SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.09326 · ICLR · 2025

PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance

Song Wang, Qijun Gan, Shengtao Wu, Jianke Zhu

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 5 honoured the contract we drafted, 4 violated it and 1 has no contract verdict; 3 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2406.09326.json · badge: /api/ran/2406.09326.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
agnJason/PianoMotion10M canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
agnjason/pianomotion10m canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
identity Ran
ran, honoured the contract we drafted
agnJason/PianoMotion10M/models/denoise_diffusion.py
code served (permissive licence) · get_code("7f1040f5e3991d5e")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:37:21Z). 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 torch.nn as nn

torch.manual_seed(0)

# The identity function simply returns its first argument
# and ignores all other args and kwargs
# So we need to provide a value for t and can optionally provide other args/kwargs

t = torch.randn(2, 4)
extra_arg_1 = torch.randn(3, 5)
extra_arg_2 = "some_string"
extra_kwarg_1 = 42
extra_kwarg_2 = [1, 2, 3]

ARGS = {
    "t": t,
    "args": (extra_arg_1, extra_arg_2),
    "kwargs": {"key1": extra_kwarg_1, "key2": extra_kwarg_2}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, dtype family float, shape (2, 4) — shape (2, 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
GaussianDiffusion1D_piano2pose Ran
ran on a synthesized input · constructed an object; no result was computed
agnjason/pianomotion10m/models/denoise_diffusion.py
code served (permissive licence) · get_code("0b4dc4c570105906")
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 an instance of its own class, GaussianDiffusion1D_piano2pose: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from torch import nn
import math

torch.manual_seed(0)

# Helper functions from the code
def exists(x):
    return x is not None

def default(val, d):
    if exists(val):
        return val
    return d() if callable(d) else d

def extract(a, t, x_shape):
    b, *_ = t.shape
    out = a.gather(-1, t)
    return out.reshape(b, *(1,) * (len(x_shape) - 1))

def identity(t, *args, **kwargs):
    return t

def normalize_to_neg_one_to_one(img):
    return img * 2 - 1

def unnormalize_to_zero_to_one(t):
    return (t + 1) * 0.5

def cosine_beta_schedule(timesteps, s=0.008):
    steps = timesteps + 1
    x = torch.linspace(0, timesteps, steps, dtype=torch.float64)
    alphas_cumprod = torch.cos((x / timesteps + s) / (1 + s) * math.pi * 0.5) ** 2
    alphas_cumprod = alphas_cumprod / alphas_cumprod[0]
    betas = 1 - alphas_cumprod[1:] / alphas_cumprod[:-1]
    return torch.clip(betas, 0, 0.999)

def linear_beta_schedule(timesteps):
    scale = 1000 / timesteps
    beta_start = scale * 0.0001
    beta_end = scale * 0.02
    return torch.linspace(beta_start, beta_end, timesteps, dtype=torch.float64)

# Minimal model that satisfies the interface
class DummyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.channels = 4
        self.self_condition = False
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, t, x_self_cond=None):
        # model is called with (x, t, x_self_cond) signature
        return self.linear(x)

# Minimal piano2posi model
class DummyPiano2Posi(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

# Create instances
model = DummyModel()
piano2posi = DummyPiano2Posi()

ARGS = {
    'model': model,
    'piano2posi': piano2posi,
    'seq_length': 16,
    'timesteps': 100,
    'sampling_timesteps': None,
    'objective': 'pred_noise',
    'beta_schedule': 'cosine',
    'ddim_sampling_eta': 0.0,
    'auto_normalize': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GaussianDiffusion1D_piano2pose — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GaussianDiffusion1D_piano2pose 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
MW2 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
agnJason/PianoMotion10M/models/evaluate.py
code served (permissive licence) · get_code("c0cec5eb44a6d5fb")
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 float64, ndim 0, 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 numpy as np
from sklearn.mixture import GaussianMixture
import ot
from sklearn.decomposition import IncrementalPCA

# Create small synthetic distributions
np.random.seed(0)

# dist1: shape (N, D) - first distribution with N=20 samples, D=15 features
dist1 = np.random.randn(20, 15).astype(np.float64)

# dist2: shape (N, D) - second distribution with N=25 samples, D=15 features
dist2 = np.random.randn(25, 15).astype(np.float64)

# K: number of GMM components
K = 3

ARGS = {
    'dist1': dist1,
    'dist2': dist2,
    'K': K
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, ot, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
cosine_beta_schedule Ran
ran, honoured the contract we drafted
agnjason/pianomotion10m/models/denoise_diffusion.py
code served (permissive licence) · get_code("05e94467a0de94a4")
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) and returned Tensor, ndim 1, dtype family float, shape (10,) 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 math

torch.manual_seed(0)

ARGS = {
    "timesteps": 10,
    "s": 0.008
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (10,) — shape (10,) 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
default Ran
ran, violated the contract we drafted
agnJason/PianoMotion10M/models/denoise_diffusion.py
code served (permissive licence) · get_code("d1ef6b8cb9a28a53")
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) 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

torch.manual_seed(0)

def exists(x):
    return x is not None

def default(val, d):
    if exists(val):
        return val
    return d() if callable(d) else d

# Test case 1: val is not None, should return val
val_1 = "test_value"
d_1 = lambda: "default_value"

# Test case 2: val is None, d is callable, should return d()
val_2 = None
d_2 = lambda: "computed_default"

# Test case 3: val is None, d is not callable, should return d
val_3 = None
d_3 = "static_default"

# Test case 4: val is a number
val_4 = 42
d_4 = 100

# Test case 5: val is a tensor
val_5 = torch.tensor([1.0, 2.0, 3.0])
d_5 = lambda: torch.tensor([0.0])

ARGS = {
    "val": val_1,
    "d": d_1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
enc_dec_mask Ran
ran, violated the contract we drafted
agnJason/PianoMotion10M/models/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from psyai-net/EmoTalk_release, is pointer only (licence: NOASSERTION) · get_code("7ed01fed1fc1f58f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from psyai-net/EmoTalk_release, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

exists Ran
ran, violated the contract we drafted
agnJason/PianoMotion10M/models/denoise_diffusion.py
code served (permissive licence) · get_code("608e364a9d2376a3")
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) and returned bool, ndim 0, dtype family float, shape () 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

def exists(x):
    return x is not None

ARGS = {
    "x": torch.tensor([1, 2, 3, 4])
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () 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
fid Ran
ran, honoured the contract we drafted
agnJason/PianoMotion10M/models/evaluate.py
code served (permissive licence) · get_code("48d5d027f2a36562")
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 float, ndim 0, dtype family float, shape () 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
import torch

torch.manual_seed(0)

# Create small numpy arrays for real and fake data
# Shape: (batch_size, feature_dim)
batch_size = 2
feature_dim = 4

real = np.random.randn(batch_size, feature_dim).astype(np.float32)
fake = np.random.randn(batch_size, feature_dim).astype(np.float32)

ARGS = {
    "real": real,
    "fake": fake,
}
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 float, ndim 0, dtype family float, shape () — shape () 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
init_biased_mask Ran
ran, honoured the contract we drafted
agnJason/PianoMotion10M/models/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from psyai-net/SelfTalk_release, is pointer only (licence: NOASSERTION) · get_code("f7b0318637b0548a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from psyai-net/SelfTalk_release, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

linear_beta_schedule Ran
ran, honoured the contract we drafted
agnjason/pianomotion10m/models/denoise_diffusion.py
code served (permissive licence) · get_code("482723f534770483")
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) and returned Tensor, ndim 1, dtype family float, shape (50,) 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)

ARGS = {
    "timesteps": 50
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (50,) — shape (50,) 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
linear_interpolation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
agnJason/PianoMotion10M/models/wav2vec.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from psyai-net/EmoTalk_release, is pointer only (licence: NOASSERTION) · get_code("e45a37313dcbbaac")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from psyai-net/EmoTalk_release, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

loc_distance Ran
ran, violated the contract we drafted
agnJason/PianoMotion10M/models/evaluate.py
code served (permissive licence) · get_code("ae9bd94543a16207")
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 float32, ndim 0, dtype family float, shape () 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 small numpy arrays representing locations
# real: shape (2, 4) - batch of 2 location samples, 4 dimensions
# fake: shape (2, 4) - batch of 2 location samples, 4 dimensions
real = np.array([
    [0.1, 0.2, 0.3, 0.4],
    [0.5, 0.6, 0.7, 0.8]
], dtype=np.float32)

fake = np.array([
    [0.15, 0.25, 0.35, 0.45],
    [0.55, 0.65, 0.75, 0.85]
], dtype=np.float32)

ARGS = {
    "real": real,
    "fake": fake
}
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 float32, ndim 0, dtype family float, shape () — shape () 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
velocity_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
agnJason/PianoMotion10M/models/utils.py
code served (permissive licence) · get_code("4537026d64143186")
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 0, dtype family float, shape () 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 torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for bs and bs_hat
# Shape: (batch_size=2, sequence_length=3, feature_dim=4)
# These represent sequences of positions/states over time
bs = torch.randn(2, 3, 4)
bs_hat = torch.randn(2, 3, 4)

# The func parameter defaults to torch.nn.functional.mse_loss
# which is already imported as F.mse_loss
func = torch.nn.functional.mse_loss

ARGS = {
    "bs": bs,
    "bs_hat": bs_hat,
    "func": func,
}
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 0, dtype family float, shape () — shape () 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
scatter Not yet run
unverified (harvested, no recorded run)
agnJason/PianoMotion10M/models/BalancedDataParallel.py
code served (permissive licence) · get_code("e44e6e20f6209f87")
How it ran

no invocation recorded.

scatter_kwargs Not yet run
unverified (harvested, no recorded run)
agnJason/PianoMotion10M/models/BalancedDataParallel.py
code served (permissive licence) · get_code("ca2a9ebf352702e2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 6 the same month, 5 later) and 5 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
exists
brick of this paper's assembly: helper
144 other papers
86 dated earlier, 5 the same month, 48 later, 5 same year, order not determinable · 40 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 141 more not named here
default
brick of this paper's assembly: helper
79 other papers
43 dated earlier, 1 the same month, 32 later, 3 same year, order not determinable · 15 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
and 76 more not named here
identity
brick of this paper's assembly: helper
54 other papers
33 dated earlier, 1 the same month, 19 later, 1 same year, order not determinable · 11 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 51 more not named here
linear_beta_schedule
brick of this paper's assembly: scheduler
18 other papers
6 dated earlier, 1 the same month, 11 later · 12 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
and 15 more not named here
cosine_beta_schedule
brick of this paper's assembly: scheduler
13 other papers
7 dated earlier, 1 the same month, 5 later · 5 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2303.11579 (2023-03)
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
2303.17959 (2023-03)
Diffusion Action Segmentation
and 10 more not named here
scatter_kwargs 11 other papers
10 dated earlier, 1 the same month
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2106.06295 (2021-06)
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
2204.03883 (2022-04)
Vision Transformers for Single Image Dehazing
and 8 more not named here
init_biased_mask 4 other papers
4 dated earlier
2112.05329 (2021-12)
FaceFormer: Speech-Driven 3D Facial Animation with Transformers
2303.11089 (2023-03)
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation
2306.10799 (2023-06)
SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces
and 1 more not named here
linear_interpolation 2 other papers
2 dated earlier
2112.05329 (2021-12)
FaceFormer: Speech-Driven 3D Facial Animation with Transformers
2303.11089 (2023-03)
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation
scatter 2 other papers
2 dated earlier
2023.findings-acl.765 (2023 (year only))
Explanation Regeneration via Information Bottleneck
2303.15043 (2023-03)
Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time
enc_dec_mask 1 other paper
1 dated earlier
2303.11089 (2023-03)
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation

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

Recently, artificial intelligence techniques for education have been received increasing attentions, while it still remains an open problem to design the effective music instrument instructing systems. Although key presses can be directly derived from sheet music, the transitional movements among key presses require more extensive guidance in piano performance. In this work, we construct a pianohand motion generation benchmark to guide hand movements and fingerings for piano playing. To this end, we collect an annotated dataset, PianoMotion10M, consisting of 116 hours of piano playing videos from a bird's-eye view with 10 million annotated hand poses. We also introduce a powerful baseline model that generates hand motions from piano audios through a position predictor and a position-guided gesture generator. Furthermore, a series of evaluation metrics are designed to assess the performance of the baseline model, including motion similarity, smoothness, positional accuracy of left and right hands, and overall fidelity of movement distribution. Despite that piano key presses with respect to music scores or audios are already accessible, PianoMotion10M aims to provide guidance on piano fingering for instruction purposes. The source code and dataset can be accessed at https://github.com/agnJason/PianoMotion10M.

For agents

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

get_harvested_code_for_paper("2406.09326")
get_code_for_paper("2406.09326")
have("2406.09326")

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

curl https://syntology.ai/api/ran/2406.09326.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.09326.svg)](https://syntology.ai/paper/2406.09326)

Connect an agent — have() is free.