SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.07428 · 2024

Just Label the Repeats for In-The-Wild Audio-to-Score Alignment

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 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/2411.07428.json · badge: /api/ran/2411.07428.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
irmakbky/jltr-alignment canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
beam_search Ran
ran; our contract draft was wrong, not the code
irmakbky/jltr-alignment/magenta/common/beam_search.py
code served (permissive licence) · get_code("fc965e87e24dc01d")
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 copy
import torch

torch.manual_seed(0)

# Define a simple generate_step_fn that extends sequences and updates states/scores
def generate_step_fn(sequences, states, scores):
    """
    Extends each sequence by one step, updates state, and updates score.
    
    Args:
        sequences: list of sequences (each is a list of integers)
        states: list of states (each is a dict with 'step_count')
        scores: list of scores (floats)
    
    Returns:
        tuple of (extended_sequences, updated_states, updated_scores)
    """
    new_sequences = []
    new_states = []
    new_scores = []
    
    for seq, state, score in zip(sequences, states, scores):
        # Extend sequence by appending next token (simple: just append step_count)
        new_seq = seq + [state['step_count']]
        
        # Update state: increment step_count
        new_state = copy.deepcopy(state)
        new_state['step_count'] += 1
        
        # Update score: add a small random bonus
        new_score = score + torch.randn(1).item() * 0.1
        
        new_sequences.append(new_seq)
        new_states.append(new_state)
        new_scores.append(new_score)
    
    return new_sequences, new_states, new_scores


# Define initial sequence and state
initial_sequence = [0, 1]
initial_state = {'step_count': 2, 'hidden': torch.randn(4)}

ARGS = {
    'initial_sequence': initial_sequence,
    'initial_state': initial_state,
    'generate_step_fn': generate_step_fn,
    'num_steps': 8,
    'beam_size': 3,
    'branch_factor': 2,
    'steps_per_iteration': 2,
}
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 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
estimateLineSep Ran
ran; our contract draft was wrong, not the code
irmakbky/jltr-alignment/mus_align/score/detect_noteheads.py
code served (permissive licence) · get_code("da4baafdd3caa596")
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 numpy as np
from scipy.signal import convolve2d

# Create a small synthetic image (simulating a scanned document page)
# The function expects a grayscale image where text appears as dark regions
np.random.seed(0)

# Create a small test image with some structure
# pim should be a 2D array (height x width)
imgHeight = 64
imgWidth = 80
pim = np.random.randint(100, 256, size=(imgHeight, imgWidth)).astype(np.uint8)

# Add some darker regions to simulate text lines
for line_idx in range(0, imgHeight, 10):
    pim[line_idx:line_idx+2, :] = np.random.randint(50, 100, size=(2, imgWidth))

# Parameters for the function
ncols = 3  # number of column regions to analyze
lrange = 6  # lower bound of line separation range
urange = 20  # upper bound of line separation range
delta = 2  # step size for line separation search

ARGS = {
    'pim': pim,
    'ncols': ncols,
    'lrange': lrange,
    'urange': urange,
    'delta': delta
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
getPenalizedCombFilter Ran
ran, honoured the contract we drafted
irmakbky/jltr-alignment/mus_align/score/detect_noteheads.py
code served (permissive licence) · get_code("e1f790617a192362")
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 (12,) 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

# The function takes a single parameter: linesep
# which should be a numeric value representing line separation
# The function uses it in calculations with np.round and multiplication

ARGS = {
    "linesep": 2.5
}
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 (12,) — shape (12,) 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_info_from_key_sig Ran
ran; our contract draft was wrong, not the code
irmakbky/jltr-alignment/mus_align/score/bootleg.py
code served (permissive licence) · get_code("8351c90a9428ef34")
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 dict. 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.

class MockClef:
    def __init__(self, name):
        self.name = name

class MockKeySig:
    def __init__(self, name):
        self.name = name

clefs = [MockClef('TREBLE'), MockClef('BASS')]
key_sig = MockKeySig('G_MAJOR')
transposition_factor = 2

ARGS = {
    'clefs': clefs,
    'key_sig': key_sig,
    'transposition_factor': transposition_factor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_scale_notes Ran
ran; our contract draft was wrong, not the code
irmakbky/jltr-alignment/mus_align/score/bootleg.py
code served (permissive licence) · get_code("d9ec0f689a298e7f")
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 list, ndim 1, 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.

class Clef:
    def __init__(self, name):
        self.name = name

clef = Clef('TREBLE')
sharps = ['F', 'C']
flats = ['B']
transposition_factor = 2

ARGS = {
    'clef': clef,
    'sharps': sharps,
    'flats': flats,
    'transposition_factor': transposition_factor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
removeBkgdLighting Ran
ran; our contract draft was wrong, not the code
irmakbky/jltr-alignment/mus_align/score/detect_noteheads.py
code served (permissive licence) · get_code("5c448b3b824597a3")
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 Image. 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.

from PIL import Image
import numpy as np

# Create a small test image as PIL Image
# The function expects a PIL Image object
img_array = np.random.randint(50, 200, size=(120, 150, 3), dtype=np.uint8)
test_image = Image.fromarray(img_array, mode='RGB')

ARGS = {
    'pimg': test_image,
    'filtsz': 5,
    'thumbnailW': 100,
    'thumbnailH': 100,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
serialized Ran
ran; our contract draft was wrong, not the code
irmakbky/jltr-alignment/magenta/common/concurrency.py
code served (permissive licence) · get_code("51cf513fe9f6c28e")
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 functools
import threading

def serialized(func):
    """Decorator to provide mutual exclusion for method using _lock attribute."""

    @functools.wraps(func)
    def serialized_method(self, *args, **kwargs):
        lock = getattr(self, '_lock')
        with lock:
            return func(self, *args, **kwargs)
    return serialized_method


class MockObject:
    def __init__(self):
        self._lock = threading.Lock()
    
    @serialized
    def example_method(self, x, y):
        return x + y


def dummy_func(self, x, y):
    return x * y


ARGS = {
    'func': dummy_func
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 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
beam_search 2 other papers
2 dated earlier
1804.09399 (2018-04)
Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
1904.02632 (2019-04)
A Learned Representation for Scalable Vector Graphics
serialized 2 other papers
2 dated earlier
1804.09399 (2018-04)
Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
1904.02632 (2019-04)
A Learned Representation for Scalable Vector Graphics

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 an efficient workflow for high-quality offline alignment of in-the-wild performance audio and corresponding sheet music scans (images). Recent work on audio-to-score alignment extends dynamic time warping (DTW) to be theoretically able to handle jumps in sheet music induced by repeat signs-this method requires no human annotations, but we show that it often yields low-quality alignments. As an alternative, we propose a workflow and interface that allows users to quickly annotate jumps (by clicking on repeat signs), requiring a small amount of human supervision but yielding much higher quality alignments on average. Additionally, we refine audio and score feature representations to improve alignment quality by: (1) integrating measure detection into the score feature representation, and (2) using raw onset prediction probabilities from a music transcription model instead of piano roll. We propose an evaluation protocol for audio-to-score alignment that computes the distance between the estimated and ground truth alignment in units of measures. Under this evaluation, we find that our proposed jump annotation workflow and improved feature representations together improve alignment accuracy by 150% relative to prior work (33% to 82%).

For agents

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

get_harvested_code_for_paper("2411.07428")
get_code_for_paper("2411.07428")
have("2411.07428")

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

curl https://syntology.ai/api/ran/2411.07428.json

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

[![Syntology run record](https://syntology.ai/api/ran/2411.07428.svg)](https://syntology.ai/paper/2411.07428)

Connect an agent — have() is free.