SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.06123 · ICML · 2020

OtoWorld: Towards Learning to Separate by Learning to Move

Prem Seetharaman, Omkar Ranadive, Grant Gasser, David Terpay

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 4 have no contract verdict; 0 failures of our instrument; 0 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/2007.06123.json · badge: /api/ran/2007.06123.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
pseeth/otoworld canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
autoclip Ran
ran on a synthesized input
pseeth/otoworld/src/utils.py
code served (permissive licence) · get_code("45f5fb156f286869")
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 torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Create a minimal model with some parameters that have gradients
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear2(self.linear1(x))

# Instantiate the model
model = SimpleModel()

# Create a dummy batch and perform a forward/backward pass to generate gradients
x = torch.randn(2, 4)
y = torch.randn(2, 2)
loss_fn = nn.MSELoss()

output = model(x)
loss = loss_fn(output, y)
loss.backward()

# Now the model has gradients in its parameters
percentile = 50.0

# grad_norms starts as None (default), but we can also test with an initial list
grad_norms = None

ARGS = {
    "model": model,
    "percentile": percentile,
    "grad_norms": grad_norms
}
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
compute_ideal_binary_mask Ran
ran on a synthesized input
pseeth/otoworld/src/transforms.py
code served (permissive licence) · get_code("552c9ce2c2acfc5d")
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 float, shape (2, 4, 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 numpy as np

# Create source_magnitudes array
# Shape should be (batch, freq_bins, sources) or similar
# The function uses:
# - np.max(source_magnitudes, axis=-1, keepdims=True)
# - np.sum(ibm, axis=-1, keepdims=True)
# - Comparison operations
# So we need at least 2 dimensions

batch_size = 2
freq_bins = 4
num_sources = 3

# Create a small array with some variation
# Last axis represents different sources, we want max operations to work
source_magnitudes = np.array([
    [[1.0, 0.5, 2.0],
     [0.3, 1.5, 0.2],
     [2.0, 0.1, 0.5],
     [0.5, 0.5, 0.5]],
    [[1.2, 0.8, 1.5],
     [0.2, 2.0, 0.1],
     [1.0, 1.0, 1.0],
     [0.7, 0.3, 0.9]]
], dtype=np.float32)

ARGS = {
    "source_magnitudes": source_magnitudes
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 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
generate_data_from_log Ran
ran on a synthesized input
pseeth/otoworld/src/plot_runs.py
code served (permissive licence) · get_code("38c3a53e5808d0e5")
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 tempfile
import os

# Create a temporary log file with content matching what the function expects
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.log')
temp_file.write("""Episode: 1
Some line
Finished: 42
Another line
Steps/second: 3.14
Episode: 5
Some line
Finished: 50
Another line
Steps/second: 2.71
Episode: 6
Some line
Finished: 55
Another line
Steps/second: 3.50
Episode: 10
Some line
Finished: 60
Another line
Steps/second: 2.50
""")
temp_file.close()

ARGS = {
    'file_name': temp_file.name
}
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 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
ipd_ild_features Ran
ran on a synthesized input
pseeth/otoworld/src/audio_processing.py
code served (permissive licence) · get_code("d474f9a41a26ca78")
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. 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)

# Construct stft_data tensor
# Shape: (batch_size, time_frames, mag+phase, channels, sources)
# We need mag+phase dimension to be even so it can be split
# Let's use: batch=2, time_frames=3, mag+phase=4, channels=2, sources=1
batch_size = 2
time_frames = 3
mag_phase = 4  # even number
channels = 2
sources = 1

stft_data = torch.randn(batch_size, time_frames, mag_phase, channels, sources)

sampling_rate = 8000

ARGS = {
    "stft_data": stft_data,
    "sampling_rate": sampling_rate
}
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 — 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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 present OtoWorld 1 , an interactive environment in which agents must learn to listen in order to solve navigational tasks. The purpose of OtoWorld is to facilitate reinforcement learning research in computer audition, where agents must learn to listen to the world around them to navigate. OtoWorld is built on three open source libraries: OpenAI Gym for environment and agent interaction, PyRoomAcoustics for ray-tracing and acoustics simulation, and nussl for training deep computer audition models. OtoWorld is the audio analogue of GridWorld, a simple navigation game. OtoWorld can be easily extended to more complex environments and games. To solve one episode of OtoWorld, an agent must move towards each sounding source in the auditory scene and "turn it off". The agent receives no other input than the current sound of the room. The sources are placed randomly within the room and can vary in number. The agent receives a reward for turning off a source. We present preliminary results on the ability of agents to win at OtoWorld. OtoWorld is open-source and available. 23

For agents

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

get_harvested_code_for_paper("2007.06123")
get_code_for_paper("2007.06123")
have("2007.06123")

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

curl https://syntology.ai/api/ran/2007.06123.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.06123.svg)](https://syntology.ai/paper/2007.06123)

Connect an agent — have() is free.