SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.02385 · 2022

MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 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/2203.02385.json · badge: /api/ran/2203.02385.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
zerohd4869/mm-dfn canonical (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
edge_perms Ran
ran, honoured the contract we drafted
zerohd4869/mm-dfn/code/model.py
code served (permissive licence) · get_code("788e7ba8a42fe51c")
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 2, 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 numpy as np

ARGS = {
    "l": 5,
    "window_past": 2,
    "window_future": 1
}
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 list, ndim 2, 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
get_train_valid_sampler Ran
ran on a synthesized input
zerohd4869/mm-dfn/code/run_train_erc.py
code served (permissive licence) · get_code("828716810d62f8c3")
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, 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.

import torch
import torch.nn as nn
from torch.utils.data import Dataset

torch.manual_seed(0)

class DummyDataset(Dataset):
    def __init__(self, size=20):
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return torch.randn(4), torch.randint(0, 2, (1,))

trainset = DummyDataset(size=20)

ARGS = {
    "trainset": trainset,
    "valid": 0.1
}
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, ndim 1, dtype family float — a tuple 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
pad Ran
ran on a synthesized input
zerohd4869/mm-dfn/code/model.py
code served (permissive licence) · get_code("10f8b1f4c189a2d5")
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 (5, 4) as a later run recorded it. 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, 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create a small tensor with shape (2, 4) - 2 is the sequence length, 4 is feature dim
tensor_arg = torch.randn(2, 4)

# Create a Variable from the tensor (for testing the Variable branch)
# Note: In modern PyTorch, Variable is deprecated and tensors are Variables by default
var_arg = Variable(torch.randn(3, 5))

# Test with a length that requires padding
length_arg = 5

# no_cuda flag - set to True since we're CPU-only
no_cuda_arg = True

# Test case 1: Regular tensor that needs padding
ARGS = {
    "tensor": tensor_arg,
    "length": length_arg,
    "no_cuda": no_cuda_arg
}
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 (5, 4) — shape (5, 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
simple_batch_graphify Ran
ran on a synthesized input
zerohd4869/mm-dfn/code/model.py
code served (permissive licence) · get_code("c62a6bdab532578b")
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. 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

torch.manual_seed(0)

# Construct arguments for simple_batch_graphify
# The function expects:
# - features: a 3D tensor of shape (max_seq_len, batch_size, feature_dim)
# - lengths: a list/tensor of sequence lengths for each item in the batch
# - no_cuda: a boolean flag

# Create a small 3D tensor: (seq_len=5, batch_size=2, feature_dim=4)
features = torch.randn(5, 2, 4)

# Create lengths for each item in the batch
# Item 0 has length 3, item 1 has length 4
lengths = [3, 4]

# CPU only - set no_cuda to True to avoid CUDA operations
no_cuda = True

ARGS = {
    "features": features,
    "lengths": lengths,
    "no_cuda": no_cuda
}
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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 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
get_train_valid_sampler 2 other papers
1 dated earlier, 1 later
2002.08267 (2020-02)
Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation
aaai_26541 (2023 (year only))
SKIER: A Symbolic Knowledge Integrated Model for Conversational Emotion Recognition
edge_perms 1 other paper
1 dated earlier
1908.11540 (2019-08)
DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation
pad 1 other paper
1 dated earlier
1908.11540 (2019-08)
DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation

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

Emotion Recognition in Conversations (ERC) has considerable prospects for developing empathetic machines. For multimodal ERC, it is vital to understand context and fuse modality information in conversations. Recent graph-based fusion methods generally aggregate multimodal information by exploring unimodal and cross-modal interactions in a graph. However, they accumulate redundant information at each layer, limiting the context understanding between modalities. In this paper, we propose a novel Multimodal Dynamic Fusion Network (MM-DFN) to recognize emotions by fully understanding multimodal conversational context. Specifically, we design a new graph-based dynamic fusion module to fuse multimodal contextual features in a conversation. The module reduces redundancy and enhances complementarity between modalities by capturing the dynamics of contextual information in different semantic spaces. Extensive experiments on two public benchmark datasets demonstrate the effectiveness and superiority of MM-DFN.

For agents

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

get_harvested_code_for_paper("2203.02385")
get_code_for_paper("2203.02385")
have("2203.02385")

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

curl https://syntology.ai/api/ran/2203.02385.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.02385.svg)](https://syntology.ai/paper/2203.02385)

Connect an agent — have() is free.