SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.18091 · CVPR · 2024

Polos: Multimodal Metric Learning from Human Feedback for Image Captioning

Komei Sugiura, Yuiga Wada, Kanta Kaneda, Daichi Saito

arXiv · PDF · Open in the Atlas

Code that ran

8 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 0 have no contract verdict; 8 failures of our instrument; 1 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/2402.18091.json · badge: /api/ran/2402.18091.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
keio-smilab24/Polos canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
average_pooling Ran
ran; our contract draft was wrong, not the code
keio-smilab24/Polos/polos/models/utils.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("bc589f40704cf78a")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, keio-smilab24/Polos, is not in the permissive set Syntology serves inline. 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.

basic_clean Ran
ran; our contract draft was wrong, not the code
keio-smilab24/Polos/polos/simple_tokenizer.py
pointer only (licence: BSD-3-Clause-Clear); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("98f385d847636a3e")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, keio-smilab24/Polos, is not in the permissive set Syntology serves inline. 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.

build_activation Ran
ran; our contract draft was wrong, not the code
keio-smilab24/Polos/polos/modules/activations.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("b0b39e3b4affdd63")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, keio-smilab24/Polos, is not in the permissive set Syntology serves inline. 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_pairs Ran
ran; our contract draft was wrong, not the code
keio-smilab24/Polos/polos/simple_tokenizer.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("d919ae32e5e4e616")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, keio-smilab24/Polos, is not in the permissive set Syntology serves inline. 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.

mask_fill Ran
ran; our contract draft was wrong, not the code
keio-smilab24/Polos/polos/models/utils.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("490410c5af6ef847")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, keio-smilab24/Polos, is not in the permissive set Syntology serves inline. 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.

max_pooling Ran
ran; our contract draft was wrong, not the code
keio-smilab24/Polos/polos/models/utils.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("b211e3cd0942a18f")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, keio-smilab24/Polos, is not in the permissive set Syntology serves inline. 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.

swish Ran
ran; our contract draft was wrong, not the code
keio-smilab24/Polos/polos/modules/activations.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("48d39f3e15bed9c4")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, keio-smilab24/Polos, is not in the permissive set Syntology serves inline. 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.

whitespace_clean Ran
ran; our contract draft was wrong, not the code
keio-smilab24/Polos/polos/simple_tokenizer.py
pointer only (licence: BSD-3-Clause-Clear); the stored copy get_code serves, from ltpwy/MSCI, is pointer only (licence: NONE) · get_code("9542161e9640b858")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, keio-smilab24/Polos, is not in the permissive set Syntology serves inline. 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.

build_model Not yet run
unverified (harvested, no recorded run)
keio-smilab24/Polos/polos/model.py
pointer only (licence: BSD-3-Clause-Clear) · get_code("39e6b23b55f376ea")
How it ran

The body of this sample is withheld: BSD-3-Clause-Clear, as GitHub detects it on this paper's repository, keio-smilab24/Polos, is not in the permissive set Syntology serves inline. 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 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 (9 with at least one paper dated earlier, 7 the same month, 5 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
get_pairs 258 other papers
112 dated earlier, 3 the same month, 135 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1803.01128 (2018-03)
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
1809.00125 (2018-09)
Simple Fusion: Return of the Language Model
and 255 more not named here
whitespace_clean 231 other papers
94 dated earlier, 3 the same month, 126 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 228 more not named here
basic_clean 218 other papers
94 dated earlier, 3 the same month, 113 later, 7 same year, order not determinable, 1 undated · 4 only as an assembly brick
1901.07441 (2019-01)
PadChest: A large chest x-ray image dataset with multi-label annotated reports
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2108.10904 (2021-08)
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
and 215 more not named here
build_model 53 other papers
17 dated earlier, 1 the same month, 33 later, 2 same year, order not determinable
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2210.01115 (2022-10)
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
2211.09552 (2022-11)
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
and 50 more not named here
max_pooling 5 other papers
3 dated earlier, 1 the same month, 1 later
2005.00547 (2020-05)
GoEmotions: A Dataset of Fine-Grained Emotions
2109.06352 (2021-09)
Uncertainty-Aware Machine Translation Evaluation
2023.acl-long.47 (2023 (year only))
Test-time Adaptation for Machine Translation Evaluation by Uncertainty Minimization
and 2 more not named here
average_pooling 4 other papers
3 dated earlier, 1 the same month
2005.00547 (2020-05)
GoEmotions: A Dataset of Fine-Grained Emotions
2109.06352 (2021-09)
Uncertainty-Aware Machine Translation Evaluation
2023.acl-long.47 (2023 (year only))
Test-time Adaptation for Machine Translation Evaluation by Uncertainty Minimization
and 1 more not named here
mask_fill 3 other papers
2 dated earlier, 1 the same month
2109.06352 (2021-09)
Uncertainty-Aware Machine Translation Evaluation
2023.acl-long.47 (2023 (year only))
Test-time Adaptation for Machine Translation Evaluation by Uncertainty Minimization
2402.18191 (2024-02)
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
build_activation 1 other paper
1 dated earlier
2109.06352 (2021-09)
Uncertainty-Aware Machine Translation Evaluation
swish 1 other paper
1 dated earlier
2109.06352 (2021-09)
Uncertainty-Aware Machine Translation Evaluation

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

Establishing an automatic evaluation metric that closely aligns with human judgments is essential for effectively developing image captioning models. Recent data-driven metrics have demonstrated a stronger correlation with human judgments than classic metrics such as CIDEr; however they lack sufficient capabilities to handle hallucinations and generalize across diverse images and texts partially because they compute scalar similarities merely using embeddings learned from tasks unrelated to image captioning evaluation. In this study, we propose Polos, a supervised automatic evaluation metric for image captioning models. Polos computes scores from multimodal inputs, using a parallel feature extraction mechanism that leverages embeddings trained through large-scale contrastive learning. To train Polos, we introduce Multimodal Metric Learning from Human Feedback (M 2 LHF), a framework for developing metrics based on human feedback. We constructed the Polaris dataset, which comprises 131K human judgments from 550 evaluators, which is approximately ten times larger than standard datasets. Our approach achieved state-of-theart performance on Composite, Flickr8K-Expert, Flickr8K-CF, PASCAL-50S, FOIL, and the Polaris dataset, thereby demonstrating its effectiveness and robustness.

For agents

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

get_harvested_code_for_paper("2402.18091")
get_code_for_paper("2402.18091")
have("2402.18091")

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

curl https://syntology.ai/api/ran/2402.18091.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.18091.svg)](https://syntology.ai/paper/2402.18091)

Connect an agent — have() is free.