SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.04014 · EMNLP · 2021

Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering

Chitta Baral, Man Luo, Pratyay Banerjee, Yankai Zeng

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 2 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2109.04014.json · badge: /api/ran/2109.04014.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
luomancs/retriever_reader_for_okvqa marked official in Papers with Code
Papers with Code archive
2 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Reader Ran
ran on a synthesized input · constructed an object; no result was computed
luomancs/retriever_reader_for_okvqa/DPR/dpr/model_lxmert/reader.py
code served (permissive licence) · get_code("30c98cb903350faa")
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 an instance of its own class, Reader: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

class DummyEncoder(nn.Module):
    def __init__(self, hidden_size, seq_length):
        super(DummyEncoder, self).__init__()
        self.hidden_size = hidden_size
        self.seq_length = seq_length
        self.linear = nn.Linear(hidden_size, hidden_size)
    
    def forward(self, input_ids, token_type_ids, attention_mask):
        batch_size = input_ids.size(0)
        # Return (sequence_output, pooled_output, hidden_states)
        sequence_output = torch.randn(batch_size, self.seq_length, self.hidden_size)
        pooled_output = torch.randn(batch_size, self.hidden_size)
        hidden_states = torch.randn(batch_size, self.seq_length, self.hidden_size)
        return sequence_output, pooled_output, hidden_states

hidden_size = 4
seq_length = 3
encoder = DummyEncoder(hidden_size, seq_length)

ARGS = {
    'encoder': encoder,
    'hidden_size': hidden_size
}
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 Reader — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Reader 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
_calc_mml Ran
ran; our contract draft was wrong, not the code
luomancs/retriever_reader_for_okvqa/DPR/dpr/model_lxmert/reader.py
code served (permissive licence) · get_code("fcb2544f4ef7c452")
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 0, dtype family float; no output shape is stated. 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 and ndim 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 a loss_tensor with shape (batch_size, num_losses)
# The function expects a 2D tensor where:
# - dim 0 is batch size
# - dim 1 contains loss values
# We use batch_size=2 and num_losses=4 to keep it tiny and distinct

loss_tensor = torch.randn(2, 4)

# Ensure some non-zero values and potentially a zero value to test the masking
loss_tensor[0, 0] = 0.5
loss_tensor[0, 1] = 1.2
loss_tensor[1, 0] = 0.0  # This will be masked out by the (loss_tensor == 0) condition
loss_tensor[1, 1] = 2.3

ARGS = {
    "loss_tensor": loss_tensor
}
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 0, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
compute_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from microsoft/AR2
pointer only · get_code("1df81ea9d2da7b70")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

init_weights Not yet run
unverified (harvested, no recorded run)
luomancs/retriever_reader_for_okvqa/DPR/dpr/model_lxmert/reader.py
code served (permissive licence) · get_code("62e3d8ee4f0d3ff3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
compute_loss
brick of this paper's assembly: loss
5 other papers
5 later
2110.03611 (2021-10)
Adversarial Retriever-Ranker for dense text retrieval
2205.09843 (2022-05)
Table Retrieval May Not Necessitate Table-specific Model Design
2024.findings-acl.708 (2024 (year only))
Analyze, Generate and Refine: Query Expansion with LLMs for Zero-Shot Open-Domain QA
and 2 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 2026-11-21.

Repositories linked to this paper

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

Abstract

Knowledge-based visual question answering (VQA) requires answering questions with external knowledge in addition to the content of images. One dataset that is mostly used in evaluating knowledge-based VQA is OK-VQA, but it lacks a gold standard knowledge corpus for retrieval. Existing work leverage different knowledge bases (e.g., ConceptNet and Wikipedia) to obtain external knowledge. Because of varying knowledge bases, it is hard to fairly compare models' performance. To address this issue, we collect a natural language knowledge base that can be used for any VQA system. Moreover, we propose a Visual Retriever-Reader pipeline to approach knowledge-based VQA. The visual retriever aims to retrieve relevant knowledge, and the visual reader seeks to predict answers based on given knowledge. We introduce various ways to retrieve knowledge using text and images and two reader styles: classification and extraction. Both the retriever and reader are trained with weak supervision. Our experimental results show that a good retriever can significantly improve the reader's performance on the OK-VQA challenge. The code and corpus are provided in this link. Question: What sort of vehicle used this item? Answer: fire truck LXMERT: truck LXMERT + Caption: fire truck Ours: fire truck kn: fire engine, also called fire truck, mobile (nowadays selfpropelled) piece of equipment used in firefighting.... Caption: a red fire hydrant sitting on the side of a road. Question: Where did this sport originate? Answer: australia, hawaii, polynesian LXMERT: california LXMERT + Caption: california Ours: hawaii kn: surfing was invented in hawaii... Caption: a man riding a wave on a surfboard in the ocean.

For agents

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

get_harvested_code_for_paper("2109.04014")
get_code_for_paper("2109.04014")
have("2109.04014")

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

curl https://syntology.ai/api/ran/2109.04014.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.04014.svg)](https://syntology.ai/paper/2109.04014)

Connect an agent — have() is free.