SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.00029 · 2019

Chirality Nets for Human Pose Regression

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 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/1911.00029.json · badge: /api/ran/1911.00029.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
raymondyeh07/chirality_nets community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Recurrent Ran
ran on a synthesized input
raymondyeh07/chirality_nets/pose_chiral/chiral_layers/chiral_rnn_base.py
code served (permissive licence) · get_code("ad890e0a731a24c3")
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 function. 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)

# Define the inner function that processes a single timestep
def inner_step(x, hidden, w_hi, w_hh, b_ih, b_hh):
    """
    Simple RNN cell computation.
    Takes input x, hidden state, and weight matrices.
    Returns new hidden state (and optionally cell state as tuple for LSTM-like behavior).
    """
    # x: (batch_size, input_dim)
    # hidden: (batch_size, hidden_dim)
    # w_hi: (hidden_dim, input_dim)
    # w_hh: (hidden_dim, hidden_dim)
    # b_ih: (hidden_dim,)
    # b_hh: (hidden_dim,)
    
    new_hidden = torch.tanh(
        torch.mm(x, w_hi.t()) + b_ih + 
        torch.mm(hidden, w_hh.t()) + b_hh
    )
    return new_hidden

# Create small test tensors
batch_size = 2
seq_len = 3
input_dim = 4
hidden_dim = 5

# Input sequence: (seq_len, batch_size, input_dim)
input_tensor = torch.randn(seq_len, batch_size, input_dim)

# Initial hidden state: (batch_size, hidden_dim)
hidden_state = torch.randn(batch_size, hidden_dim)

# Weight matrices
w_hi = torch.randn(hidden_dim, input_dim)  # hidden-to-input weights
w_hh = torch.randn(hidden_dim, hidden_dim)  # hidden-to-hidden weights

# Bias vectors
b_ih = torch.randn(hidden_dim)
b_hh = torch.randn(hidden_dim)

ARGS = {
    'inner': inner_step,
    'reverse': False
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
chiral_transform Ran
ran on a synthesized input
raymondyeh07/chirality_nets/pose_chiral/data_utils.py
code served (permissive licence) · get_code("94ade65d8594f256")
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 4, dtype family float, shape (2, 5, 4, 6) 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

torch.manual_seed(0)

# Analyze the function signature and body:
# - x: Tensor of shape [batch x joints x channels x time]
# - num_joints: int, must equal sum(sym_grouping)
# - in_dim: int, must equal x.shape[2]
# - neg_dim_in: int, must be < in_dim
# - sym_grouping: tuple of two ints that sum to num_joints

# Create a valid sym_grouping tuple
sym_grouping = (3, 2)  # 3 + 2 = 5 joints total
num_joints = sum(sym_grouping)  # 5

# Create input tensor [batch x joints x channels x time]
batch_size = 2
channels = 4
time_steps = 6
x = torch.randn(batch_size, num_joints, channels, time_steps)

# in_dim must equal x.shape[2]
in_dim = channels  # 4

# neg_dim_in must be < in_dim
neg_dim_in = 2

ARGS = {
    "x": x,
    "num_joints": num_joints,
    "in_dim": in_dim,
    "neg_dim_in": neg_dim_in,
    "sym_grouping": sym_grouping
}
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 4, dtype family float, shape (2, 5, 4, 6) — shape (2, 5, 4, 6) 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_group_lists Ran
ran on a synthesized input
raymondyeh07/chirality_nets/pose_chiral/data_utils.py
code served (permissive licence) · get_code("8ce05fc099606d67")
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

class MockSelf:
    """Mock self object for the method"""
    pass

# Create a mock instance
mock_instance = MockSelf()

# sym_grouping is a tuple/list with two elements: [left_size, right_size]
# The function uses sym_grouping[0] and sym_grouping[1] to create index lists
sym_grouping = (3, 4)

ARGS = {
    "self": mock_instance,
    "sym_grouping": sym_grouping,
}
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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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 propose Chirality Nets, a family of deep nets that is equivariant to the "chirality transform," i.e., the transformation to create a chiral pair. Through parameter sharing, odd and even symmetry, we propose and prove variants of standard building blocks of deep nets that satisfy the equivariance property, including fully connected layers, convolutional layers, batch-normalization, and LSTM/GRU cells. The proposed layers lead to a more data efficient representation and a reduction in computation by exploiting symmetry. We evaluate chirality nets on the task of human pose regression, which naturally exploits the left/right mirroring of the human body. We study three pose regression tasks: 3D pose estimation from video, 2D pose forecasting, and skeleton based activity recognition. Our approach achieves/matches state-of-the-art results, with more significant gains on small datasets and limited-data settings.

For agents

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

get_harvested_code_for_paper("1911.00029")
get_code_for_paper("1911.00029")
have("1911.00029")

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

curl https://syntology.ai/api/ran/1911.00029.json

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

[![Syntology run record](https://syntology.ai/api/ran/1911.00029.svg)](https://syntology.ai/paper/1911.00029)

Connect an agent — have() is free.