SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_29448 · AAAI · 2024

A Two-Stage Information Extraction Network for Incomplete Multi-View Multi-Label Classification

Chengliang Liu, Jie Wen, Xin Tan, Ce Zhao, Zhanyan Tang

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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/aaai_29448.json · badge: /api/ran/aaai_29448.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
KevinTan10/TSIEN canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
compare_supervise_value Ran
ran on a synthesized input
KevinTan10/TSIEN/evaluation.py
code served (permissive licence) · get_code("511490822da4e487")
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 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

torch.manual_seed(0)

# Test case 1: 'ranking loss' supervision with supervise_value1 > supervise_value2
ARGS = {
    'supervise': 'ranking loss',
    'supervise_value1': 0.5,
    'supervise_value2': 0.3
}
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 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
do_metric Ran
ran on a synthesized input
KevinTan10/TSIEN/evaluation.py
code served (permissive licence) · get_code("fd4af3ccd1e85582")
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 (9,) 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

# Set up small test data for multi-label classification
# y_prob: probability predictions, shape (num_samples, num_labels)
# label: binary labels, shape (num_samples, num_labels)

np.random.seed(0)

num_samples = 2
num_labels = 4

# Create probability predictions (values between 0 and 1)
y_prob = np.random.rand(num_samples, num_labels).astype(np.float64)

# Create binary labels (0 or 1, represented as > 0.5 checks)
label = (np.random.rand(num_samples, num_labels) > 0.5).astype(np.float64)

# Ensure there's at least one positive and negative label per label column
# to avoid division by zero in AUC computation
label[0, 0] = 1.0
label[1, 0] = 0.0
label[0, 1] = 1.0
label[1, 1] = 0.0

ARGS = {
    "y_prob": y_prob,
    "label": label
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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 (9,) — shape (9,) 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_supervise Ran
ran on a synthesized input
KevinTan10/TSIEN/evaluation.py
code served (permissive licence) · get_code("0d3bef041e3e7fd0")
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 torch
import numpy as np

torch.manual_seed(0)

# The function takes a single parameter 'supervise' which is a string
# It checks the value against different metric types and returns a corresponding loss/metric value
# We need to provide a valid string that matches one of the conditions

ARGS = {
    'supervise': 'ranking loss'
}
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
setLogger Ran
ran on a synthesized input
KevinTan10/TSIEN/utils.py
code served (permissive licence) · get_code("ea457b48256b6714")
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 RootLogger. 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 logging
import tempfile
import os

# Create a temporary file path for logging
temp_dir = tempfile.gettempdir()
logfile_path = os.path.join(temp_dir, "test_logger.log")

ARGS = {
    "logfile": logfile_path
}
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 RootLogger — a RootLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RootLogger 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
getComDataloader Not yet run
unverified (harvested, no recorded run)
KevinTan10/TSIEN/MLdataset.py
code served (permissive licence) · get_code("2c4a1103809b644f")
How it ran

no invocation recorded.

loadMfDIMvMlDataFromMat Not yet run
unverified (harvested, no recorded run)
KevinTan10/TSIEN/MLdataset.py
code served (permissive licence) · get_code("f3681cfe566bd22b")
How it ran

no invocation recorded.

loadMvMlDataFromMat Not yet run
unverified (harvested, no recorded run)
KevinTan10/TSIEN/MLdataset.py
code served (permissive licence) · get_code("f81f9f77aed469ee")
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, 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
compare_supervise_value 1 other paper
1 dated earlier
2303.08358 (2023-03)
DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification
init_supervise 1 other paper
1 dated earlier
2303.08358 (2023-03)
DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification

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, multi-view multi-label classification (MvMLC) has received a significant amount of research interest and many methods have been proposed based on the assumptions of view completion and label completion. However, in realworld scenarios, multi-view multi-label data tends to be incomplete due to various uncertainties involved in data collection and manual annotation. As a result, the conventional MvMLC methods fail. In this paper, we propose a new twostage MvMLC network to solve this incomplete MvMLC issue with partial missing views and missing labels. Different from the existing works, our method attempts to leverage the diverse information from the partially missing data based on the information theory. Specifically, our method aims to minimize task-irrelevant information while maximizing task-relevant information through the principles of information bottleneck theory and mutual information extraction. The first stage of our network involves training viewspecific classifiers to concentrate the task-relevant information. Subsequently, in the second stage, the hidden states of these classifiers serve as input for an alignment model, an autoencoder-based mutual information extraction framework, and a weighted fusion classifier to make the final prediction. Extensive experiments performed on five datasets validate that our method outperforms other state-of-the-art methods. Code is available at https://github.com/KevinTan10/TSIEN.

For agents

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

get_harvested_code_for_paper("aaai_29448")
get_code_for_paper("aaai_29448")
have("aaai_29448")

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

curl https://syntology.ai/api/ran/aaai_29448.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_29448.svg)](https://syntology.ai/paper/aaai_29448)

Connect an agent — have() is free.