SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.15867 · NeurIPS · 2024

In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understanding

Janusz Marecki, Ammar Anwar, Moucheng Xu, Evangelos Chatzaroulas, Luc Mccutcheon, Abdul Ahad, Hamzah Azeem

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 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/2409.15867.json · badge: /api/ran/2409.15867.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
moucheng2017/action-labelling canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
load_config Ran
ran; our contract draft was wrong, not the code
moucheng2017/action-labelling/helpers.py
pointer only (licence: NONE) · get_code("5bd665029e0d3d9a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moucheng2017/action-labelling 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.

openai_completion Ran
ran; our contract draft was wrong, not the code
moucheng2017/action-labelling/ensembles/ensemble_gpt.py
pointer only (licence: NONE) · get_code("19ec64c922043398")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moucheng2017/action-labelling 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.

preprocess_pseudo_labels Ran
ran; our contract draft was wrong, not the code
moucheng2017/action-labelling/ensembles/ensemble_gemini.py
pointer only (licence: NONE) · get_code("79dca242f8e21c99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moucheng2017/action-labelling 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.

read_paths_from_txt Ran
ran; our contract draft was wrong, not the code
moucheng2017/action-labelling/helpers.py
pointer only (licence: NONE) · get_code("946712bf4fabe874")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moucheng2017/action-labelling 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.

sort_key Ran
ran, honoured the contract we drafted
moucheng2017/action-labelling/helpers.py
pointer only (licence: NONE) · get_code("ee3a0742a3013971")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, moucheng2017/action-labelling 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.

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, 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 5 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

A Standard Operating Procedure (SOP) defines a low-level, step-by-step written guide for a business software workflow. SOP generation is a crucial step towards automating end-to-end software workflows. Manually creating SOPs can be time-consuming. Recent advancements in large videolanguage models offer the potential for automating SOP generation by analyzing recordings of human demonstrations. However, current large video-language models face challenges with zero-shot SOP generation. In this work, we first explore in-context learning with video-language models for SOP generation. We then propose an exploration-focused strategy called In-Context Ensemble Learning, to aggregate pseudo labels of multiple possible paths of SOPs. The proposed in-context ensemble learning as well enables the models to learn beyond its context window limit with an implicit consistency regularisation. We report that in-context learning helps video-language models to generate more temporally accurate SOP, and the proposed in-context ensemble learning can consistently enhance the capabilities of the video-language models in SOP generation.

For agents

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

get_harvested_code_for_paper("2409.15867")
get_code_for_paper("2409.15867")
have("2409.15867")

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

curl https://syntology.ai/api/ran/2409.15867.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.15867.svg)](https://syntology.ai/paper/2409.15867)

Connect an agent — have() is free.