SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1710.04833 · 2017

Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure

arXiv · PDF · Open in the Atlas

Code that ran

1 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 1 has 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/1710.04833.json · badge: /api/ran/1710.04833.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
dingliu0305/Tree-Tensor-Networks-in-Machine-Learning canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
squash_layer Ran
ran on a synthesized input
dingliu0305/Tree-Tensor-Networks-in-Machine-Learning/code/tsne_mnist.py
code served (permissive licence) · get_code("3a67b0da03d55f42")
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 (2, 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
import numpy as np

torch.manual_seed(0)

# The function expects:
# - contraction: a list (or indexable container) where contraction[which_layer] 
#   returns a list of rows
# - which_layer: an integer index
# - Each element in a row should have a .data attribute (like torch tensors)
# - The data should be stackable with np.vstack

# Create mock tensor-like objects with .data attributes
class MockTensor:
    def __init__(self, data):
        self.data = data

# Build contraction as a list of layers
# Each layer is a list of rows
# Each row is a list of MockTensor objects
contraction = []

# Layer 0: 2 rows, each with 3 elements
layer_0 = [
    [MockTensor(np.array([1.0, 2.0])), MockTensor(np.array([3.0, 4.0])), MockTensor(np.array([5.0, 6.0]))],
    [MockTensor(np.array([7.0, 8.0])), MockTensor(np.array([9.0, 10.0])), MockTensor(np.array([11.0, 12.0]))]
]
contraction.append(layer_0)

# Layer 1: another layer with different structure
layer_1 = [
    [MockTensor(np.array([13.0, 14.0, 15.0])), MockTensor(np.array([16.0, 17.0, 18.0]))],
    [MockTensor(np.array([19.0, 20.0, 21.0])), MockTensor(np.array([22.0, 23.0, 24.0]))]
]
contraction.append(layer_1)

which_layer = 0

ARGS = {
    "contraction": contraction,
    "which_layer": which_layer
}
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 ndarray, ndim 2, dtype family float, shape (2, 6) — shape (2, 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
sort Not yet run
unverified (harvested, no recorded run)
dingliu0305/Tree-Tensor-Networks-in-Machine-Learning/code/tsne_mnist.py
code served (permissive licence) · get_code("00f8d8103028800e")
How it ran

no invocation recorded.

tsne Not yet run
unverified (harvested, no recorded run)
dingliu0305/Tree-Tensor-Networks-in-Machine-Learning/code/tsne_mnist.py
code served (permissive licence) · get_code("846444068359d8ea")
How it ran

no invocation recorded.

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

The resemblance between the methods used in quantum-many body physics and in machine learning has drawn considerable attention. In particular, tensor networks (TNs) and deep learning architectures bear striking similarities to the extent that TNs can be used for machine learning. Previous results used one-dimensional TNs in image recognition, showing limited scalability and flexibilities. In this work, we train two-dimensional hierarchical TNs to solve image recognition problems, using a training algorithm derived from the multi-scale entanglement renormalization ansatz. This approach introduces mathematical connections among quantum many-body physics, quantum information theory, and machine learning. While keeping the TN unitary in the training phase, TN states are defined, which encode classes of images into quantum many-body states. We study the quantum features of the TN states, including quantum entanglement and fidelity. We find these quantities could be properties that characterize the image classes, as well as the machine learning tasks.

For agents

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

get_harvested_code_for_paper("1710.04833")
get_code_for_paper("1710.04833")
have("1710.04833")

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

curl https://syntology.ai/api/ran/1710.04833.json

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

[![Syntology run record](https://syntology.ai/api/ran/1710.04833.svg)](https://syntology.ai/paper/1710.04833)

Connect an agent — have() is free.