HypercubeEtalon

HypercubeEtalon is for high-dimensional data that has no natural clock — spectra, sensor frames, packed images, stills. Those are the same kinds of static fields people usually feed a spatial CNN, an MLP, or a similar feed-forward stack. HypercubeEtalon puts one frozen hypercube preprocessor in front of the CNN: an etalon transit — a deterministic wave swept across every vertex/antipode cavity of a Boolean hypercube. The transit's neighbor weights are drawn once and never trained. A small HypercubeCNN head trains on the transit output. The CNN never sees the original field — it sees what the wave leaves behind.

That is the product idea: take a static field, pass it through a frozen nonlinearity, and train a spatial readout on what remains. The aim is a preprocessor effective enough that the readout can be a single convolutional layer with a single channel and no pooling.

This package is the Python surface for that product (import hypercube_etalon). Full API reference: docs/Python_SDK.md. C++ integration guide: docs/CPP_SDK.md. Project home: github.com/dliptak001/HypercubeEtalon.

HypercubeAI ecosystem

HypercubeESN · HypercubeCNN · HypercubeHopfield · HypercubeWTF · HypercubeEtalon · HypercubeCascade

HypercubeEtalon is an experiment in the HypercubeAI project — our quest to systematically re-implement classical neural architectures on a Boolean hypercube topology instead of Euclidean grids or random graphs. The central thesis is “topology-native intelligence”: the hypercube’s algebraic structure (vertex-transitive symmetry, Hamming geometry, bitwise addressing) can serve as a first-class computational substrate.

A topology you don’t store — the graph is specified: connectivity is implicit in the vertex indices; with a seed and a few config scalars the whole preprocessor reconstructs mathematically.
Perfect homogeneity — every vertex has the same degree and the same local world, so local dynamics mean the same thing everywhere — no structural favorites baked in by a random graph.
Cheap navigation — each neighbor is a few bit operations on the vertex index, not a pointer chase through a stored edge list, so walks stay arithmetic and cache-friendly.
Topology-native pairing — the readout consumes the preprocessor output with zero geometric distortion, and the learned kernels exploit the same locality that generated the dynamics. The data never leaves the hypercube it was born on.

Each product in the family is a different architecture on that same foundation.

What is HypercubeEtalon?

An etalon here is a start vertex and its face antipode treated as a pair of reflectors. One transit sweeps a tanh wave out to the antipode and back for every start vertex on the cube; the value standing at the start after the wave returns is that vertex's output sample. N starts → N output samples — the transit output is a field with the same length and vertex indexing as the input.

In classical reservoir computing (and in the siblings HypercubeWTF and HypercubeCascade):

Preprocessor weights are frozen
Only a readout is trained
Nonlinear dynamics expand and mix the drive into a rich state

Whether the single-stage transit has real product value is still an open question. Early studies suggest it adds noise filtering the raw field does not have (see Early observations), and the built-in bypass_exciter flag runs the no-transit ablation so you can check on your own task.

Pipeline

x  (your length-N field — already on the cube, no natural time)
    │
    ▼
 frozen etalon transit (one wave over every cavity)
    │
    ▼
 transit output (length N) → HypercubeCNN → logits / values

Cube size from dim (N = 2^dim; dim 4…12, prefer ≥ 5).
Only the readout trains.
Everyday loop in this package: collect_batch → train → predict / predict_class, or one-shot fit (collect + train).

Unlike HypercubeESN’s Python API, there is no stream of small samples over real time and no next-step fit on a 1D signal. Each sample is one full field; the CNN only ever sees the transit output for that field.

Full method list and knobs: docs/Python_SDK.md.

Early observations (exploratory)

On the MNIST white-noise study (train clean, test with Gaussian field noise), the transit path holds its accuracy markedly better than the pack-only bypass as test noise grows. On a Raman baseline-extraction regression the etalon readout runs at the goal size — one conv layer, one channel, no pooling — and edges out the two-stage cascade sibling on validation RMSE. The write-ups have the details and how we ran them:

Document	Question
WhiteNoiseFilter.md	Noisy test fields: does the transit help vs pack-only → CNN?
RamanBaselineExtraction/README.md	Baseline regression at the goal readout size

The MNIST study uses small cubes because they are handy to pack and run, not because we are chasing digit accuracy. A more rigorous study is still needed before treating any of those results as settled. You can reproduce the same ideas from Python with this package (pack fields yourself, then collect, train, and predict). The original write-ups and C++ demos that produced the numbers live under examples/.

Installation

Preferred: install a pre-built wheel from PyPI (no compiler).

pip install hypercube-etalon

import hypercube_etalon as he
print(he.__version__)

Package name on PyPI: hypercube-etalon. Import name: hypercube_etalon. Main type: he.Etalon.

Wheels target Python 3.10–3.14 on common Windows, Linux, and macOS machines. Runtime dependency: NumPy only.

From source (full repository)

To compile the extension yourself, clone this entire repository (not a minimal source-only download of the python/ folder alone — the C++ core and vendored HypercubeCNN live next to python/). You need Python 3.10+, a C++23 compiler, and CMake ≥ 3.20.

git clone https://github.com/dliptak001/HypercubeEtalon.git
cd HypercubeEtalon/python
pip install .

On Windows with CLion’s MinGW, put that compiler’s bin folder (and Ninja) on your PATH, then:

pip install . --no-build-isolation --force-reinstall --no-deps

(Exact CLion paths change with the version.) Step-by-step toolchain notes: docs/Python_SDK.md.

Quick start

You bring each sample as a length-N float array (N = 2^dim). How you get there — pad an image, reshape a spectrum, invent a layout — is up to you. This package does not pack 784 pixels or 300 bins for you.

Shapes that matter:

Array	Shape	Notes
`fields`	`(count, N)`	one length-N field per row
`labels` (classification)	`(count,)`	integer class indices
`targets` (regression)	`(count, num_outputs)`	float targets

import numpy as np
import hypercube_etalon as he

dim = 7
N = 2**dim
rng = np.random.default_rng(0)
fields = rng.standard_normal((200, N), dtype=np.float32)
labels = rng.integers(0, 4, size=200)

et = he.Etalon(
    dim=dim,
    exciter_subcube_dim=5,
    exciter_input_scaling=1.0,
    exciter_weight_scaling=0.15,
    readout_num_outputs=4,
    readout_task="classification",
    readout_epochs=80,
)
et.fit(fields, labels)  # collect_batch + train

print(et.N, et.subcube_dim, et.num_collected)
print(f"train sanity check: {et.accuracy_on_collected():.3f}")
print(et.predict_class(fields[0]), et.predict(fields[0]).shape)

et.save("model.pkl")
loaded = he.Etalon.load("model.pkl")

Step by step (same loop, more control)

et = he.Etalon(
    dim=7,
    exciter_subcube_dim=5,
    exciter_input_scaling=1.0,
    exciter_weight_scaling=0.15,
    readout_num_outputs=4,
    readout_task="classification",
)
et.collect_batch(fields_train, labels_train)
et.train()
logits = et.predict(fields_test[0])       # (num_outputs,) float32
cls = et.predict_class(fields_test[0])    # int
test_acc = et.accuracy(fields_test, labels_test)  # held-out, fresh maps

For regression, set readout_task="regression" and pass float targets instead of class labels. Then use r2_on_collected() / r2(fields, targets) the same way.

accuracy_on_collected and r2_on_collected only look at the samples you already trained on — they are a quick sanity check, not a test score. For real evaluation, hold fields out and call accuracy / r2 (or predict / predict_class yourself).

Features

One class — hypercube_etalon.Etalon is the whole product surface
Map loop — collect / collect_batch → train → predict / predict_class
fit — clear, collect, and train when your arrays are ready
dim 4–12 — field length N = 2^dim; etalon face exciter_subcube_dim
Two gains — exciter_input_scaling (field → transit) and exciter_weight_scaling (neighbor-weight amplitude); the demos run ~1.0 and 0.15–0.5 (the header defaults 0.02 barely drive tanh)
Built-in ablation — bypass_exciter=True feeds the raw field to the same readout
Classification or regression — readout_task fixed at construction
Held-out scoring — accuracy(fields, labels) / r2(fields, targets) map fresh in bulk
Bulk calls can parallelize — collect_threads (0 = auto)
Inspect a map — run(x) then last_features() for gain tuning
Save / load — save / load (pickle: config + readout weights; collected samples are not stored). Optional save_readout_hcnn_model / load_readout_hcnn_model for portable HCNW + arch JSON
NumPy float32 — arrays converted for you; prefer contiguous float32

Examples

For a first try, paste the Quick start after pip install hypercube-etalon. That is self-contained.

If you want a longer walk-through, the demo scripts on GitHub under python/examples/ are there to open or download — they are not added to your machine by pip.

Script	What it is for
synthetic_classification.py	Multi-class toy fields: `fit`, then train and test accuracy

# from a clone of HypercubeEtalon, after: pip install hypercube-etalon
python python/examples/synthetic_classification.py

These use easy made-up fields so the API is obvious — not scores to publish. More notes: python/examples/README.md.

Documentation

Doc	Role
docs/Python_SDK.md	Canonical Python API — every method, layout, pickle, limits
python/examples/README.md	Demo scripts on GitHub
Project README	Product story and C++ demos from the repo root
docs/CPP_SDK.md	Native library guide (same product, C++)
WhiteNoiseFilter.md	Early white-noise study (MNIST as a test bed)

Ecosystem

HypercubeWTF — a reservoir orbit as the frozen stage instead of a transit.
HypercubeCascade — the transit and the orbit in series; Etalon is its first stage.
HypercubeCNN — cube-native conv stack; Etalon’s trainable head.
HypercubeESN — echo-state / reservoir computing on streams.
HypercubeHopfield — Hopfield-style dynamics on the cube.

License

Apache 2.0. See LICENSE.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hypercube_etalon-1.0.0.tar.gz (25.5 kB view details)

Uploaded Aug 19, 2026 Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

hypercube_etalon-1.0.0-cp314-cp314-win_amd64.whl (418.1 kB view details)

Uploaded Aug 19, 2026 CPython 3.14Windows x86-64

hypercube_etalon-1.0.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (287.0 kB view details)

Uploaded Aug 19, 2026 CPython 3.14manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

hypercube_etalon-1.0.0-cp314-cp314-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (260.6 kB view details)

Uploaded Aug 19, 2026 CPython 3.14manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

hypercube_etalon-1.0.0-cp314-cp314-macosx_13_0_x86_64.whl (250.1 kB view details)

Uploaded Aug 19, 2026 CPython 3.14macOS 13.0+ x86-64

hypercube_etalon-1.0.0-cp314-cp314-macosx_13_0_arm64.whl (219.5 kB view details)

Uploaded Aug 19, 2026 CPython 3.14macOS 13.0+ ARM64

hypercube_etalon-1.0.0-cp313-cp313-win_amd64.whl (405.0 kB view details)

Uploaded Aug 19, 2026 CPython 3.13Windows x86-64

hypercube_etalon-1.0.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (287.1 kB view details)

Uploaded Aug 19, 2026 CPython 3.13manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

hypercube_etalon-1.0.0-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (260.0 kB view details)

Uploaded Aug 19, 2026 CPython 3.13manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

hypercube_etalon-1.0.0-cp313-cp313-macosx_13_0_x86_64.whl (250.0 kB view details)

Uploaded Aug 19, 2026 CPython 3.13macOS 13.0+ x86-64

hypercube_etalon-1.0.0-cp313-cp313-macosx_13_0_arm64.whl (219.1 kB view details)

Uploaded Aug 19, 2026 CPython 3.13macOS 13.0+ ARM64

hypercube_etalon-1.0.0-cp312-cp312-win_amd64.whl (405.0 kB view details)

Uploaded Aug 19, 2026 CPython 3.12Windows x86-64

hypercube_etalon-1.0.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (287.1 kB view details)

Uploaded Aug 19, 2026 CPython 3.12manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

hypercube_etalon-1.0.0-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (259.9 kB view details)

Uploaded Aug 19, 2026 CPython 3.12manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

hypercube_etalon-1.0.0-cp312-cp312-macosx_13_0_x86_64.whl (249.9 kB view details)

Uploaded Aug 19, 2026 CPython 3.12macOS 13.0+ x86-64

hypercube_etalon-1.0.0-cp312-cp312-macosx_13_0_arm64.whl (219.1 kB view details)

Uploaded Aug 19, 2026 CPython 3.12macOS 13.0+ ARM64

hypercube_etalon-1.0.0-cp311-cp311-win_amd64.whl (402.4 kB view details)

Uploaded Aug 19, 2026 CPython 3.11Windows x86-64

hypercube_etalon-1.0.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (285.7 kB view details)

Uploaded Aug 19, 2026 CPython 3.11manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

hypercube_etalon-1.0.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (258.6 kB view details)

Uploaded Aug 19, 2026 CPython 3.11manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

hypercube_etalon-1.0.0-cp311-cp311-macosx_13_0_x86_64.whl (247.4 kB view details)

Uploaded Aug 19, 2026 CPython 3.11macOS 13.0+ x86-64

hypercube_etalon-1.0.0-cp311-cp311-macosx_13_0_arm64.whl (217.3 kB view details)

Uploaded Aug 19, 2026 CPython 3.11macOS 13.0+ ARM64

hypercube_etalon-1.0.0-cp310-cp310-win_amd64.whl (401.2 kB view details)

Uploaded Aug 19, 2026 CPython 3.10Windows x86-64

hypercube_etalon-1.0.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (284.9 kB view details)

Uploaded Aug 19, 2026 CPython 3.10manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

hypercube_etalon-1.0.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (257.9 kB view details)

Uploaded Aug 19, 2026 CPython 3.10manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

hypercube_etalon-1.0.0-cp310-cp310-macosx_13_0_x86_64.whl (245.9 kB view details)

Uploaded Aug 19, 2026 CPython 3.10macOS 13.0+ x86-64

hypercube_etalon-1.0.0-cp310-cp310-macosx_13_0_arm64.whl (216.2 kB view details)

Uploaded Aug 19, 2026 CPython 3.10macOS 13.0+ ARM64

File details

Details for the file hypercube_etalon-1.0.0.tar.gz.

File metadata

Download URL: hypercube_etalon-1.0.0.tar.gz
Upload date: Aug 19, 2026
Size: 25.5 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for hypercube_etalon-1.0.0.tar.gz
Algorithm	Hash digest
SHA256	`db84cbf18612328346a0a33a8fde7404beff49361e0c746d19014de07d26c520`
MD5	`6315e4d9454d44e8909bfa72bf90e05b`
BLAKE2b-256	`082b3ddf5a12bd26c4c44ff4c8b5d6794d0075ca236492abc156944490c795e0`

Algorithm	Hash digest
SHA256	`226f4daf5b5efec683518fa6d171752299d317785d543fa9d20bcf5063974dac`
MD5	`364548e284866e9038478114062593f9`
BLAKE2b-256	`3513f9356cbb16a2f016bda6a8e164b34716b415d7d89b5b91ff97966cf1b54b`

Algorithm	Hash digest
SHA256	`ad456e9333f27ebfa39624bab3affa6cfe1c6b63f916861c6cda8f1dca035cab`
MD5	`bdcc70e24574582e2bdb202eb06f464e`
BLAKE2b-256	`40e93bb79289e2815ea18608e30e4709ca2a2e15d4c121199511ca57e6f870eb`

Algorithm	Hash digest
SHA256	`ec3db024902f5d0210dec0334d92efb1c340ef5183ba08240661391950a1d823`
MD5	`21280c23dba295d05bd7e805162dc711`
BLAKE2b-256	`216d0af47570d55a83f1809b9baf399ac7ba0c84a8119a838287d031cc365836`

Algorithm	Hash digest
SHA256	`7d6c2d14eeba3d5cf0bd22bb83329c335af68cf2fc76f5390239ab254e27cd34`
MD5	`bd0ca953dd26da28b90033d946c9f19d`
BLAKE2b-256	`b545abbac957ef02c7675a9d396f4d3e15f55ca63ed5c2dcec41e0d8a36fda37`

Algorithm	Hash digest
SHA256	`378c940a90b0062ac192fc4b85ca66eb7a9a604564ca7f42db159afcba7d8177`
MD5	`33cb9ec7a192aa5253017e0246f7bf35`
BLAKE2b-256	`ad364b55505fb3d432dcb709b4d7baec0b74464dd800fcdf2c49737978b28411`

Algorithm	Hash digest
SHA256	`55ba118613d7fde6b106ce17f68202c55bc81e252fccbabe90db7751eca0deb0`
MD5	`e3c6f4e918dea4632adf54b1c88af59f`
BLAKE2b-256	`0c04d4b34e64c2db1befd2b487cd7e95eb13c6fe58ba3ad24d05ecdaf3281d0a`

Algorithm	Hash digest
SHA256	`36607b97cb841859b9084e3c13124cc08788db52040859c6228ff380755d00d7`
MD5	`4f3c6dcf0c58b833c18824bdeeb27ef0`
BLAKE2b-256	`cdfff0285beee1e853f92e29f4225001303eb6d40d3bc1641faff7c59094dadc`

Algorithm	Hash digest
SHA256	`96d606bad77f27d9f374247b5490a4a361b71c7a7e1d4a1996e2b381711ddc3b`
MD5	`7ee22c4c1a75210ab700b711dc89c095`
BLAKE2b-256	`73e03daf90211cd045393f146560ec134117b278278a3d0be74a3959667025d5`

Algorithm	Hash digest
SHA256	`863269ef1fae1ffe0aaa751df5b9b93d85e2f2a10361b755d9d5c26d6860022d`
MD5	`50c156a51387ae356e0caa05c6f40cde`
BLAKE2b-256	`25fcb405f4a64c81ada6ae8b1a4f1848028bef71ac382983d4051e78b9007180`

Algorithm	Hash digest
SHA256	`64cce3e266a2c60f3c99b77e15876d3f8d0b6e0b85db7993ba5e32afd7be54e8`
MD5	`a4db893bb6fad5292834b4b5dc75a7ff`
BLAKE2b-256	`1c2337c77f2d0465ee863e81467399765617576e8c0935d7d797506b60ef00ff`

Algorithm	Hash digest
SHA256	`8a12107d6b6aade2c201c2ddf55a81c57e6fbf5ec7920290c73ac6c5af13cb92`
MD5	`787aefafd0145094ca8c421fce8eb02a`
BLAKE2b-256	`94532a821ef9da924e8e985d7e0767325680a27776a4c1d6e42532574846b4a0`

Algorithm	Hash digest
SHA256	`910a6cfd009747d59525eb3b6c4e3e17c7302172765bbe813048c622f8f03e12`
MD5	`a76686ddc2f718c8d976a4b87409f3fa`
BLAKE2b-256	`38b271b0228fe050b12f05393594f66b0d2987fd901214acb416302426755b99`

Algorithm	Hash digest
SHA256	`5a84fcb766020ea9bc7616a9ac795ea08936fd2978a352ae820a4df4262f0114`
MD5	`bd4671bb8175e0a52b2f1b227d71028e`
BLAKE2b-256	`7a9c6d63c987fbdf203b4858f558837e289616bcfca3307caa461176a38ea1f9`

Algorithm	Hash digest
SHA256	`8bd93b202061407471b7ff7298e93f64e176c350fbafea7cd7c454a926498fbb`
MD5	`614bfe71b2c2a8ce322814d766827c70`
BLAKE2b-256	`4b016f5b892252aef4a8f82abba45f8e5688422625d47d302b28650a0b57e416`

Algorithm	Hash digest
SHA256	`a41a7b0ea854f8cf62c00f66ce29058cd8691999fd3fb5e9210ea863cc0a61d6`
MD5	`8bc4429018e55a38a53c07a587e85744`
BLAKE2b-256	`5a9e597af96f242bcb9ffc24ce2dc9e0203e64fbb068b7f3e22bca64d2263a41`

Algorithm	Hash digest
SHA256	`0c62f48eb6f58cf9f54c9c0d473ac84f94a3b5899bc95be47d9ea0ab9affdb67`
MD5	`140455ba09b548766817522ea5a53c9f`
BLAKE2b-256	`047f3683a7c2238ef87c56df64946f02077c646c9ab271f9171ea38b9b4db586`

Algorithm	Hash digest
SHA256	`b76a150b3b1ed542792d7e8635bcfdd52be40a0c5ff9f98d072bf91380a6196d`
MD5	`ffb66432b0943dca06411d7ca8a31492`
BLAKE2b-256	`2a38ac4a5bb27e9286b7905becb8cd6f22e31074c19de1b32efb38992f710ccf`

Algorithm	Hash digest
SHA256	`e9ce004b30a747b3e19e0c170927e4b59c853a2a5a7bc05e807538a44b5ce1e9`
MD5	`d5e7d37c4cbfee0e23cb65385a665714`
BLAKE2b-256	`3806fd5c6c017e4995ae155bb9c7bd3c467eaf77b379fc2cd59a61febe9b539c`

Algorithm	Hash digest
SHA256	`af4ebc5fa5fd61c46f51ab623ad46b489275d48ad0f8be2ff263f8f013e440e3`
MD5	`c5a4b89ce0531088b4fbd3d7227130c8`
BLAKE2b-256	`16bf9635a11b4e6ea8a64d24c24419c82025f486923cd814c90df86002990669`

Algorithm	Hash digest
SHA256	`31ca0f856069442140375c6a8d6a8e68721573f15dd2c483469582f687b018e6`
MD5	`a87060a4b6da606dc4f19e6bde7b781b`
BLAKE2b-256	`f8b2bad497758849dc736b0fb757e19042b5ea89e394a1b1f8cb59d523f6099d`

hypercube-etalon 1.0.0

HypercubeEtalon

What is HypercubeEtalon?

Pipeline

Early observations (exploratory)

Installation

From source (full repository)

Quick start

Step by step (same loop, more control)

Features

Examples

Documentation

Ecosystem

License

Project links

Key dates

1 maintainer

GitHub Statistics

License expression

Requires

Provides Extra

Classifiers

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Algorithm	Hash digest
SHA256	`3b8a3f2bfb10eb9f55ea1e53eef91606ac4cc5fbc2277d14030076c76f2fab20`
MD5	`bc829af123ae6f241f04b1da207904ff`
BLAKE2b-256	`61065b16d6db49c4a461469ebeca10d70b3d323230fb61d6c712f7ee4a27911f`

Algorithm	Hash digest
SHA256	`e31ecaa0c10b6d8a7c794f6924d8f7afaa583e78cd36985db851f1165535a253`
MD5	`8101616242400f4889481a914d1c7882`
BLAKE2b-256	`ed0d31c63c503199714e2f3b5c879c0d30b68f2e47192abbb6be81a72d5e8abd`

Algorithm	Hash digest
SHA256	`afd27837892672ce1f15d636420d40a972ee575f3675bb667eed1278b5154817`
MD5	`68f0d91d19c9aeedc3c60403a5c6a51e`
BLAKE2b-256	`108b7e6a00be7eb94af12b5bbb802dbaef13c049073d5176f4084bb8f26bcb14`

Algorithm	Hash digest
SHA256	`b410e2de5938490515ebd76a1185a10f10e1ff5d1603a037386e164a0abccd6b`
MD5	`ffa26f4130ef598e3dd4c97fed0b97aa`
BLAKE2b-256	`6f6b1bc7a85cb280fbad09c5d3d0bc8eced761f7b9028bf42282f4ed744186c3`

Algorithm	Hash digest
SHA256	`c159629099a81418497c9da4115582328993184df0b7cd0355961d64894ec7a8`
MD5	`1241f2778b43334114fcb3ef71869de9`
BLAKE2b-256	`4b5f6f3c77c74d13fe7242dde3991849bf9e289552bef6c4454c904463bc53f1`