SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1606.06259 · 2016

MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 5 have no contract verdict; 0 failures of our instrument; 1 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/1606.06259.json · badge: /api/ran/1606.06259.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
soujanyaporia/multimodal-sentiment-analysis community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
soujanyaporia/contextual-multimodal-fusion community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
calc_test_result Ran
ran on a synthesized input
soujanyaporia/contextual-multimodal-fusion/trimodal_attention_models.py
code served (permissive licence) · get_code("554151737f430fcc")
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 numpy as np
import torch

torch.manual_seed(0)

# Create sample data
# result: predicted logits/probabilities with shape (batch_size, sequence_length, num_classes)
batch_size = 2
sequence_length = 3
num_classes = 4

result = np.random.randn(batch_size, sequence_length, num_classes).astype(np.float32)

# test_label: gold labels with same shape as result (one-hot or logits)
test_label = np.random.randn(batch_size, sequence_length, num_classes).astype(np.float32)

# test_mask: binary mask indicating which positions to evaluate (1 = evaluate, 0 = ignore)
test_mask = np.random.randint(0, 2, size=(batch_size, sequence_length)).astype(np.int32)
# Ensure at least some positions are marked as 1
test_mask[0, 0] = 1
test_mask[0, 1] = 1
test_mask[1, 0] = 1

# print_detailed_results flag
print_detailed_results = True

ARGS = {
    'result': result,
    'test_label': test_label,
    'test_mask': test_mask,
    'print_detailed_results': print_detailed_results
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, 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
createOneHot Ran
ran on a synthesized input
soujanyaporia/multimodal-sentiment-analysis/data_prep.py
code served (permissive licence) · get_code("d9e0bcc53d0d02b1")
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

# Create small sample label arrays with shape (batch_size, sequence_length)
# Labels should be integers representing class indices
train_label = np.array([[0, 1, 2], [1, 2, 0]], dtype=np.int32)
test_label = np.array([[2, 0], [1, 1]], dtype=np.int32)

ARGS = {
    'train_label': train_label,
    'test_label': test_label
}
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 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
createOneHotMosei2way Ran
ran on a synthesized input
soujanyaporia/multimodal-sentiment-analysis/data_prep.py
code served (permissive licence) · get_code("83df8e0058e82e28")
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

# Create small sample label arrays
# Shape: (batch_size, sequence_length)
train_label = np.array([
    [0.5, -0.3, 0.1, 0.8],
    [-0.2, 0.4, -0.5, 0.2]
], dtype=np.float32)

test_label = np.array([
    [0.1, -0.1],
    [0.3, -0.4]
], dtype=np.float32)

ARGS = {
    "train_label": train_label,
    "test_label": test_label
}
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 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
createOneHotMosei3way Ran
ran on a synthesized input
soujanyaporia/multimodal-sentiment-analysis/data_prep.py
code served (permissive licence) · get_code("466577bea7ea7593")
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

# Create small sample label arrays
# train_label: shape (2, 4) - 2 samples, 4 timesteps
# test_label: shape (3, 5) - 3 samples, 5 timesteps
train_label = np.array([
    [1.5, -0.5, 0.0, 2.0],
    [-1.0, 0.0, 1.2, -0.8]
], dtype=np.float32)

test_label = np.array([
    [0.5, -1.5, 0.0],
    [2.0, 0.0, -0.3],
    [-2.5, 1.0, 0.0]
], dtype=np.float32)

ARGS = {
    "train_label": train_label,
    "test_label": test_label,
}
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 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
create_mask Ran
ran on a synthesized input
soujanyaporia/contextual-multimodal-fusion/trimodal_attention_models.py
code served (permissive licence) · get_code("5d48dbaa71ca5e6a")
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
import gc
import pickle

# Construct small test data
# train_data: shape (num_train_samples, max_sequence_length)
# test_data: shape (num_test_samples, max_sequence_length)
train_data = np.random.randn(2, 5).astype('float32')  # 2 samples, max length 5
test_data = np.random.randn(3, 4).astype('float32')   # 3 samples, max length 4

# train_length: list of actual lengths for each training sample
train_length = [3, 5]  # First sample has 3 actual timesteps, second has 5

# test_length: list of actual lengths for each test sample
test_length = [2, 4, 3]  # Three test samples with lengths 2, 4, 3

ARGS = {
    'train_data': train_data,
    'test_data': test_data,
    'train_length': train_length,
    'test_length': test_length
}
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 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
create_one_hot_labels Not yet run
unverified (harvested, no recorded run)
soujanyaporia/contextual-multimodal-fusion/trimodal_attention_models.py
code served (permissive licence) · get_code("face24f110e23bad")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

People are sharing their opinions, stories and reviews through online video sharing websites every day. Studying sentiment and subjectivity in these opinion videos is experiencing a growing attention from academia and industry. While sentiment analysis has been successful for text, it is an understudied research question for videos and multimedia content. The biggest setbacks for studies in this direction are lack of a proper dataset, methodology, baselines and statistical analysis of how information from different modality sources relate to each other. This paper introduces to the scientific community the first opinion-level annotated corpus of sentiment and subjectivity analysis in online videos called Multimodal Opinion-level Sentiment Intensity dataset (MOSI). The dataset is rigorously annotated with labels for subjectivity, sentiment intensity, per-frame and per-opinion annotated visual features, and per-milliseconds annotated audio features. Furthermore, we present baselines for future studies in this direction as well as a new multimodal fusion approach that jointly models spoken words and visual gestures.

For agents

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

get_harvested_code_for_paper("1606.06259")
get_code_for_paper("1606.06259")
have("1606.06259")

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

curl https://syntology.ai/api/ran/1606.06259.json

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

[![Syntology run record](https://syntology.ai/api/ran/1606.06259.svg)](https://syntology.ai/paper/1606.06259)

Connect an agent — have() is free.