Paper Citation Record · LEDGER

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis

As of 14 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2505.22079.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.22079 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:21:12.948487Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

41 of 41 outbound references displayed

verified exact2
verified fuzzy17
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f206edcc-ed16-45b6-8254-7fdf2e151234 · outbound

This paper cites Publicly Available Clinical BERT Embeddings.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Publicly Available Clinical BERT Embeddings

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:09.538223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95198e46-19ee-4108-b762-a5ee0641bc77 · outbound

This paper cites ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metrics.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metrics

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:21:13.529453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d9a0ceb1-4188-47f5-b2ce-d830818e005e · outbound

This paper cites Learning to exploit temporal structure for biomed- ical vision-language processing.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Learning to exploit temporal structure for biomed- ical vision-language processing

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:15.629358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c200ebbe-3e8a-4032-bb39-249ec057e277 · outbound

This paper cites MAIRA-2: Grounded Radiology Report Generation.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis MAIRA-2: Grounded Radiology Report Generation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:09.650114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b9cca04-c59e-4eda-832f-df28a1e25d0b · outbound

This paper cites LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:09.714262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37a52147-b0a7-4777-ad54-bbdcc5c9eeb3 · outbound

This paper cites Making the most of text semantics to improve biomedical vision–language processing.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Making the most of text semantics to improve biomedical vision–language processing

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:09.800073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c3e7aa2-bbd3-4304-b2ad-f1e28810afe5 · outbound

This paper cites CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:09.877280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d167aa2f-2880-40ee-8632-bad3f19594e5 · outbound

This paper cites A simple framework for contrastive learning of visual representations.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis A simple framework for contrastive learning of visual representations

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:09.920356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46964f6c-5d62-445a-af16-5565c6698452 · outbound

This paper cites Preparing a collection of radiology examinations for distribution and re- trieval.Journal of the American Medical Informatics Asso- ciation, 23(2):304–310, 2016.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Preparing a collection of radiology examinations for distribution and re- trieval.Journal of the American Medical Informatics Asso- ciation, 23(2):304–310, 2016

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:15.471495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 279dd3ac-9f83-4977-aced-81ba312298bc · outbound

This paper cites Improving clip training with language rewrites.Advances in Neural Information Processing Sys- tems, 36, 2024.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Improving clip training with language rewrites.Advances in Neural Information Processing Sys- tems, 36, 2024

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:15.390639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation aed39819-3e0a-4730-bfc0-db47e70c66ff · outbound

This paper cites Pyramidclip: Hierarchical fea- ture alignment for vision-language model pretraining.Ad- vances in neural information processing systems, 35:35959– 35970, 2022.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Pyramidclip: Hierarchical fea- ture alignment for vision-language model pretraining.Ad- vances in neural information processing systems, 35:35959– 35970, 2022

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:15.251527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b3813d71-b592-4228-baae-40f2ebebe455 · outbound

This paper cites Softclip: Softer cross-modal alignment makes clip stronger.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Softclip: Softer cross-modal alignment makes clip stronger

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:15.101894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation baed0c05-6634-4b75-8d2c-e24d043b0a49 · outbound

This paper cites Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality.Advances in neural information processing systems, 36, 2024.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality.Advances in neural information processing systems, 36, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:10.410255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 298e8e29-1d7a-406a-bc7c-253392c86caa · outbound

This paper cites Gloria: A multimodal global-local represen- tation learning framework for label-efficient medical image recognition.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Gloria: A multimodal global-local represen- tation learning framework for label-efficient medical image recognition

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:14.964294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6f030050-e1d7-4bf2-848d-d6e41ce6218e · outbound

This paper cites Llm2clip: Powerful language model unlock richer visual representation.arXiv preprint arXiv:2411.04997, 2024.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Llm2clip: Powerful language model unlock richer visual representation.arXiv preprint arXiv:2411.04997, 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:10.623305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cbadacc-5e11-4c0c-bcfc-825322910e2e · outbound

This paper cites RadGraph: Extracting Clinical Entities and Relations from Radiology Reports.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis RadGraph: Extracting Clinical Entities and Relations from Radiology Reports

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:10.725718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40c851b4-f971-4b56-89be-c8d72d97fbf8 · outbound

This paper cites Mimic- iv.PhysioNet.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Mimic- iv.PhysioNet

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:14.838414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 455e70d9-a831-4732-b4ec-85b108b647b0 · outbound

This paper cites Mimic-iii, a freely accessible critical care database.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Mimic-iii, a freely accessible critical care database

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:14.756514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ed2ad613-6bf6-4d07-b2a8-403acd629ac0 · outbound

This paper cites Carzero: Cross-attention alignment for radiology zero-shot classifica- tion.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Carzero: Cross-attention alignment for radiology zero-shot classifica- tion

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:14.575791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d77a6c48-9565-4f39-98f8-80179d8c550b · outbound

This paper cites Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:11.100535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adcbfdc5-eba3-4b4d-a322-57009c7e9a23 · outbound

This paper cites Mlip: Enhanc- ing medical visual representation with divergence encoder and knowledge-guided contrastive learning.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Mlip: Enhanc- ing medical visual representation with divergence encoder and knowledge-guided contrastive learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:14.524824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 35a0c975-b975-4908-a59a-c121d1e619a1 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Swin transformer: Hierarchical vision transformer using shifted windows

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:11.248543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f49f1b-5508-4419-a824-349dbdab8246 · outbound

This paper cites Crepe: Can vision-language foundation models reason compositionally? InProceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 10910–10921, 2023.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Crepe: Can vision-language foundation models reason compositionally? InProceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 10910–10921, 2023

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:14.426785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0d292422-69ec-41b4-808c-2f2956de3fee · outbound

This paper cites Vindr-cxr: An open dataset of chest x-rays with radiologist’s annotations.Scientific Data, 9(1):429, 2022.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Vindr-cxr: An open dataset of chest x-rays with radiologist’s annotations.Scientific Data, 9(1):429, 2022

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:14.281363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c80185bd-c3d8-4801-90a3-6966f6e1310d · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Representation Learning with Contrastive Predictive Coding

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:11.468964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6173f5b-e527-43fa-9f9f-4c1ba745c318 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Learning transferable visual models from natural language supervi- sion

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:11.540120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce6f11b4-6ac9-4f16-bf50-d9b75f17bf91 · outbound

This paper cites Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:11.636602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c888b2a6-dd4a-4779-8236-808d55b1eb71 · outbound

This paper cites CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:11.754802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8afd1af0-f75c-4b2a-bbc9-271a2e036191 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Gemini: A Family of Highly Capable Multimodal Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:11.826337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2528832a-1bc4-44ee-85a8-2c2e19706ed9 · outbound

This paper cites Expert-level detection of pathologies from unannotated chest x-ray images via self- supervised learning.Nature Biomedical Engineering, 6(12): 1399–1406, 2022.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Expert-level detection of pathologies from unannotated chest x-ray images via self- supervised learning.Nature Biomedical Engineering, 6(12): 1399–1406, 2022

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:14.186464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 50ac963b-7d0d-49c3-9303-179b09061bb1 · outbound

This paper cites Chestx- ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Chestx- ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:12.010746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67bb6d96-cf59-4449-ae5f-dcb462bea47c · outbound

This paper cites Exploring vision-language models for imbalanced learning.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Exploring vision-language models for imbalanced learning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:14.003475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bd1f5940-7dec-408a-840a-bffeeff288f1 · outbound

This paper cites What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:21:13.143651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f8e46638-94e2-4759-9ca3-9a2a00c0163a · outbound

This paper cites MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:12.293018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af9da242-978c-4539-8238-a51dd118ef4e · outbound

This paper cites Medklip: Medical knowledge enhanced language-image pre-training for x-ray diagnosis.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Medklip: Medical knowledge enhanced language-image pre-training for x-ray diagnosis

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:13.930777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8ca92bd8-2432-4974-b685-cd7ef639c942 · outbound

This paper cites Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:12.456215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fc4d945-6945-47db-b88f-018a8c4ce72d · outbound

This paper cites Graph convo- lutional networks for text classification.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Graph convo- lutional networks for text classification

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:13.782151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0b999f1d-07f8-4b41-8826-2a59bcb1886c · outbound

This paper cites Cxr-clip: Toward large scale chest x-ray language-image pre-training.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Cxr-clip: Toward large scale chest x-ray language-image pre-training

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:21:13.660978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5978c2a7-5ae2-4d2b-a6dc-1796a0f67198 · outbound

This paper cites When and why vision-language models behave like bags-of-words, and what to do about it?.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:12.731024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0793282e-30ea-4e68-b329-ee97ebf82a00 · outbound

This paper cites Contrastive learning of medical visual representations from paired images and text.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis Contrastive learning of medical visual representations from paired images and text

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:12.872050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10ce43f0-2cca-49ec-a63e-2a646f5a7f39 · outbound

This paper cites CLIP in Medical Imaging: A Survey.

Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis CLIP in Medical Imaging: A Survey

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:12.948487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.