SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.01613 · 2026

CAP-IQA: Context-Aware Prompt-Guided CT Image Quality Assessment

Jie Zhang, Ramisa Kazi, Rifa, Abdullah Imran

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 (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 0 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/2601.01613.json · badge: /api/ran/2601.01613.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
KaziRamisaRifa/capiqa community
Papers with Code archive
5 ran · 0 no recorded run
FunctionStatusWhere it lives
CPA Ran
ran on a synthesized input · constructed an object; no result was computed
KaziRamisaRifa/capiqa/model.py
code served (permissive licence) · get_code("2f39d48b5eba1398")
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, CPA: the run constructed the object and did not call it, so no result was computed. The image it ran in was 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)

# CPA constructor parameters:
# - text_dim: int (embedding dimension)
# - attn_heads: int (number of attention heads)
# - alpha_init: float (initialization value for DyT alpha)

ARGS = {
    "text_dim": 8,
    "attn_heads": 2,
    "alpha_init": 0.5,
}
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 CPA — 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 CPA 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
ContextBranch Ran
ran on a synthesized input · constructed an object; no result was computed
KaziRamisaRifa/capiqa/model.py
code served (permissive licence) · get_code("f40c7611055e0c57")
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, ContextBranch: the run constructed the object and did not call it, so no result was computed. The image it ran in was 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)

# Construct arguments for ContextBranch.__init__
# Parameters: feat_dim, text_dim=768, L=4

# feat_dim: integer specifying input feature dimension
feat_dim = 16

# text_dim: integer specifying text embedding dimension (default 768)
text_dim = 32

# L: integer specifying number of learnable context tokens (default 4)
L = 3

ARGS = {
    "feat_dim": feat_dim,
    "text_dim": text_dim,
    "L": L,
}
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 ContextBranch — 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 ContextBranch 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
DoubleConv Ran
ran on a synthesized input · constructed an object; no result was computed
KaziRamisaRifa/capiqa/model.py
code served (permissive licence) · get_code("300a9716e4eda684")
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, DoubleConv: the run constructed the object and did not call it, so no result was computed. The image it ran in was 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)

ARGS = {
    'in_ch': 3,
    'out_ch': 16,
}
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 DoubleConv — 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 DoubleConv 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
DyT Ran
ran on a synthesized input · constructed an object; no result was computed
KaziRamisaRifa/capiqa/model.py
code served (permissive licence) · get_code("176372fcffe0e9dc")
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, DyT: the run constructed the object and did not call it, so no result was computed. The image it ran in was 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)

# The DyT.__init__ takes num_features and alpha_init_value
# The forward method takes x (a tensor)
# We need to construct arguments for the __init__ method

num_features = 4
alpha_init_value = 0.5

ARGS = {
    "num_features": num_features,
    "alpha_init_value": alpha_init_value,
}
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 DyT — 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 DyT 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
UNet_IQA Ran
ran on a synthesized input · constructed an object; no result was computed
KaziRamisaRifa/capiqa/model.py
code served (permissive licence) · get_code("9edf31ef0e8d6760")
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, UNet_IQA: the run constructed the object and did not call it, so no result was computed. The image it ran in was 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)

ARGS = {
    "in_ch": 1,
    "base_dim": 32,
    "text_dim": 768,
    "context_L": 4,
}
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 UNet_IQA — 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 UNet_IQA 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

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

Prompt-based methods, which encode medical priors through descriptive text, have been only minimally explored for CT Image Quality Assessment (IQA). While such prompts can embed prior knowledge about diagnostic quality, they often introduce bias by reflecting idealized definitions that may not hold under real-world degradations such as noise, motion artifacts, or scanner variability. To address this, we propose the Context-Aware Prompt-guided Image Quality Assessment (CAP-IQA) framework, which integrates text-level priors with instancelevel context prompts and applies causal debiasing to separate idealized knowledge from factual, image-specific degradations. Our framework combines a CNN-based visual encoder with a domain-specific text encoder to assess diagnostic visibility, anatomical clarity, and noise perception in abdominal CT images. The model leverages radiology-style prompts and context-aware fusion to align semantic and perceptual representations. On the 2023 LDCTIQA challenge benchmark, CAP-IQA achieves an overall correlation score of 2.8590 (sum of PLCC, SROCC, and KROCC), surpassing the top-ranked leaderboard team (2.7427) by 4.24%. Moreover, our comprehensive ablation experiments confirm that prompt-guided fusion and the simplified encoder-only design jointly enhance feature alignment and interpretability. Furthermore, evaluation on an in-house dataset of 91,514 pediatric CT images demonstrates the true generalizability of CAP-IQA in assessing perceptual fidelity in a different patient population. Our code is available at https://github.com/KaziRamisaRifa/capiqa.

For agents

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

get_harvested_code_for_paper("2601.01613")
get_code_for_paper("2601.01613")
have("2601.01613")

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

curl https://syntology.ai/api/ran/2601.01613.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.01613.svg)](https://syntology.ai/paper/2601.01613)

Connect an agent — have() is free.