SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.14622 · 2024

Language Repository for Long Video Understanding

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 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/2403.14622.json · badge: /api/ran/2403.14622.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
kkahatapitiya/langrepo canonical (classifier label)
classifier basis: census
9 ran · 0 no recorded run
FunctionStatusWhere it lives
clean_text Ran
ran; our contract draft was wrong, not the code
kkahatapitiya/langrepo/util.py
code served (permissive licence) · get_code("d3cd8c8e5b09319c")
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 str. 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 torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    'txt': 'Hello world . This is a test... with.. multiple  spaces and punctuation.'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
do_nothing Ran
ran, honoured the contract we drafted
kkahatapitiya/langrepo/merge.py
code served (permissive licence) · get_code("bd041cf95d856b5d")
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

torch.manual_seed(0)

ARGS = {
    "x": torch.randn(2, 4),
    "mode": 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 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
first_char_after_anchor Ran
ran; our contract draft was wrong, not the code
kkahatapitiya/langrepo/prompts.py
code served (permissive licence) · get_code("7beee5e0aa97c0e8")
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 function. 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 torch

# Analyze the function: first_char_after_anchor takes an 'anchor' parameter
# The returned function f takes 'res' (a string) and:
# - Finds the anchor in res using res.find(anchor)
# - Gets the character after the anchor
# - Maps it to a number using a hardcoded mapping

# The anchor parameter should be a string
anchor = "MARKER"

ARGS = {
    "anchor": anchor
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
first_char_as_answer Ran
ran, honoured the contract we drafted
kkahatapitiya/langrepo/prompts.py
code served (permissive licence) · get_code("ef77f23d65b9a1cf")
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 int, ndim 0, dtype family int, 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)

ARGS = {
    'res': 'Answer: A'
}
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 int, ndim 0, dtype family int, 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
identity Ran
ran, honoured the contract we drafted
kkahatapitiya/langrepo/prompts.py
code served (permissive licence) · get_code("036725c05a3d96f8")
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
import numpy as np

torch.manual_seed(0)

# The identity function simply returns its input
# So res can be any value - let's use a simple tensor
res = torch.randn(2, 4)

ARGS = {
    "res": res
}
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 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
init_generator Ran
ran; our contract draft was wrong, not the code
kkahatapitiya/langrepo/merge.py
code served (permissive licence) · get_code("c66afae7b5227098")
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 Generator. 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)

# The function takes a device and an optional fallback generator
# It creates a generator on the given device and seeds it from the current RNG state

device_cpu = torch.device('cpu')
fallback_generator = torch.Generator(device='cpu')

ARGS = {
    'device': device_cpu,
    'fallback': fallback_generator
}
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 Generator — a Generator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Generator 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
load_json Ran
ran; our contract draft was wrong, not the code
kkahatapitiya/langrepo/util.py
code served (permissive licence) · get_code("658682feda4928a2")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with test data
temp_dir = tempfile.mkdtemp()
test_file = os.path.join(temp_dir, 'test_data.json')

test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(test_file, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    'fn': test_file
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
load_pkl Ran
ran; our contract draft was wrong, not the code
kkahatapitiya/langrepo/util.py
code served (permissive licence) · get_code("8080055de6293a6b")
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 dict. 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 pickle
import tempfile
import os

# Create a temporary pickle file with some test data
test_data = {
    'key1': 'value1',
    'key2': [1, 2, 3],
    'key3': {'nested': 'dict'}
}

# Create a temporary file
temp_dir = tempfile.gettempdir()
temp_file = os.path.join(temp_dir, 'test_data.pkl')

# Write the pickle file
with open(temp_file, 'wb') as f:
    pickle.dump(test_data, f)

# Define arguments for load_pkl
ARGS = {
    'fn': temp_file
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
mps_gather_workaround Ran
ran; our contract draft was wrong, not the code
kkahatapitiya/langrepo/merge.py
code served (permissive licence) · get_code("16eb26a585c085e1")
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 3, dtype family float, shape (2, 3, 1) 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)

# Create test tensors for the function
# input: tensor to gather from
# dim: dimension along which to gather
# index: indices to gather

# Case 1: input with shape[-1] == 1 (the workaround case)
input_tensor = torch.randn(2, 4, 1)
dim = 1
index = torch.randint(0, 4, (2, 3, 1))

ARGS = {
    "input": input_tensor,
    "dim": dim,
    "index": index
}
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 3, dtype family float, shape (2, 3, 1) — shape (2, 3, 1) 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 9 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 9 later) and 0 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
do_nothing 7 other papers
3 dated earlier, 4 later · 2 only as an assembly brick
2210.09461 (2022-10)
Token Merging: Your ViT But Faster
2303.17604 (2023-03)
Token Merging for Fast Stable Diffusion
2312.10656 (2023-12)
VidToMe: Video Token Merging for Zero-Shot Video Editing
and 4 more not named here
mps_gather_workaround 7 other papers
3 dated earlier, 4 later · 2 only as an assembly brick
2210.09461 (2022-10)
Token Merging: Your ViT But Faster
2303.17604 (2023-03)
Token Merging for Fast Stable Diffusion
2312.10656 (2023-12)
VidToMe: Video Token Merging for Zero-Shot Video Editing
and 4 more not named here
identity 5 other papers
1 dated earlier, 3 later, 1 same year, order not determinable
2312.17235 (2023-12)
A Simple LLM Framework for Long-Range Video Question-Answering
2024.emnlp-main.1209 (2024 (year only))
A Simple LLM Framework for Long-Range Video Question-Answering
2405.19209 (2024-05)
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
and 2 more not named here
load_json 5 other papers
1 dated earlier, 3 later, 1 same year, order not determinable
2312.17235 (2023-12)
A Simple LLM Framework for Long-Range Video Question-Answering
2024.emnlp-main.1209 (2024 (year only))
A Simple LLM Framework for Long-Range Video Question-Answering
2405.19209 (2024-05)
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
and 2 more not named here
load_pkl 5 other papers
1 dated earlier, 3 later, 1 same year, order not determinable
2312.17235 (2023-12)
A Simple LLM Framework for Long-Range Video Question-Answering
2024.emnlp-main.1209 (2024 (year only))
A Simple LLM Framework for Long-Range Video Question-Answering
2405.19209 (2024-05)
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
and 2 more not named here
init_generator 4 other papers
2 dated earlier, 2 later
2303.17604 (2023-03)
Token Merging for Fast Stable Diffusion
2312.10656 (2023-12)
VidToMe: Video Token Merging for Zero-Shot Video Editing
2025.findings-acl.294 (2025 (year only))
Language Repository for Long Video Understanding
and 1 more not named here
clean_text 1 other paper
1 later
2025.findings-acl.294 (2025 (year only))
Language Repository for Long Video Understanding
first_char_after_anchor 1 other paper
1 later
2025.findings-acl.294 (2025 (year only))
Language Repository for Long Video Understanding
first_char_as_answer 1 other paper
1 later
2025.findings-acl.294 (2025 (year only))
Language Repository for Long Video Understanding

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

Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical, especially in applications such as long-form video understanding. In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., all-textual) representation. Our repository is updated iteratively based on multi-scale video chunks. We introduce write and read operations that focus on pruning redundancies in text, and extracting information at various temporal scales. The proposed framework is evaluated on zero-shot visual question-answering benchmarks including EgoSchema, NExT-QA, IntentQA and NExT-GQA, showing state-of-the-art performance at its scale. Our code is available at https://github.com/kkahatapitiya/LangRepo.

For agents

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

get_harvested_code_for_paper("2403.14622")
get_code_for_paper("2403.14622")
have("2403.14622")

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

curl https://syntology.ai/api/ran/2403.14622.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.14622.svg)](https://syntology.ai/paper/2403.14622)

Connect an agent — have() is free.