SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.00381 · 2026

Modeling Image-Caption Rating from Comparative Judgments

Qiang Zhang, Zhe Yu, Kezia Minni, Mahbub Khan

arXiv · PDF · Open in the Atlas

Code that ran

12 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; 10 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2602.00381.json · badge: /api/ran/2602.00381.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
hil-se/comparative_image_caption canonical (classifier label)
classifier basis: census
12 ran · 1 no recorded run
FunctionStatusWhere it lives
acc_kappa Ran
ran, honoured the contract we drafted
hil-se/comparative_image_caption/code/comparative_agreement.py
pointer only (licence: NONE) · get_code("908600128fb982fd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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.

build_model Ran
ran; our contract draft was wrong, not the code
hil-se/comparative_image_caption/src/compare.py
pointer only (licence: NONE) · get_code("218ea173a82c8673")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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.

build_model Ran
ran; our contract draft was wrong, not the code
hil-se/comparative_image_caption/src/regression.py
pointer only (licence: NONE) · get_code("5a6f66fcafdca8ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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.

create_encoder Ran
ran; our contract draft was wrong, not the code
hil-se/comparative_image_caption/src/compare_same_image.py
pointer only (licence: NONE) · get_code("2144a71f14fd2cc0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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.

generate_pairs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hil-se/comparative_image_caption/code/comparative_agreement.py
pointer only (licence: NONE) · get_code("9cd7d4712d2b83c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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.

generate_pairs_from_choices Ran
ran; our contract draft was wrong, not the code
hil-se/comparative_image_caption/code/comparative_interrater_agreement.py
pointer only (licence: NONE) · get_code("0d5e72e05773253a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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.

make_gt_choice_from_scores Ran
ran; our contract draft was wrong, not the code
hil-se/comparative_image_caption/code/comparative_interrater_agreement.py
pointer only (licence: NONE) · get_code("7cc2a89596402032")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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_float_list Ran
ran; our contract draft was wrong, not the code
hil-se/comparative_image_caption/src/embeddings_serialize.py
pointer only (licence: NONE) · get_code("75c1d01886e70451")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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_np_array Ran
ran; our contract draft was wrong, not the code
hil-se/comparative_image_caption/src/embeddings_serialize.py
pointer only (licence: NONE) · get_code("e325963bc7d461c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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_string Ran
ran; our contract draft was wrong, not the code
hil-se/comparative_image_caption/src/embeddings_serialize.py
pointer only (licence: NONE) · get_code("fcfac834009eb852")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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.

summarize_agreement Ran
ran; our contract draft was wrong, not the code
hil-se/comparative_image_caption/code/compute_averages.py
pointer only (licence: NONE) · get_code("37a781d3bb276bc7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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.

to_dir Ran
ran, honoured the contract we drafted
hil-se/comparative_image_caption/code/comparative_interrater_agreement.py
pointer only (licence: NONE) · get_code("3c78fecc2efc84c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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.

create_pairwise_data Not yet run
unverified (harvested, no recorded run)
hil-se/comparative_image_caption/src/compare.py
pointer only (licence: NONE) · get_code("ddfefac384cee41a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hil-se/comparative_image_caption 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, 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 13 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

Image caption rating is becoming increasingly important because computer-generated captions are used extensively for descriptive annotation. However, rating the accuracy of captions in describing images is time-consuming and subjective in nature. In contrast, it is often easier for people to compare (between two pairs) which image-caption pair better matches each other. In this study, we propose a machine learning framework that models such comparative judgments instead of direct ratings. The model can then be applied to rank unseen image-caption pairs in the same way as a regression model trained on direct ratings. Inspired by a state-of-the-art regression approach, we extracted visual and text features using a pre-trained ViLBERT model and tweaked the learning parameters of the baseline model to improve the model performance. This new regression model (with Kendall's 𝜏 𝑐 = 0.812) outperformed the baseline model (with Kendall's 𝜏 𝑐 = 0.758) on the VICR dataset. The same model structure was applied to the comparative learning framework. Trained on comparative judgments (image-caption pair A better matches each other than image-caption pair B), the comparative learning model achieved a performance similar (with Kendall's 𝜏 𝑐 = 0.804) to that of the regression model. In addition, a small-scale human subject study was conducted to compare the cost and quality of direct ratings, pairwise comparisons, and same-image comparisons. The results showed that comparative judgments yielded faster results and greater agreement among human annotators than direct ratings. These results suggest that collecting comparative judgments instead of direct ratings as training data labels is promising for lower annotation costs and greater consistency. The model trained on such comparative judgments can perform as well as the model trained on direct ratings.

For agents

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

get_harvested_code_for_paper("2602.00381")
get_code_for_paper("2602.00381")
have("2602.00381")

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

curl https://syntology.ai/api/ran/2602.00381.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.00381.svg)](https://syntology.ai/paper/2602.00381)

Connect an agent — have() is free.