SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.09188 · 2020

Detecting natural disasters, damage, and incidents in the wild

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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 9 have no contract verdict; 0 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/2008.09188.json · badge: /api/ran/2008.09188.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
ethanweber/IncidentsDataset community (classifier label)
classifier basis not recorded on the link
10 ran · 2 no recorded run
FunctionStatusWhere it lives
decode_base64 Ran
ran on a synthesized input
ethanweber/IncidentsDataset/run_demo_server.py
code served (permissive licence) · get_code("7d5ba557296e35b7")
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 bytes. 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 base64
import re

# The function decode_base64 takes two parameters:
# 1. data: Base64 data as an ASCII byte string
# 2. altchars: Alternative characters for base64 alphabet (default b'+/')

# Create valid base64 encoded data
# Let's encode a simple string to get valid base64
original_data = b"Hello, World!"
encoded_data = base64.b64encode(original_data)

ARGS = {
    "data": encoded_data,
    "altchars": b'+/'
}
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 bytes — a bytes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a bytes 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
get_incident_layer Ran
ran on a synthesized input
ethanweber/IncidentsDataset/architectures.py
code served (permissive licence) · get_code("4e77041bd9871828")
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 Linear. 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)

class Args:
    def __init__(self, activation, fc_dim, num_incidents):
        self.activation = activation
        self.fc_dim = fc_dim
        self.num_incidents = num_incidents

ARGS = {
    'args': Args(activation='softmax', fc_dim=8, num_incidents=5)
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
get_loaded_json_file Ran
ran on a synthesized input
ethanweber/IncidentsDataset/utils.py
code served (permissive licence) · get_code("ae8d3a9a2fe8ac53")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with valid test data
temp_dir = tempfile.mkdtemp()
json_path = os.path.join(temp_dir, "test_data.json")

test_data = {
    "name": "test",
    "value": 42,
    "items": [1, 2, 3],
    "nested": {"key": "value"}
}

with open(json_path, 'w') as fp:
    json.dump(test_data, fp)

ARGS = {
    "path": json_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_loaded_pickle_file Ran
ran on a synthesized input
ethanweber/IncidentsDataset/utils.py
code served (permissive licence) · get_code("ec930c6d5744dbc2")
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 dict. 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 pickle
import tempfile
import os

# Create a temporary file with pickled data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_pickle.pkl")

# Create some simple test data
test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "dict"}
}

# Write the test data to a pickle file
with open(temp_file, 'wb') as f:
    pickle.dump(test_data, f)

ARGS = {
    "path": temp_file
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_loss Ran
ran on a synthesized input
ethanweber/IncidentsDataset/loss.py
code served (permissive licence) · get_code("480f759020fc42a0")
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. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

class Args:
    def __init__(self):
        self.activation = 'sigmoid'

# Create arguments
args = Args()

# Create small tensors for incident task
# batch_size=2, num_classes=4
incident_output = torch.randn(2, 4)
incident_target = torch.randint(0, 2, (2, 4)).float()
incident_weight = torch.ones(2, 4)

# Create small tensors for place task
# batch_size=2, num_classes=3
place_output = torch.randn(2, 3)
place_target = torch.randint(0, 2, (2, 3)).float()
place_weight = torch.ones(2, 3)

ARGS = {
    'args': args,
    'incident_output': incident_output,
    'incident_target': incident_target,
    'incident_weight': incident_weight,
    'place_output': place_output,
    'place_target': place_target,
    'place_weight': place_weight
}
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 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
get_place_layer Ran
ran on a synthesized input
ethanweber/IncidentsDataset/architectures.py
code served (permissive licence) · get_code("022cdf6755846617")
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 Linear. 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)

class Args:
    def __init__(self, activation, fc_dim, num_places):
        self.activation = activation
        self.fc_dim = fc_dim
        self.num_places = num_places

ARGS = {
    'args': Args(activation='softmax', fc_dim=128, num_places=50)
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
get_postprocessed_args Ran
ran on a synthesized input
ethanweber/IncidentsDataset/parser.py
code served (permissive licence) · get_code("5a95e11db374d7a1")
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 Namespace. 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 argparse

# Create a simple argparse.Namespace object with various string values
# that should be converted to booleans and left as-is
args = argparse.Namespace()

# Test case 1: string 'True' should become boolean True
setattr(args, 'flag_true', 'True')

# Test case 2: string 'False' should become boolean False
setattr(args, 'flag_false', 'False')

# Test case 3: other string values should remain unchanged
setattr(args, 'model_name', 'bert-base')

# Test case 4: numeric value should remain unchanged
setattr(args, 'learning_rate', 0.001)

# Test case 5: another True string
setattr(args, 'use_cuda', 'False')

# Test case 6: integer should remain unchanged
setattr(args, 'batch_size', 32)

ARGS = {'args': args}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
get_vectors Ran
ran on a synthesized input
ethanweber/IncidentsDataset/dataset.py
code served (permissive licence) · get_code("1b51934f01834a09")
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 numpy as np

# Construct valid arguments for get_vectors function
data = {
    "flood": 1,
    "earthquake": 0,
    "wildfire": 1
}

to_index_mapping = {
    "flood": 0,
    "earthquake": 1,
    "wildfire": 2,
    "no_incident": 3
}

vector_len = 4

ARGS = {
    "data": data,
    "to_index_mapping": to_index_mapping,
    "vector_len": vector_len
}
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 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
image_loader Ran
ran on a synthesized input
ethanweber/IncidentsDataset/dataset.py
code served (permissive licence) · get_code("0743a298e2f5cc0b")
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 Image. 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 numpy as np
from PIL import Image
import io
import tempfile
import os

# Create a temporary image file
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a simple RGB image and save it
img = Image.new('RGB', (4, 3), color=(255, 0, 0))
img.save(temp_image_path)

ARGS = {
    "filename": temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
is_image_file Ran
ran, violated the contract we drafted
ethanweber/IncidentsDataset/dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from ermongroup/fairgen, is pointer only (licence: NONE) · get_code("4e6a8faaf8e44abe")
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 ermongroup/fairgen, 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.

batched_index_select Not yet run
unverified (harvested, no recorded run)
ethanweber/IncidentsDataset/metrics.py
code served (permissive licence) · get_code("ece732ae6abd28b6")
How it ran

no invocation recorded.

get_trunk_model Not yet run
unverified (harvested, no recorded run)
ethanweber/IncidentsDataset/architectures.py
code served (permissive licence) · get_code("b283e847f417052d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 11 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
is_image_file 22 other papers
10 dated earlier, 1 the same month, 11 later
1406.2661 (2014-06)
Generative Adversarial Networks
1603.08511 (2016-03)
Colorful Image Colorization
1805.08318 (2018-05)
Self-Attention Generative Adversarial Networks
and 19 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

Responding to natural disasters, such as earthquakes, floods, and wildfires, is a laborious task performed by on-the-ground emergency responders and analysts. Social media has emerged as a low-latency data source to quickly understand disaster situations. While most studies on social media are limited to text, images offer more information for understanding disaster and incident scenes. However, no large-scale image datasets for incident detection exists. In this work, we present the Incidents Dataset, which contains 446,684 images annotated by humans that cover 43 incidents across a variety of scenes. We employ a baseline classification model that mitigates false-positive errors and we perform image filtering experiments on millions of social media images from Flickr and Twitter. Through these experiments, we show how the Incidents Dataset can be used to detect images with incidents in the wild. Code, data, and models are available online at http://incidentsdataset.csail.mit.edu.

For agents

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

get_harvested_code_for_paper("2008.09188")
get_code_for_paper("2008.09188")
have("2008.09188")

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

curl https://syntology.ai/api/ran/2008.09188.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.09188.svg)](https://syntology.ai/paper/2008.09188)

Connect an agent — have() is free.