stored copy get_code serves, from hkust-nisl/oat_eccv24, is pointer only (licence: NONE) · get_code("583e0bc15a6d0763")
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 hkust-nisl/oat_eccv24, 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.

convert_coordinate Ran
ran on a synthesized input
cvlab-stonybrook/Scanpath_Prediction/plot_scanpath.py
code served (permissive licence) · get_code("6a761592bad486a7")
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 2, 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)

# The function convert_coordinate takes:
# X - x coordinate of the fixations (numeric)
# Y - y coordinate of the fixations (numeric)
# im_w - image width (numeric)
# im_h - image height (numeric)

# These can be scalars, lists, or numpy arrays based on the operations performed
# The function performs arithmetic operations on X and Y

ARGS = {
    "X": np.array([100.0, 200.0, 300.0]),
    "Y": np.array([150.0, 250.0, 350.0]),
    "im_w": 800,
    "im_h": 600,
}
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 tuple, ndim 2, 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
gen_scanpath_structure Ran
ran on a synthesized input
cvlab-stonybrook/Scanpath_Prediction/irl_dcb/multimatch.py
code served (permissive licence) · get_code("a48371b91bd100e7")
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 OrderedDict. 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
import collections

# Create a small record array with fixation data
# Each row is (start_x, start_y, duration)
data = np.array([
    (100.0, 200.0, 250),
    (150.0, 180.0, 300),
    (120.0, 220.0, 275),
    (200.0, 150.0, 350)
], dtype=[('x', 'f8'), ('y', 'f8'), ('duration', 'i4')])

# Convert to array format that the function expects (nx3)
data_array = np.array([
    [100.0, 200.0, 250],
    [150.0, 180.0, 300],
    [120.0, 220.0, 275],
    [200.0, 150.0, 350]
])

ARGS = {
    'data': data_array
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
pred2feat Ran
ran on a synthesized input
cvlab-stonybrook/Scanpath_Prediction/extract_DCBs_demo.py
code served (permissive licence) · get_code("e4c0b7d9c92f02c6")
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 (134, 20, 32) 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.functional as F

torch.manual_seed(0)

# seg should be a tensor with shape [height, width]
# The function checks seg == pred['id'] and expects integer values
seg = torch.randint(0, 10, (320, 512))

# info is a list of dicts, each containing:
# - 'id': integer id to match against seg
# - 'isthing': boolean flag
# - 'category_id': integer in range [0, 80) for things or [0, 54) for stuff
# - 'score': float score (used when isthing is True)

info = [
    {
        'id': 1,
        'isthing': True,
        'category_id': 5,
        'score': 0.9
    },
    {
        'id': 2,
        'isthing': False,
        'category_id': 10,
        'score': 0.8
    },
    {
        'id': 3,
        'isthing': True,
        'category_id': 15,
        'score': 0.7
    }
]

ARGS = {
    'seg': seg,
    'info': info
}
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 (134, 20, 32) — shape (134, 20, 32) 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
scanpath2clusters Ran
ran on a synthesized input
cvlab-stonybrook/Scanpath_Prediction/irl_dcb/metrics.py
code served (permissive licence) · get_code("f68bdca5bedf95f1")
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 torch
import numpy as np
from sklearn.cluster import MeanShift

# Create a simple MeanShift model
meanshift = MeanShift(bandwidth=0.5)

# Train it on some dummy 2D data
training_data = np.array([
    [0.0, 0.0],
    [0.1, 0.1],
    [5.0, 5.0],
    [5.1, 5.1]
])
meanshift.fit(training_data)

# Create a scanpath dict with X and Y coordinates
scanpath = {
    'X': [0.05, 5.05],
    'Y': [0.05, 5.05]
}

ARGS = {
    'meanshift': meanshift,
    'scanpath': scanpath
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, 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 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
build Not yet run
unverified (harvested, no recorded run)
cvlab-stonybrook/Scanpath_Prediction/irl_dcb/builder.py
code served (permissive licence) · get_code("06e89ab5539e3aae")
How it ran

no invocation recorded.

compute_mm Not yet run
unverified (harvested, no recorded run)
cvlab-stonybrook/Scanpath_Prediction/irl_dcb/metrics.py
code served (permissive licence) · get_code("fdf8b58a70477c91")
How it ran

no invocation recorded.

get_DCBs Not yet run
unverified (harvested, no recorded run)
cvlab-stonybrook/Scanpath_Prediction/extract_DCBs_demo.py
code served (permissive licence) · get_code("2a5028d22f350324")
How it ran

no invocation recorded.

multimatch Not yet run
unverified (harvested, no recorded run)
cvlab-stonybrook/Scanpath_Prediction/irl_dcb/metrics.py
code served (permissive licence) · get_code("8d3693df283e426d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
calcangle 1 other paper
1 later
2407.13335 (2024-07)
OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction
cart2pol 1 other paper
1 later
2407.13335 (2024-07)
OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction

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

Being able to predict human gaze behavior has obvious importance for behavioral vision and for computer vision applications. Most models have mainly focused on predicting free-viewing behavior using saliency maps, but these predictions do not generalize to goal-directed behavior, such as when a person searches for a visual target object. We propose the first inverse reinforcement learning (IRL) model to learn the internal reward function and policy used by humans during visual search. The viewer's internal belief states were modeled as dynamic contextual belief maps of object locations. These maps were learned by IRL and then used to predict behavioral scanpaths for multiple target categories. To train and evaluate our IRL model we created COCO-Search18, which is now the largest dataset of high-quality search fixations in existence. COCO-Search18 has 10 participants searching for each of 18 target-object categories in 6202 images, making about 300,000 goal-directed fixations. When trained and evaluated on COCO-Search18, the IRL model outperformed baseline models in predicting search fixation scanpaths, both in terms of similarity to human search behavior and search efficiency. Finally, reward maps recovered by the IRL model reveal distinctive target-dependent patterns of object prioritization, which we interpret as a learned object context.

For agents

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

get_harvested_code_for_paper("2005.14310")
get_code_for_paper("2005.14310")
have("2005.14310")

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

curl https://syntology.ai/api/ran/2005.14310.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.14310.svg)](https://syntology.ai/paper/2005.14310)

Connect an agent — have() is free.