SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.00163 · 2020

Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 3 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2002.00163.json · badge: /api/ran/2002.00163.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
ictnlp/DSTC8-AVSD community (classifier label)
classifier basis: plan_row
5 ran · 0 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran on a synthesized input
ictnlp/DSTC8-AVSD/dataset.py
code served (permissive licence) · get_code("d645589251b05e85")
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 3, 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

torch.manual_seed(0)

# Create a batch of data items
# Each item is a tuple of (input_ids, token_type_ids, lm_labels, [i3d])
# input_ids: 1D tensor of token indices
# token_type_ids: 1D tensor of token type ids
# lm_labels: 1D tensor of labels
# i3d: 2D tensor of video features (optional)

batch_without_features = [
    (
        torch.tensor([1, 2, 3], dtype=torch.long),
        torch.tensor([0, 0, 1], dtype=torch.long),
        torch.tensor([1, 2, 3], dtype=torch.long),
    ),
    (
        torch.tensor([4, 5], dtype=torch.long),
        torch.tensor([1, 1], dtype=torch.long),
        torch.tensor([4, 5], dtype=torch.long),
    ),
]

batch_with_features = [
    (
        torch.tensor([1, 2, 3], dtype=torch.long),
        torch.tensor([0, 0, 1], dtype=torch.long),
        torch.tensor([1, 2, 3], dtype=torch.long),
        torch.randn((3, 4)),
    ),
    (
        torch.tensor([4, 5], dtype=torch.long),
        torch.tensor([1, 1], dtype=torch.long),
        torch.tensor([4, 5], dtype=torch.long),
        torch.randn((2, 4)),
    ),
]

pad_token = 0

ARGS = {
    "batch": batch_without_features,
    "pad_token": pad_token,
    "features": None,
}
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 3, dtype family int — 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
gelu Ran
ran; our contract draft was wrong, not the code
ictnlp/DSTC8-AVSD/VideoGPT2.py
code served (permissive licence) · get_code("8d23fbe2b99b840b")
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 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 math

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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
get_dataset Ran
ran on a synthesized input
ictnlp/DSTC8-AVSD/dataset.py
code served (permissive licence) · get_code("91592b72681a74a3")
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.

import json
import tempfile
import os

class MockTokenizer:
    def tokenize(self, text):
        # Simple mock: split by spaces and add token markers
        return ['[CLS]'] + text.split() + ['[SEP]']
    
    def convert_tokens_to_ids(self, tokens):
        # Simple mock: map each token to a unique id
        token_to_id = {
            '[CLS]': 101,
            '[SEP]': 102,
            'a': 1000,
            'cat': 1001,
            'sat': 1002,
            'on': 1003,
            'mat': 1004,
            'test': 1005,
            'caption': 1006,
            'summary': 1007,
            'question': 1008,
            'answer': 1009,
            '__UNDISCLOSED__': 1010,
        }
        return [token_to_id.get(token, 999) for token in tokens]

# Create a temporary JSON data file
mock_data = {
    "dialogs": [
        {
            "image_id": "vid_001",
            "caption": "a cat sat",
            "summary": "test summary",
            "dialog": [
                {"question": "what animal", "answer": "cat"},
                {"question": "where sitting", "answer": "mat"},
                {"question": "color", "answer": "__UNDISCLOSED__"}
            ]
        },
        {
            "image_id": "vid_002",
            "caption": "another test",
            "summary": "another summary",
            "dialog": [
                {"question": "test q1", "answer": "test a1"},
                {"question": "test q2", "answer": "__UNDISCLOSED__"}
            ]
        }
    ]
}

# Write to temporary file
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.json')
json.dump(mock_data, temp_file)
temp_file.close()

ARGS = {
    'tokenizer': MockTokenizer(),
    'data_file': temp_file.name,
    'feature_path': None,
    'undisclosed_only': False,
    'n_history': 3
}
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
tokenize Ran
ran on a synthesized input
ictnlp/DSTC8-AVSD/dataset.py
code served (permissive licence) · get_code("6a891e00701aa131")
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

class MockTokenizer:
    def tokenize(self, text):
        # Simple mock tokenizer that splits on spaces and returns tokens
        return text.split()
    
    def convert_tokens_to_ids(self, tokens):
        # Simple mock that converts tokens to ids based on their hash
        return [hash(token) % 1000 for token in tokens]

# Create a mock tokenizer instance
tokenizer = MockTokenizer()

# Test the function behavior by examining what it does:
# 1. If obj is a string: calls tokenizer.tokenize() and tokenizer.convert_tokens_to_ids()
# 2. If obj is a dict: recursively tokenizes each value
# 3. Otherwise: treats as iterable and recursively tokenizes each element

# Create test data covering all three cases
test_string = "hello world"
test_dict = {
    "text": "foo bar",
    "nested": ["hello", "world"]
}
test_list = ["hello", "foo bar"]

ARGS = {
    "obj": test_string,
    "tokenizer": tokenizer
}
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
top_filtering Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ictnlp/DSTC8-AVSD/generate.py
code served (permissive licence) · get_code("695eaa24be6f2a1d")
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 torch.nn.functional as F

torch.manual_seed(0)

# Create a small logits tensor (vocabulary size of 10)
logits = torch.randn(10)

# Define arguments for the top_filtering function
ARGS = {
    'logits': logits,
    'top_k': 5,
    'top_p': 0.9,
    'threshold': -2.0,
    'filter_value': -float('Inf')
}
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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 2 later) and 3 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
gelu 51 other papers
11 dated earlier, 1 the same month, 39 later · 8 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
and 48 more not named here
top_filtering 7 other papers
3 dated earlier, 1 the same month, 3 later
1901.08149 (2019-01)
TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
1904.09751 (2019-04)
THE CURIOUS CASE OF NEURAL TEXT DeGENERATION
1911.00536 (2019-11)
DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
and 4 more not named here

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8). To solve the task, we propose a universal multimodal transformer and introduce the multi-task learning method to learn joint representations among different modalities as well as generate informative and fluent responses. Our method extends the natural language generation pre-trained model to multimodal dialogue generation task. Our system achieves the best performance in both objective and subjective evaluations in the challenge.

For agents

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

get_harvested_code_for_paper("2002.00163")
get_code_for_paper("2002.00163")
have("2002.00163")

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

curl https://syntology.ai/api/ran/2002.00163.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.00163.svg)](https://syntology.ai/paper/2002.00163)

Connect an agent — have() is free.