paper_id	claim	claim_status	evidence_status	source_depth	source_quote	page_or_section	taxonomy_fit	audit_status
2603.10027v1	It specifies a governance layer for deterministic clinical decision-support systems, formalizing when recommendations are permissible and when the system must abstain.	supported	has evidence row	full-text	No silent generalization beyond the defined scope is permitted. 2.3 Separation of Clinical Logic and Governance Clinical logic and governance mechanisms are treated as distinct design layers.	abstract	in-scope: LLM extractor confirmed direction match	needs work; full-text verified; report=audit_report.md
1803.08691v1	The model is trained and evaluated on a clinical computed tomography (CT) dataset and shows state-of-the-art performance in multi-organ segmentation.	preliminary-linked	has evidence row	full-text	we achieve an average Dice score performance of 89.4±6.4 (range [42.2, 95.9])% in training and 89.3±6.5 (range [63.1, 95.6])% in testing	III. EXPERIMENTS & RESULTS	in-scope: LLM extractor confirmed direction match	needs work; filled but source-depth unclear; report=audit_report.md
2212.08228v2	To the best of our knowledge, we are one of the first to explore the temporal dependency of sequential data and use it as a prior in diffusion models for medical image generation.	preliminary-linked	has evidence row	full-text	Our model outperforms the GAN-based method [4] by 3 to 13% in each metric while slightly outperforming the diffusion-based model [12].	11	in-scope: LLM extractor confirmed direction match	needs work; filled but source-depth unclear; report=audit_report.md
2109.02722v2	We extended our previously published end-to-end self-supervised deep learning method for automatically finding landmark correspondences in medical images from 2D to 3D.	supported	has evidence row	full-text	The results showed significant improvement in DIR performance when landmark correspondences predicted by DCNN-Match were used in the case of simulated (p = 0e0) as well as clinical deformations (p = 0.030).	Abstract	in-scope: LLM extractor confirmed direction match	needs work; full-text verified; report=audit_report.md
2101.02323v1	This is the first comprehensive study of multiple methods for active learning for medical image segmentation.	supported	has evidence row	full-text	The results indicate an improvement in terms of data reduction by achieving full accuracy while only using 22.69 % and 48.85 % of the available data for each dataset, respectively.	Abstract	in-scope: LLM extractor confirmed direction match	needs work; full-text verified; report=audit_report.md
2407.03548v1	We propose a novel hybrid diffusion framework (HiDiff) for medical image segmentation, which can synergize the strengths of existing discriminative segmentation models and the generative diffusion models.	supported	has evidence row	full-text	DiffEnsemble, cannot surpass most discriminative segmentor, even the vanilla U- Net baseline, which can be attributed to the deficiency of Gaussian diffusion kernel to handle the discrete nature of segmentation tasks.	Abstract	in-scope: LLM extractor confirmed direction match	needs work; full-text verified; report=audit_report.md
1804.03830v1	Our main contribution is to combine JULE with k-means for medical image segmentation.	supported	has evidence row	full-text	(For simpli cation, we have drawn the gure with a stride equal to w.) 2.5 Segmentation In the segmentation phase, we rst extract a possible number of patches of wwwvoxels from the target image separated by svoxels each.	3.3 Evaluations	in-scope: LLM extractor confirmed direction match	needs work; full-text verified; report=audit_report.md