SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.02249 · 2023

Recursive Visual Programming

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2312.02249.json · badge: /api/ran/2312.02249.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
para-lost/rvp canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
FunctionStatusWhere it lives
whitespace_tokenize Ran
ran; our contract draft was wrong, not the code
para-lost/rvp/base_models/tcl/tcl_tokenization_bert.py
pointer only (licence: NONE) · get_code("cf9ffa02a42184af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, para-lost/rvp 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.

bool_to_yesno Ran
ran; our contract draft was wrong, not the code
para-lost/rvp/image_patch.py
pointer only (licence: NOASSERTION) · get_code("38e334384d86aaa1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, para-lost/rvp (NOASSERTION). 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.

collate Ran
ran; our contract draft was wrong, not the code
para-lost/rvp/vision_processes.py
pointer only (licence: NOASSERTION) · get_code("b54134f48b26b8b8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, para-lost/rvp (NOASSERTION). 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.

denormalize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
para-lost/rvp/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from sachit-menon/generating-illustrated-instructions-reproduction, is pointer only (licence: NONE) · get_code("191a0905a11888a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, para-lost/rvp 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.

draw_bounding_boxes Ran
ran; our contract draft was wrong, not the code
para-lost/rvp/utils.py
pointer only (licence: NOASSERTION) · get_code("44efca8c80c8d48f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, para-lost/rvp (NOASSERTION). 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.

extract_start_index Ran
ran, honoured the contract we drafted
para-lost/rvp/main_batch.py
pointer only (licence: NOASSERTION) · get_code("7cc4a60389346b00")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, para-lost/rvp (NOASSERTION). 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.

get_index_from_sample_id Ran
ran, honoured the contract we drafted
para-lost/rvp/utils.py
pointer only (licence: NOASSERTION) · get_code("ef08d7159362c3db")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, para-lost/rvp (NOASSERTION). 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.

get_transform Ran
ran; our contract draft was wrong, not the code
para-lost/rvp/base_models/inspyrenet/saliency_transforms.py
pointer only (licence: NOASSERTION) · get_code("bc2728b9cedba3e5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, para-lost/rvp (NOASSERTION). 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.

interpolate_pos_embed Ran
ran; our contract draft was wrong, not the code
para-lost/rvp/base_models/tcl/tcl_vit.py
pointer only (licence: NOASSERTION) · get_code("4262ed39e3ce5c97")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, para-lost/rvp (NOASSERTION). 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.

load_vocab Ran
ran; our contract draft was wrong, not the code
para-lost/rvp/base_models/tcl/tcl_tokenization_bert.py
pointer only (licence: NONE) · get_code("e7fbc7a74a3457c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, para-lost/rvp 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.

my_collate Ran
ran; our contract draft was wrong, not the code
para-lost/rvp/main_batch.py
pointer only (licence: NONE); the stored copy get_code serves, from cvlab-columbia/viper, is pointer only (licence: NOASSERTION) · get_code("18839b05574cb883")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, para-lost/rvp 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.

concat_all_gather Not yet run
unverified (harvested, no recorded run)
para-lost/rvp/base_models/tcl/tcl_model_pretrain.py
pointer only (licence: NONE) · get_code("73cecca9f3575f09")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, para-lost/rvp 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. No invocation recorded.

load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
para-lost/rvp/base_models/tcl/tcl_xbert.py
pointer only (licence: NONE) · get_code("26be70dca3249c0b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, para-lost/rvp 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. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 4 the same month, 4 later) and 7 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
concat_all_gather 138 other papers
96 dated earlier, 4 the same month, 37 later, 1 same year, order not determinable · 33 only as an assembly brick
1710.09412 (2017-10)
mixup: BEYOND EMPIRICAL RISK MINIMIZATION
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 135 more not named here
whitespace_tokenize 43 other papers
33 dated earlier, 1 the same month, 9 later
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.01698 (2019-06)
Open Sesame: Getting Inside BERT's Linguistic Knowledge
and 40 more not named here
load_vocab 29 other papers
20 dated earlier, 1 the same month, 8 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
and 26 more not named here
load_tf_weights_in_bert 28 other papers
19 dated earlier, 8 later, 1 same year, order not determinable
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
2021.emnlp-main.154 (2021 (year only))
Reconstruction Attack on Instance Encoding for Language Understanding
2104.06599 (2021-04)
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
and 25 more not named here
denormalize 1 other paper
1 the same month
2312.04552 (2023-12)
Generating Illustrated Instructions
my_collate 1 other paper
1 dated earlier
2311.06411 (2023-11)
Analyzing Modular Approaches for Visual Question Decomposition

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

Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities, especially in few-shot and zero-shot scenarios. However, existing VP methods generate all code in a single function, resulting in code that is suboptimal in terms of both accuracy and interpretability. Inspired by human coding practices, we propose Recursive Visual Programming (RVP), which simplifies generated routines, provides more efficient problem solving, and can manage more complex data structures. RVP is inspired by human coding practices and approaches VQA tasks with an iterative recursive code generation approach, allowing decomposition of complicated problems into smaller parts. Notably, RVP is capable of dynamic type assignment, i.e., as the system recursively generates a new piece of code, it autonomously determines the appropriate return type and crafts the requisite code to generate that output. We show RVP's efficacy through extensive experiments on benchmarks including VSR, COVR, GQA, and NextQA, underscoring the value of adopting human-like recursive and modular programming techniques for solving VQA tasks through coding.

For agents

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

get_harvested_code_for_paper("2312.02249")
get_code_for_paper("2312.02249")
have("2312.02249")

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

curl https://syntology.ai/api/ran/2312.02249.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.02249.svg)](https://syntology.ai/paper/2312.02249)

Connect an agent — have() is free.