SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.17443 · 2024

HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 6 failures of our instrument; 2 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/2408.17443.json · badge: /api/ran/2408.17443.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
joslefaure/HERMES canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
calculate_scores Ran
ran; our contract draft was wrong, not the code
joslefaure/HERMES/lavis/tasks/moviecore_eval.py
code served (permissive licence) · get_code("6e0b77da286c6cb3")
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 torch

# Construct valid arguments for calculate_scores function
results_list = [
    {
        'classification': 'category_A, category_B',
        'results': {
            'accuracy': {'score': 0.85},
            'comprehensiveness': {'score': 0.90},
            'depth': {'score': 0.75},
            'evidence': {'score': 0.88},
            'coherence': {'score': 0.92}
        }
    },
    {
        'classification': 'category_A',
        'results': {
            'accuracy': {'score': 0.80},
            'comprehensiveness': {'score': 0.85},
            'depth': {'score': 0.70},
            'evidence': {'score': 0.82},
            'coherence': {'score': 0.87}
        }
    },
    {
        'classification': 'category_B',
        'results': {
            'accuracy': {'score': 0.92},
            'comprehensiveness': {'score': 0.95},
            'depth': {'score': 0.88},
            'evidence': {'score': 0.91},
            'coherence': {'score': 0.96}
        }
    },
    {
        'classification': 'category_C',
        'results': {
            'accuracy': {'score': 0.78},
            'comprehensiveness': {'score': 0.80},
            'depth': {'score': 0.72},
            'evidence': {'score': 0.76},
            'coherence': {'score': 0.81}
        }
    },
    None,
    {},
]

ARGS = {
    'results_list': results_list
}
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 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
download_cached_file Ran
ran on a synthesized input
joslefaure/HERMES/lavis/common/dist_utils.py
code served (permissive licence) · get_code("aee911f7b46c600a")
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 os

torch.manual_seed(0)

# Mock timm_hub.get_cache_dir() to return a temporary directory
import timm.models.hub as timm_hub
original_get_cache_dir = timm_hub.get_cache_dir

def mock_get_cache_dir():
    return "/tmp/timm_cache"

timm_hub.get_cache_dir = mock_get_cache_dir

# Mock timm_hub.download_cached_file to avoid actual downloads
original_download_cached_file = timm_hub.download_cached_file

def mock_download_cached_file(url, check_hash=True, progress=False):
    pass

timm_hub.download_cached_file = mock_download_cached_file

# Define ARGS for the download_cached_file function
ARGS = {
    "url": "https://example.com/model.pth",
    "check_hash": True,
    "progress": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, 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
getAttMap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
joslefaure/HERMES/lavis/common/gradcam.py
code served (permissive licence) · get_code("7d214655954e2bc6")
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 3, dtype family float, shape (4, 3, 3) 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
from matplotlib import pyplot as plt
from scipy.ndimage import filters
from skimage import transform as skimage_transform

# Create a small RGB image (height=4, width=3, channels=3)
img = np.random.rand(4, 3, 3).astype(np.float32)

# Create an attention map (height=2, width=2) - smaller than img
attMap = np.random.rand(2, 2).astype(np.float32)

ARGS = {
    'img': img,
    'attMap': attMap,
    'blur': True,
    'overlap': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, scipy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (4, 3, 3) — shape (4, 3, 3) 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
interpolate_pos_embed Ran
ran; our contract draft was wrong, not the code
joslefaure/HERMES/lavis/models/vit.py
code served (permissive licence) · get_code("c6ec173f19f5c34d")
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 3, dtype family float, shape (1, 17, 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

torch.manual_seed(0)

class PatchEmbed(nn.Module):
    def __init__(self, num_patches):
        super().__init__()
        self.num_patches = num_patches

class VisualEncoder(nn.Module):
    def __init__(self, num_patches, pos_embed_shape):
        super().__init__()
        self.patch_embed = PatchEmbed(num_patches)
        self.pos_embed = torch.randn(pos_embed_shape)

# Create a visual encoder with 16 patches (4x4 grid)
# pos_embed shape: (1, num_patches + num_extra_tokens, embedding_dim)
num_patches = 16
num_extra_tokens = 1
embedding_size = 4
visual_encoder = VisualEncoder(
    num_patches=num_patches,
    pos_embed_shape=(1, num_patches + num_extra_tokens, embedding_size)
)

# Create pos_embed_checkpoint with original size 2x2 (4 patches) + 1 extra token
# This will trigger interpolation from 2x2 to 4x4
orig_size = 2
orig_num_patches = orig_size * orig_size
pos_embed_checkpoint = torch.randn(1, orig_num_patches + num_extra_tokens, embedding_size)

ARGS = {
    "pos_embed_checkpoint": pos_embed_checkpoint,
    "visual_encoder": visual_encoder,
}
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 3, dtype family float, shape (1, 17, 4) — shape (1, 17, 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
main_process Ran
ran; our contract draft was wrong, not the code
joslefaure/HERMES/lavis/common/dist_utils.py
code served (permissive licence) · get_code("98589643273920ba")
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
import torch.nn as nn
import functools

torch.manual_seed(0)

def get_dist_info():
    import torch.distributed as dist
    if torch.__version__ < '1.0':
        initialized = dist._initialized
    else:
        initialized = dist.is_initialized()
    if initialized:
        rank = dist.get_rank()
        world_size = dist.get_world_size()
    else:
        rank = 0
        world_size = 1
    return (rank, world_size)

def main_process(func):
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        rank, _ = get_dist_info()
        if rank == 0:
            return func(*args, **kwargs)
    return wrapper

# Create a simple test function to decorate
def sample_function(x, y):
    return x + y

# Apply the decorator
decorated_func = main_process(sample_function)

# The main_process function takes a single parameter: func (a callable)
ARGS = {
    'func': sample_function
}
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
node_to_dict Ran
ran; our contract draft was wrong, not the code
joslefaure/HERMES/lavis/common/config.py
code served (permissive licence) · get_code("791c72070c0b1cfb")
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.

from omegaconf import OmegaConf

# Create a simple OmegaConf node to pass to node_to_dict
# The function converts an OmegaConf node to a regular Python container
node = OmegaConf.create({
    "model": {
        "name": "test_model",
        "layers": 3,
        "hidden_dim": 128
    },
    "training": {
        "lr": 0.001,
        "epochs": 100,
        "batch_size": 32
    },
    "data": ["sample1", "sample2", "sample3"]
})

ARGS = {
    "node": node
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
omegaconf — 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
tile Ran
ran; our contract draft was wrong, not the code
joslefaure/HERMES/lavis/models/base_model.py
pointer only (licence: MIT); the stored copy get_code serves, from MengzhouLu/RetroMPA, is pointer only (licence: NONE) · get_code("cb33571427334815")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from MengzhouLu/RetroMPA, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

all_gather_with_grad Not yet run
unverified (harvested, no recorded run)
joslefaure/HERMES/lavis/models/base_model.py
code served (permissive licence) · get_code("0ec9fc2025c16f65")
How it ran

no invocation recorded.

get_prompt Not yet run
unverified (harvested, no recorded run)
joslefaure/HERMES/lavis/tasks/moviecore_eval_prompts.py
code served (permissive licence) · get_code("50228589040ec9ac")
How it ran

no invocation recorded.

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, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 5 the same month, 7 later) and 2 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
all_gather_with_grad 91 other papers
68 dated earlier, 2 the same month, 17 later, 4 same year, order not determinable · 2 only as an assembly brick
2206.02967 (2022-06)
Masked Unsupervised Self-training for Label-free Image Classification
2210.08773 (2022-10)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
2302.06605 (2023-02)
UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
and 88 more not named here
tile 84 other papers
66 dated earlier, 1 the same month, 12 later, 5 same year, order not determinable
2206.07699 (2022-06)
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
2210.07795 (2022-10)
EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
2210.08773 (2022-10)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
and 81 more not named here
interpolate_pos_embed 52 other papers
42 dated earlier, 8 later, 2 same year, order not determinable
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
2111.09452 (2021-11)
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
2205.11169 (2022-05)
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
and 49 more not named here
node_to_dict 39 other papers
30 dated earlier, 1 the same month, 6 later, 2 same year, order not determinable
2305.04160 (2023-05)
X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
2305.14167 (2023-05)
DetGPT: Detect What You Need via Reasoning
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
and 36 more not named here
download_cached_file 37 other papers
29 dated earlier, 1 the same month, 5 later, 2 same year, order not determinable
2305.04160 (2023-05)
X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
2305.14167 (2023-05)
DetGPT: Detect What You Need via Reasoning
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
and 34 more not named here
main_process 35 other papers
27 dated earlier, 1 the same month, 5 later, 2 same year, order not determinable
2305.04160 (2023-05)
X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
2305.14167 (2023-05)
DetGPT: Detect What You Need via Reasoning
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
and 32 more not named here
getAttMap 28 other papers
22 dated earlier, 4 later, 2 same year, order not determinable
2305.04160 (2023-05)
X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
2305.07558 (2023-05)
Measuring Progress in Fine-grained Vision-and-Language Understanding
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
and 25 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Long-form video understanding presents unique challenges that extend beyond traditional short-video analysis approaches, particularly in capturing long-range dependencies, processing redundant information efficiently, and extracting high-level semantic concepts. To address these challenges, we propose a novel approach that more accurately reflects human cognition. This paper introduces HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics, featuring two versatile modules that can enhance existing video-language models or operate as a standalone system. Our Episodic COmpressor (ECO) efficiently aggregates representations from micro to semi-macro levels, reducing computational overhead while preserving temporal dependencies. Our Semantics ReTRiever (SeTR) enriches these representations with semantic information by focusing on broader context, dramatically reducing feature dimensionality while preserving relevant macro-level information. We demonstrate that these modules can be seamlessly integrated into existing SOTA models, consistently improving their performance while reducing inference latency by up to 43% and memory usage by 46%. As a standalone system, HERMES achieves state-of-the-art performance across multiple long-video understanding benchmarks in both zero-shot and fully-supervised settings.

For agents

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

get_harvested_code_for_paper("2408.17443")
get_code_for_paper("2408.17443")
have("2408.17443")

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

curl https://syntology.ai/api/ran/2408.17443.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.17443.svg)](https://syntology.ai/paper/2408.17443)

Connect an agent — have() is free.