SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.02724 · 2022

Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision

arXiv · PDF · Open in the Atlas

Code that ran

4 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 3 have no contract verdict; 0 failures of our instrument; 3 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/2210.02724.json · badge: /api/ran/2210.02724.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
JieyuZ2/wrench canonical (classifier label)
classifier basis not recorded on the link
4 ran · 3 no recorded run
FunctionStatusWhere it lives
calc_prior Ran
ran on a synthesized input
JieyuZ2/wrench/wrench/endmodel/ars2.py
code served (permissive licence) · get_code("3fa1363dd8984924")
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 int; 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 torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# calc_prior takes:
# - labels: List - used with labels.count(i) in a loop
# - n_class: int - used in range(n_class)
# The function counts occurrences of each class index in the labels list

# Create sample labels list with some class indices
labels = [0, 1, 1, 2, 0, 1, 2, 2]

# Number of classes
n_class = 3

ARGS = {
    "labels": labels,
    "n_class": n_class,
}
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 list, ndim 1, dtype family int — 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
contrastive_loss Ran
ran on a synthesized input
JieyuZ2/wrench/wrench/endmodel/cosine.py
code served (permissive licence) · get_code("8c515f7346076b72")
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 inputs and feat
# inputs: logits or probabilities, shape (batch_size, num_classes)
# feat: features, shape (batch_size, feature_dim)
batch_size = 2
num_classes = 4
feature_dim = 3

inputs = torch.randn(batch_size, num_classes)
feat = torch.randn(batch_size, feature_dim)

device = torch.device('cpu')

ARGS = {
    'inputs': inputs,
    'feat': feat,
    'margin': 2.0,
    'device': device
}
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
random_embedding Ran
ran, honoured the contract we drafted
JieyuZ2/wrench/wrench/layers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from jiacheng-ye/UANet, is pointer only (licence: NONE) · get_code("ffcb36e0c6ef81dd")
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 jiacheng-ye/UANet, and GitHub detected no licence in that repository when it was checked. 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.

soft_frequency Ran
ran on a synthesized input
JieyuZ2/wrench/wrench/endmodel/cosine.py
code served (permissive licence) · get_code("8b6fde8bcb2e818b")
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 2, dtype family float, shape (2, 4) 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 as nn

torch.manual_seed(0)

# Create a small logits tensor
# Shape: (batch_size=2, num_classes=4)
logits = torch.randn(2, 4)

# ARGS dictionary mapping all parameters
ARGS = {
    "logits": logits,
    "probs": 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 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
calc_loss Not yet run
unverified (harvested, no recorded run)
JieyuZ2/wrench/wrench/endmodel/cosine.py
code served (permissive licence) · get_code("ad14014186a0bf9e")
How it ran

no invocation recorded.

check_bert_model Not yet run
unverified (harvested, no recorded run)
JieyuZ2/wrench/wrench/basemodel.py
code served (permissive licence) · get_code("c9a213796a572f53")
How it ran

no invocation recorded.

check_vision_model Not yet run
unverified (harvested, no recorded run)
JieyuZ2/wrench/wrench/basemodel.py
code served (permissive licence) · get_code("4ac4f520b6d01aa2")
How it ran

no invocation recorded.

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, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
random_embedding 2 other papers
2 dated earlier
2010.08895 (2020-10)
Fourier Neural Operator for Parametric Partial Differential Equations
2012.10608 (2020-12)
Uncertainty-Aware Label Refinement for Sequence Labeling
calc_loss 1 other paper
1 dated earlier
2010.08895 (2020-10)
Fourier Neural Operator for Parametric Partial Differential Equations
check_bert_model 1 other paper
1 dated earlier
2010.08895 (2020-10)
Fourier Neural Operator for Parametric Partial Differential Equations
check_vision_model 1 other paper
1 dated earlier
2010.08895 (2020-10)
Fourier Neural Operator for Parametric Partial Differential Equations
contrastive_loss 1 other paper
1 dated earlier
2010.08895 (2020-10)
Fourier Neural Operator for Parametric Partial Differential Equations
soft_frequency 1 other paper
1 dated earlier
2010.08895 (2020-10)
Fourier Neural Operator for Parametric Partial Differential Equations

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

Programmatic Weak Supervision (PWS) has emerged as a widespread paradigm to synthesize training labels efficiently. The core component of PWS is the label model, which infers true labels by aggregating the outputs of multiple noisy supervision sources abstracted as labeling functions (LFs). Existing statistical label models typically rely only on the outputs of LF, ignoring the instance features when modeling the underlying generative process. In this paper, we attempt to incorporate the instance features into a statistical label model via the proposed FABLE. In particular, it is built on a mixture of Bayesian label models, each corresponding to a global pattern of correlation, and the coefficients of the mixture components are predicted by a Gaussian Process classifier based on instance features. We adopt an auxiliary variable-based variational inference algorithm to tackle the non-conjugate issue between the Gaussian Process and Bayesian label models. Extensive empirical comparison on eleven benchmark datasets sees FABLE achieving the highest averaged performance across nine baselines.

For agents

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

get_harvested_code_for_paper("2210.02724")
get_code_for_paper("2210.02724")
have("2210.02724")

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

curl https://syntology.ai/api/ran/2210.02724.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.02724.svg)](https://syntology.ai/paper/2210.02724)

Connect an agent — have() is free.