SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.11200 · 2019

TuneNet: One-Shot Residual Tuning for System Identification and Sim-to-Real Robot Task Transfer

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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; 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/1907.11200.json · badge: /api/ran/1907.11200.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
Kukanani/tune-net-release community (classifier label)
classifier basis not recorded on the link
5 ran · 4 no recorded run
FunctionStatusWhere it lives
load_cma_output Ran
ran on a synthesized input
Kukanani/tune-net-release/tune/cma.py
code served (permissive licence) · get_code("88a27cfe0decfa30")
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 (3, 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 os
import tempfile
import csv
import numpy as np

# Create a temporary directory with a valid xmean.dat file
temp_dir = tempfile.mkdtemp()
run_name = temp_dir

# Create xmean.dat with header and some data rows
xmean_path = os.path.join(run_name, 'xmean.dat')
with open(xmean_path, 'w', newline='') as f:
    writer = csv.writer(f, delimiter=' ')
    writer.writerow(['header1', 'header2', 'header3'])
    writer.writerow([1.0, 2.0, 3.0])
    writer.writerow([4.0, 5.0, 6.0])
    writer.writerow([7.0, 8.0, 9.0])

ARGS = {
    'run_name': run_name
}
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 (3, 3) — shape (3, 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
make_video_path Ran
ran on a synthesized input
Kukanani/tune-net-release/tune/utils.py
code served (permissive licence) · get_code("b756371b0b662ada")
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 str. 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

ARGS = {
    'task_path': 'reach_center_task',
    'itr': 42
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
reflection_matrix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Kukanani/tune-net-release/tune/transformations.py
code served (permissive licence) · get_code("c5aeb2054758da8f")
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 (4, 4) 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
import math

# Construct arguments for reflection_matrix function
# The function expects:
# - point: a vector with at least 3 elements (uses point[:3])
# - normal: a vector with at least 3 elements (uses normal[:3])

# Create a point vector (4D homogeneous coordinate)
point = numpy.array([1.0, 2.0, 3.0, 1.0], dtype=numpy.float64)

# Create a normal vector (3D, will be normalized internally)
normal = numpy.array([0.5, 0.5, 0.707], dtype=numpy.float64)

ARGS = {
    "point": point,
    "normal": normal,
}
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 (4, 4) — shape (4, 4) 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
translation_from_matrix Ran
ran on a synthesized input
Kukanani/tune-net-release/tune/transformations.py
code served (permissive licence) · get_code("77cb383b0cd2a54e")
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 1, dtype family float, shape (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

def translation_matrix(direction):
    """Helper function to create a translation matrix from a direction vector."""
    matrix = numpy.eye(4)
    matrix[:3, 3] = direction
    return matrix

# Create a small translation vector
v0 = numpy.array([0.1, 0.2, 0.3])

# Create a translation matrix (4x4 homogeneous transformation matrix)
matrix = translation_matrix(v0)

ARGS = {
    "matrix": matrix
}
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 1, dtype family float, shape (3,) — shape (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
translation_matrix Ran
ran on a synthesized input
Kukanani/tune-net-release/tune/transformations.py
code served (permissive licence) · get_code("edeb1406911ce025")
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 (4, 4) 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

numpy.random.seed(0)

# The function expects a direction vector with at least 3 elements
# It accesses direction[:3] to extract the first 3 components
direction = numpy.random.random(3) - 0.5

ARGS = {
    "direction": direction
}
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 (4, 4) — shape (4, 4) 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_dataset_base_path Not yet run
unverified (harvested, no recorded run)
Kukanani/tune-net-release/tune/utils.py
code served (permissive licence) · get_code("eb9460a7ca191408")
How it ran

no invocation recorded.

sample_gp Not yet run
unverified (harvested, no recorded run)
Kukanani/tune-net-release/tune/entsearch.py
code served (permissive licence) · get_code("f2e4a59caf985b03")
How it ran

no invocation recorded.

sample_gp Not yet run
unverified (harvested, no recorded run)
Kukanani/tune-net-release/tune/vgmi.py
code served (permissive licence) · get_code("2f8a65548df56300")
How it ran

no invocation recorded.

simulate_one_tick Not yet run
unverified (harvested, no recorded run)
Kukanani/tune-net-release/tune/vgmi.py
code served (permissive licence) · get_code("9d255425a84d699b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 6 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
reflection_matrix 14 other papers
5 dated earlier, 9 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1803.04996 (2018-03)
Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning
1805.01026 (2018-05)
Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry
and 11 more not named here
translation_from_matrix 14 other papers
5 dated earlier, 9 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1803.04996 (2018-03)
Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning
1805.01026 (2018-05)
Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry
and 11 more not named here
translation_matrix 14 other papers
5 dated earlier, 9 later
1612.00593 (2016-12)
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
1803.04996 (2018-03)
Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning
1805.01026 (2018-05)
Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry
and 11 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

As researchers teach robots to perform more and more complex tasks, the need for realistic simulation environments is growing. Existing techniques for closing the reality gap by approximating real-world physics often require extensive real world data and/or thousands of simulation samples. This paper presents TuneNet, a new machine learning-based method to directly tune the parameters of one model to match another using an *iterative residual tuning* technique. TuneNet estimates the parameter difference between two models using a single observation from the target and minimal simulation, allowing rapid, accurate and sample-efficient parameter estimation. The system can be trained via supervised learning over an auto-generated simulated dataset. We show that TuneNet can perform system identification, even when the true parameter values lie well outside the distribution seen during training, and demonstrate that simulators tuned with TuneNet outperform existing techniques for predicting rigid body motion. Finally, we show that our method can estimate real-world parameter values, allowing a robot to perform sim-to-real task transfer on a dynamic manipulation task unseen during training. Code and videos are available online at http://bit.ly/2lf1bAw.

For agents

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

get_harvested_code_for_paper("1907.11200")
get_code_for_paper("1907.11200")
have("1907.11200")

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

curl https://syntology.ai/api/ran/1907.11200.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.11200.svg)](https://syntology.ai/paper/1907.11200)

Connect an agent — have() is free.