Paper Citation Record · LEDGER

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection

As of 20 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 3 inbound Pith citation observations for arXiv:2412.03342.

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

pith.paper-citation-record.v1
2412.03342 v3

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T22:33:28.953263Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:01:02.377695Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T17:22:04.608717Z

Reference resolution

38 of 38 outbound references displayed

verified exact0
verified fuzzy24
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6581f2ab-c641-4c14-9204-37e7b0f73eb2 · outbound

This paper cites The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.155711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ebab1a7-33ce-4b9c-98fe-8a2fef332293 · outbound

This paper cites Bmad: Benchmarks for medical anomaly detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Bmad: Benchmarks for medical anomaly detection

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.480735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a223500b-83e4-4ab4-a65c-6ea5ce257073 · outbound

This paper cites Diagnos- tic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Diagnos- tic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.467672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9bd039b6-3b78-46ff-a1d5-ecc6e61e69ce · outbound

This paper cites Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.453341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 98e87f4b-23d9-43d7-a55b-78c4ebf9bee2 · outbound

This paper cites Beyond dents and scratches: Logical constraints in unsupervised anomaly detection and localization.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Beyond dents and scratches: Logical constraints in unsupervised anomaly detection and localization

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.441478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 16294875-2a72-4a3e-bc32-f6c5afc29f5a · outbound

This paper cites The liver tumor segmentation benchmark (lits).

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection The liver tumor segmentation benchmark (lits)

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.428129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 62541172-ebcd-416f-905c-3a665a583122 · outbound

This paper cites Rethinking au- toencoders for medical anomaly detection from a theoretical perspective.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Rethinking au- toencoders for medical anomaly detection from a theoretical perspective

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.367784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d63eacbf-e21b-4496-beaf-c2101d4dc625 · outbound

This paper cites APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.382641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4b346dd-31e9-48a9-a44c-de3b2ebd27a6 · outbound

This paper cites Catching both gray and black swans: Open-set supervised anomaly detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Catching both gray and black swans: Open-set supervised anomaly detection

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.406467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec2cb01c-a89f-44f8-b3b4-1137f41cf685 · outbound

This paper cites Filo: Zero-shot anomaly detection by fine-grained description and high-quality local- ization.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Filo: Zero-shot anomaly detection by fine-grained description and high-quality local- ization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.425617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c29c3b7-d7a8-4654-8e96-3593ea4826c7 · outbound

This paper cites Anomalygpt: Detecting in- dustrial anomalies using large vision-language models.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Anomalygpt: Detecting in- dustrial anomalies using large vision-language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.300739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6560b674-a4c2-4568-8635-cc81f6bf813e · outbound

This paper cites Madgan: Unsupervised medical anomaly detection gan us- ing multiple adjacent brain mri slice reconstruction.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Madgan: Unsupervised medical anomaly detection gan us- ing multiple adjacent brain mri slice reconstruction

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.244243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 60e640ad-b402-4859-adc5-e0266f1a9afc · outbound

This paper cites Deep residual learning for image recognition.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Deep residual learning for image recognition

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.449706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa16dc6e-a020-4427-9296-6ed0eb3f9c28 · outbound

This paper cites CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.455225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 274fe5f0-2c38-4323-8a8f-aaab266dedc4 · outbound

This paper cites Automated seg- mentation of macular edema in oct using deep neural net- works.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Automated seg- mentation of macular edema in oct using deep neural net- works

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.219669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 982f86c3-846e-49c9-82ef-df2ec416f039 · outbound

This paper cites Adapting visual-language models for generalizable anomaly detection in medical im- ages.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Adapting visual-language models for generalizable anomaly detection in medical im- ages

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.463549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 849cf702-1805-412f-98d6-2d3831a7bec5 · outbound

This paper cites Open-set image tagging with multi-grained text su- pervision.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Open-set image tagging with multi-grained text su- pervision

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.144317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 900ab0ca-5ff4-43eb-accf-58f20a4c517b · outbound

This paper cites Recon- patch: Contrastive patch representation learning for indus- trial anomaly detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Recon- patch: Contrastive patch representation learning for indus- trial anomaly detection

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.066822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation eb949c53-ecb9-4136-9618-b50d5f68032c · outbound

This paper cites Winclip: Zero- /few-shot anomaly classification and segmentation.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Winclip: Zero- /few-shot anomaly classification and segmentation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.019732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fcf0bd94-5e97-44e3-bf47-3df3d4ff8bbd · outbound

This paper cites Identifying medical diagnoses and treatable diseases by image-based deep learning.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Identifying medical diagnoses and treatable diseases by image-based deep learning

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:30.002727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6275d6bb-d9b1-4a77-ba72-9300af445888 · outbound

This paper cites Few shot part segmentation reveals compositional logic for industrial anomaly detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Few shot part segmentation reveals compositional logic for industrial anomaly detection

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.976478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0e384bdd-d6dd-44e0-a0a3-f3a9b5eca7e2 · outbound

This paper cites Segment any- thing.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Segment any- thing

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.887426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bea71f98-6a18-4a1a-b09c-c5adcbf83f64 · outbound

This paper cites Miccai multi-atlas la- beling beyond the cranial vault–workshop and challenge.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Miccai multi-atlas la- beling beyond the cranial vault–workshop and challenge

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.784086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6833291f-92b6-4d32-b57f-d7d1e4b58ae2 · outbound

This paper cites Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.703060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22d9dceb-3d1f-46db-80d8-ab0e8aecb083 · outbound

This paper cites Component-aware anomaly detec- tion framework for adjustable and logical industrial visual inspection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Component-aware anomaly detec- tion framework for adjustable and logical industrial visual inspection

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.767427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ee6443b7-73d1-4861-adde-becfc4fdd80d · outbound

This paper cites SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.775566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0606fcc-7e33-4916-a0d1-bf98be9f7197 · outbound

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

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Learning transferable visual models from natural language supervi- sion

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.779869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 912c7452-4514-47d8-9811-1177af410992 · outbound

This paper cites Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.783839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9389edb7-df4c-4d4c-bfb5-606412be1988 · outbound

This paper cites Towards to- tal recall in industrial anomaly detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Towards to- tal recall in industrial anomaly detection

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.692752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1f7c58bd-ced2-4030-9c00-def1d54eaa11 · outbound

This paper cites Berg, and Li Fei-Fei.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Berg, and Li Fei-Fei

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.792341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba196b26-e8ff-4d1c-836b-d146913fb223 · outbound

This paper cites Self-supervised pseudo multi-class pre-training for unsupervised anomaly detection and segmentation in medi- cal images.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Self-supervised pseudo multi-class pre-training for unsupervised anomaly detection and segmentation in medi- cal images

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.426990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c6584fb3-78cd-4fb1-9007-3a5961d4e424 · outbound

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

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Chestx- ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.799969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52fdf5b5-ced7-41d2-9b4a-eaf2e934ae72 · outbound

This paper cites MedCLIP: Contrastive Learning from Unpaired Medical Images and Text.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection MedCLIP: Contrastive Learning from Unpaired Medical Images and Text

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T22:33:28.805652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e35384ac-50d8-46a4-9cd9-0b5686d5a184 · outbound

This paper cites Agca: An adaptive graph channel attention module for steel surface defect detection.IEEE Transactions on Instrumentation and Measurement, 72:1–12, 2023.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Agca: An adaptive graph channel attention module for steel surface defect detection.IEEE Transactions on Instrumentation and Measurement, 72:1–12, 2023

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.364997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 86fba50f-1166-46aa-97ca-9ca2b3acc412 · outbound

This paper cites Explicit boundary guided semi-push- pull contrastive learning for supervised anomaly detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Explicit boundary guided semi-push- pull contrastive learning for supervised anomaly detection

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.350440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f21ec844-85a8-4423-87ab-6fce1268887c · outbound

This paper cites A unified model for multi-class anomaly detection.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection A unified model for multi-class anomaly detection

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.336097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b5e73595-b223-48cd-b7a4-0ecbfbe2df3f · outbound

This paper cites Recognize anything: A strong image tagging model.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection Recognize anything: A strong image tagging model

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.292359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ec879837-6c64-474c-8ad7-fe5a7d110f6c · outbound

This paper cites deep": [],.

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection deep": [],

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T22:33:29.221284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation f3f8baed-4996-4f75-9856-f61f16d89af0 · inbound

SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Images cites this paper.

SD-MAD: Sign-Driven Few-shot Multi-Anomaly Detection in Medical Images UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:01:02.377695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79c5195f-752d-4012-8bd2-2fda2e600cc3 · inbound

OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning cites this paper.

OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:58.812195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 273c508f-5850-446d-81b3-ab619fd6baa8 · inbound

A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospects cites this paper.

A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospects UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection

Reference 177

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:22:04.715160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.