Paper Citation Record · LEDGER

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers

As of 23 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 1 inbound Pith citation observation for arXiv:2501.09221.

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

pith.paper-citation-record.v1
2501.09221 v2

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:12:58.172261Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:35:03.349259Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T17:35:03.450625Z

Reference resolution

13 of 13 outbound references displayed

verified exact1
verified fuzzy5
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1966fa80-2ed0-491e-949d-13af8a6fcf86 · outbound

This paper cites Describing objects by their attributes.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers Describing objects by their attributes

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:12:58.355315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2fc6978c-abd0-4474-91ba-1071b70ea112 · outbound

This paper cites AST: Audio Spectrogram Transformer.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers AST: Audio Spectrogram Transformer

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T20:12:58.144966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2af4640b-0220-4526-a915-86b3be921b4e · outbound

This paper cites Are Convolutional Neural Networks or Transformers more like human vision?.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers Are Convolutional Neural Networks or Transformers more like human vision?

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T20:12:58.153980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e30bcfb-b02e-4203-815c-e7bb59b0959e · outbound

This paper cites Deformable DETR: Deformable Transformers for End-to-End Object Detection.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers Deformable DETR: Deformable Transformers for End-to-End Object Detection

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T20:12:58.163307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e9718b5-4a7d-4876-a0d8-8e6e79d6de7c · outbound

This paper cites We set the patch size to correspond to 16x16 pixels.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers We set the patch size to correspond to 16x16 pixels

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:12:58.328782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5aedb210-1e7d-4602-9b5f-bfde6765f8ba · outbound

This paper cites The following convolution blocks consist of a single convolution layer of kernel size=3 and stride=2, as well as the batch norm and ReLU activations.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers The following convolution blocks consist of a single convolution layer of kernel size=3 and stride=2, as well as the batch norm and ReLU activations

Reference 1029

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:12:58.316300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 55785ad0-265a-4d90-a10f-99f7d97a28a6 · outbound

This paper cites The caltech-ucsd birds-200-2011 dataset.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers The caltech-ucsd birds-200-2011 dataset

Reference 2017

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:12:58.341517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation febaf998-ae44-47df-9776-593b65b844ff · outbound

This paper cites Image transformer for explainable au- tonomous driving system.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers Image transformer for explainable au- tonomous driving system

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:12:58.370876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 654f5a22-82c6-4486-a61c-88f8aa928c89 · outbound

This paper cites Vision Transformer Adapter for Dense Predictions.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers Vision Transformer Adapter for Dense Predictions

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-10T20:12:58.127534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a742862d-fc28-4129-aaf0-71e73f46c555 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-10T20:12:58.131823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d54e9a35-8411-4432-82d3-9ea3956193b6 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers On the Opportunities and Risks of Foundation Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-10T20:12:58.123392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec637453-89cc-459b-88f8-9e10cb04b1c7 · outbound

This paper cites SiT: Self-supervised vIsion Transformer.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers SiT: Self-supervised vIsion Transformer

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-10T20:12:58.118649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df43ab0e-c0d5-4cb3-aa0a-487c8a98c86d · outbound

This paper cites A Self-explaining Neural Architecture for Generalizable Concept Learning.

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers A Self-explaining Neural Architecture for Generalizable Concept Learning

Reference 2024

Resolution: verified exact; local_arxiv, observed 2026-08-10T20:12:58.236527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation d069482b-01f8-4bcf-8cb7-08316db20626 · inbound

Integrating attention into explanation frameworks for language and vision transformers cites this paper.

Integrating attention into explanation frameworks for language and vision transformers ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-15T17:35:03.459622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.