SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.18591 · NeurIPS · 2024

Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation Forecasting

Nicolas Longépé, Brandon Victor, Mathilde Letard, Peter Naylor, Karim Douch, Zhen He, Patrick Ebel

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 1 honoured the contract we drafted, 3 violated it and 0 have no contract verdict; 4 failures 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/2409.18591.json · badge: /api/ran/2409.18591.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
multihuntr/gff canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
Multihuntr/GFF canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
default Ran
ran, violated the contract we drafted
multihuntr/gff/gff/models/metnet.py
pointer only (licence: CC0-1.0); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (CC0-1.0), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, 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.

degrees_to_north_east Ran
ran; our contract draft was wrong, not the code
multihuntr/gff/gff/data_sources.py
code served (permissive licence) · get_code("16c3ede85ffafb6c")
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.

import torch

torch.manual_seed(0)

# Analyze the function:
# degrees_to_north_east(north: int, east: int)
# - Takes two integer parameters: north and east
# - Calls degrees_to_char(north, east) which processes them
# - Returns formatted strings based on the cardinal directions

ARGS = {
    'north': 45,
    'east': 120
}
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, 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
exists Ran
ran, violated the contract we drafted
multihuntr/gff/gff/models/metnet.py
pointer only (licence: CC0-1.0); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (CC0-1.0), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, 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.

fname_is_ks Ran
ran, violated the contract we drafted
Multihuntr/GFF/evaluate.py
code served (permissive licence) · get_code("29c326c742907405")
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 bool, ndim 0, dtype family float, 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 re

# The function expects a string parameter 'fname' and checks if it matches a pattern
# Pattern: \d{3}-\d{1,2}- which means 3 digits, hyphen, 1-2 digits, hyphen

# Valid example: "123-4-something.txt" or "999-12-file.dat"
fname_valid = "123-4-example.txt"

# We can also test with an invalid one, but let's use a valid one for the setup
ARGS = {
    'fname': fname_valid
}
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 bool, ndim 0, dtype family float, 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
get_norms Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
multihuntr/gff/gff/models/creation.py
code served (permissive licence) · get_code("a51fbb464176d09c")
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 torch
import tempfile
from pathlib import Path
from unittest.mock import MagicMock, patch
import pandas as pd

torch.manual_seed(0)

# Create a minimal config dictionary
C = {
    'data_folder': '/tmp/data',
    'data_sources': ['era5', 'era5_land', 'glofas', 'hydroatlas_basin', 'dem_local', 'hand', 's1'],
    'era5_keys': ['temperature', 'pressure'],
    'era5_land_keys': ['soil_moisture'],
    'glofas_keys': ['discharge'],
    'hydroatlas_keys': ['slope', 'elevation'],
    'fold': 'train',
}

# Mock the gff.normalisation module
mock_normalisation = MagicMock()

def create_norm_dict(num_features):
    """Create a mock norm dict with mean and std DataFrames"""
    norm_dict = {
        'mean': pd.DataFrame([[1.0] * num_features]),
        'std': pd.DataFrame([[0.5] * num_features]),
    }
    return norm_dict

mock_normalisation.get_era5_norm.return_value = create_norm_dict(2)
mock_normalisation.get_era5_land_norm.return_value = create_norm_dict(1)
mock_normalisation.get_glofas_norm.return_value = create_norm_dict(1)
mock_normalisation.get_hydroatlas_norm.return_value = create_norm_dict(2)
mock_normalisation.get_dem_norm.return_value = create_norm_dict(1)
mock_normalisation.get_hand_norm.return_value = create_norm_dict(1)
mock_normalisation.get_s1_norm.return_value = create_norm_dict(1)

# Patch the gff.normalisation module
import sys
sys.modules['gff'] = MagicMock()
sys.modules['gff.normalisation'] = mock_normalisation

ARGS = {
    'C': C
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gff, pandas, torch — 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_search_results Ran
ran; our contract draft was wrong, not the code
multihuntr/gff/gff/debug.py
code served (permissive licence) · get_code("9bbc3ce51b8362ea")
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 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 tempfile
import sqlite3
from pathlib import Path

# Create a temporary directory structure with a mock database
temp_dir = tempfile.TemporaryDirectory()
data_folder = Path(temp_dir.name)
s1_folder = data_folder / 's1'
s1_folder.mkdir(parents=True, exist_ok=True)

# Create and populate the SQLite database
db_path = s1_folder / 'index.db'
conn = sqlite3.connect(db_path)
cursor = conn.cursor()

# Create the results table with json column
cursor.execute('''
    CREATE TABLE results (
        key TEXT,
        json TEXT
    )
''')

# Insert some test data
cursor.execute("INSERT INTO results (key, json) VALUES (?, ?)", ("test_key_1", '{"result": "data1"}'))
cursor.execute("INSERT INTO results (key, json) VALUES (?, ?)", ("test_key_2", '{"result": "data2"}'))
cursor.execute("INSERT INTO results (key, json) VALUES (?, ?)", ("other_key", '{"result": "data3"}'))

conn.commit()
conn.close()

# Define the arguments dict
ARGS = {
    'data_folder': data_folder,
    'k': 'test_key_%'
}
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 list, ndim 2, 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
get_tilewise_count Ran
ran, honoured the contract we drafted
multihuntr/gff/gff/evaluation.py
code served (permissive licence) · get_code("5c8f42bac63a4058")
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 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
import torch.nn as nn

torch.manual_seed(0)

# Create a small tensor to use as the tile
# The function checks (tile == cls_idx).sum(), so we need a tensor with integer values
tile = torch.tensor([[0, 1, 2, 1],
                     [1, 0, 2, 0]], dtype=torch.long)

# Create a class index to search for
cls_idx = 1

ARGS = {
    "tile": tile,
    "cls_idx": cls_idx,
}
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 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
sometimes_things_are_lists Ran
ran; our contract draft was wrong, not the code
multihuntr/gff/gff/dataloaders.py
code served (permissive licence) · get_code("b17f0660399ad8da")
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 torch
import numpy as np

torch.manual_seed(0)

# Create a sample batch with the expected structure
# The function expects original_batch to be a list of dicts
original_batch = [
    {
        'continent': 'Africa',
        'crs': 'EPSG:4326',
        'geom': 'POLYGON((0 0, 1 0, 1 1, 0 1, 0 0))',
        'context_geom': 'POLYGON((0 0, 2 0, 2 2, 0 2, 0 0))',
        'fpaths': '/path/to/file1.tif',
        'tensor_field': np.array([1.0, 2.0, 3.0, 4.0]),
        'numeric_field': np.array([[1, 2, 3], [4, 5, 6]]),
    },
    {
        'continent': 'Europe',
        'crs': 'EPSG:3857',
        'geom': 'POLYGON((2 2, 3 2, 3 3, 2 3, 2 2))',
        'context_geom': 'POLYGON((1 1, 4 1, 4 4, 1 4, 1 1))',
        'fpaths': '/path/to/file2.tif',
        'tensor_field': np.array([5.0, 6.0, 7.0, 8.0]),
        'numeric_field': np.array([[7, 8, 9], [10, 11, 12]]),
    }
]

as_list = ['continent', 'crs', 'geom', 'context_geom', 'fpaths']

ARGS = {
    'original_batch': original_batch,
    'as_list': as_list,
}
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 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
create Not yet run
unverified (harvested, no recorded run)
multihuntr/gff/gff/models/creation.py
code served (permissive licence) · get_code("a7912da165baa8d8")
How it ran

no invocation recorded.

degrees_to_char Not yet run
unverified (harvested, no recorded run)
multihuntr/gff/gff/data_sources.py
code served (permissive licence) · get_code("7867d41bb8f2a414")
How it ran

no invocation recorded.

download_url Not yet run
unverified (harvested, no recorded run)
multihuntr/gff/gff/data_sources.py
code served (permissive licence) · get_code("223d3628a64c7b3c")
How it ran

no invocation recorded.

pack_one Not yet run
unverified (harvested, no recorded run)
multihuntr/gff/gff/models/metnet.py
code served (permissive licence) · get_code("9603f8286f20223f")
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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 2 later) and 10 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
exists 486 other papers
377 dated earlier, 7 the same month, 91 later, 9 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 163 other papers
134 dated earlier, 3 the same month, 23 later, 2 same year, order not determinable, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 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

Floods are among the most common and devastating natural hazards, imposing immense costs on our society and economy due to their disastrous consequences. Recent progress in weather prediction and spaceborne flood mapping demonstrated the feasibility of anticipating extreme events and reliably detecting their catastrophic effects afterwards. However, these efforts are rarely linked to one another and there is a critical lack of datasets and benchmarks to enable the direct forecasting of flood extent. To resolve this issue, we curate a novel dataset enabling a timely prediction of flood extent. Furthermore, we provide a representative evaluation of state-of-the-art methods, structured into two benchmark tracks for forecasting flood inundation maps i) in general and ii) focused on coastal regions. Altogether, our dataset and benchmark provide a comprehensive platform for evaluating flood forecasts, enabling future solutions for this critical challenge. Data, code & models are shared at https://github.com/Multihuntr/GFF under a CC0 license.

For agents

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

get_harvested_code_for_paper("2409.18591")
get_code_for_paper("2409.18591")
have("2409.18591")

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

curl https://syntology.ai/api/ran/2409.18591.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.18591.svg)](https://syntology.ai/paper/2409.18591)

Connect an agent — have() is free.