Paper Citation Record · LEDGER

Rethinking Expert Training for Model Merging with Prompt Learning

As of 15 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2607.24465.

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

pith.paper-citation-record.v1
2607.24465 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T14:14:14.863736Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

46 of 46 outbound references displayed

verified exact0
verified fuzzy0
unresolved45
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 272283d6-3910-455b-a1f2-5dd58762c863 · outbound

This paper cites Food-101 – Mining Discriminative Components with Ran- dom Forests.

Rethinking Expert Training for Model Merging with Prompt Learning Food-101 – Mining Discriminative Components with Ran- dom Forests

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.702179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d75456b-9837-48cd-a183-6987d79ec615 · outbound

This paper cites Remote sens- ing image scene classification: Benchmark and state of the art.Proceedings of the IEEE, 2017.

Rethinking Expert Training for Model Merging with Prompt Learning Remote sens- ing image scene classification: Benchmark and state of the art.Proceedings of the IEEE, 2017

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.706754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ef0ae5c-e59b-452a-a30c-cb37af70953d · outbound

This paper cites Describing textures in the wild.

Rethinking Expert Training for Model Merging with Prompt Learning Describing textures in the wild

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.710539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d47f8e1-e740-44ef-a987-65cb7d272823 · outbound

This paper cites Deep Learning for Classical Japanese Literature.

Rethinking Expert Training for Model Merging with Prompt Learning Deep Learning for Classical Japanese Literature

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.714164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9857c403-88ff-4c6d-af1b-47a7ff79fc64 · outbound

This paper cites An Analysis of Single-Layer Networks in Unsupervised Feature Learn- ing.

Rethinking Expert Training for Model Merging with Prompt Learning An Analysis of Single-Layer Networks in Unsupervised Feature Learn- ing

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.718675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b206bf9b-d9f6-4d52-b8e0-9240ed06703b · outbound

This paper cites EMNIST: Extending MNIST to handwritten let- ters.

Rethinking Expert Training for Model Merging with Prompt Learning EMNIST: Extending MNIST to handwritten let- ters

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.722252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 947df152-ba73-4e02-951a-ca166aff5e62 · outbound

This paper cites Model breadcrumbs: Scaling multi-task model merging with sparse masks.Proceedings of the European Conference on Com- puter Vision, 2024.

Rethinking Expert Training for Model Merging with Prompt Learning Model breadcrumbs: Scaling multi-task model merging with sparse masks.Proceedings of the European Conference on Com- puter Vision, 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.726156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3493b9a-ad9d-4bb5-85c6-e2cc1060c9d8 · outbound

This paper cites Roy, and Michael Carbin.

Rethinking Expert Training for Model Merging with Prompt Learning Roy, and Michael Carbin

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.729488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa9348a3-932e-40d2-ba03-d16ae4ce4bf0 · outbound

This paper cites Clip with generative latent replay: a strong baseline for in- cremental learning.BMVC, 2024.

Rethinking Expert Training for Model Merging with Prompt Learning Clip with generative latent replay: a strong baseline for in- cremental learning.BMVC, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.732815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c7b3801-3579-434d-9f53-7ae1c202409b · outbound

This paper cites Task singular vectors: Reducing task in- terference in model merging.Proceedings of the IEEE con- ference on Computer Vision and Pattern Recognition, 2025.

Rethinking Expert Training for Model Merging with Prompt Learning Task singular vectors: Reducing task in- terference in model merging.Proceedings of the IEEE con- ference on Computer Vision and Pattern Recognition, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.736080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abc64c3e-4698-4586-b05a-7200e0a6d55f · outbound

This paper cites Challenges in representation learning: A re- port on three machine learning contests.Neural Networks, 64, 2013.

Rethinking Expert Training for Model Merging with Prompt Learning Challenges in representation learning: A re- port on three machine learning contests.Neural Networks, 64, 2013

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.739245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebe00112-041b-4e53-a516-d00eb8bd8d5d · outbound

This paper cites EuroSAT: A Novel Dataset and Deep Learn- ing Benchmark for Land Use and Land Cover Classification.

Rethinking Expert Training for Model Merging with Prompt Learning EuroSAT: A Novel Dataset and Deep Learn- ing Benchmark for Land Use and Land Cover Classification

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.742688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85481ff5-4556-4e5e-8006-4e24e44d32eb · outbound

This paper cites an unresolved cited work.

Rethinking Expert Training for Model Merging with Prompt Learning Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.746107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55883c4-20b1-49b7-ab97-e86490d7cd5b · outbound

This paper cites Editing models with task arithmetic.

Rethinking Expert Training for Model Merging with Prompt Learning Editing models with task arithmetic

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.749468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37a1c68d-1d33-45ac-a7e7-2a4827ba644a · outbound

This paper cites Vi- sual prompt tuning.

Rethinking Expert Training for Model Merging with Prompt Learning Vi- sual prompt tuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.753660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6543ad27-54bc-48a2-940b-738566ec5eca · outbound

This paper cites Maple: Multi-modal prompt learning.

Rethinking Expert Training for Model Merging with Prompt Learning Maple: Multi-modal prompt learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.757693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8055a3a7-9c2b-4ee8-a18d-cc682aaf9743 · outbound

This paper cites Self-regulating prompts: Foundational model adaptation without forgetting.

Rethinking Expert Training for Model Merging with Prompt Learning Self-regulating prompts: Foundational model adaptation without forgetting

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.761808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d4a4ce0-f836-4dab-8a88-6021f93c6037 · outbound

This paper cites 3d object representations for fine-grained categorization.

Rethinking Expert Training for Model Merging with Prompt Learning 3d object representations for fine-grained categorization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.766087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7082b0ab-d5d0-412a-a12d-9633e63b8b7c · outbound

This paper cites Learning multiple layers of features from tiny images.University of Toronto,.

Rethinking Expert Training for Model Merging with Prompt Learning Learning multiple layers of features from tiny images.University of Toronto,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.769606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 927b9ecc-5ecb-48f7-8189-a7578c6f0410 · outbound

This paper cites Mnist hand- written digit database.ATT Labs [Online]., 2, 2010.

Rethinking Expert Training for Model Merging with Prompt Learning Mnist hand- written digit database.ATT Labs [Online]., 2, 2010

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.773247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00cbfe90-c0f3-4345-98bf-e080dc7d4e1a · outbound

This paper cites P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks.

Rethinking Expert Training for Model Merging with Prompt Learning P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.776783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9d42dcf-4421-4bd7-9ecd-3ed3735d0fb2 · outbound

This paper cites U-net transplant: the role of pre-training for model merging in 3d medical segmentation.

Rethinking Expert Training for Model Merging with Prompt Learning U-net transplant: the role of pre-training for model merging in 3d medical segmentation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.780295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d468c15-8e56-4d28-a1db-b6d7e322e85d · outbound

This paper cites MAGMAX: leveraging model merg- ing for seamless continual learning.

Rethinking Expert Training for Model Merging with Prompt Learning MAGMAX: leveraging model merg- ing for seamless continual learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.783619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5a6b957-cf4f-45b7-a344-1ba7b7de08dd · outbound

This paper cites Bagdanov, and Joost van de Weijer.

Rethinking Expert Training for Model Merging with Prompt Learning Bagdanov, and Joost van de Weijer

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.786859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8450735-c1fa-4d6a-9715-b328b3be9c65 · outbound

This paper cites Merging models with fisher-weighted averaging.

Rethinking Expert Training for Model Merging with Prompt Learning Merging models with fisher-weighted averaging

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.790122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4c59b97-55ae-4ef7-bc0d-d7284725df96 · outbound

This paper cites An empirical investigation of the role of pre- training in lifelong learning.Journal of Machine Learning Research, 24(214):1–50, 2023.

Rethinking Expert Training for Model Merging with Prompt Learning An empirical investigation of the role of pre- training in lifelong learning.Journal of Machine Learning Research, 24(214):1–50, 2023

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.793334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c9c20c1-7e85-473b-8607-379ccf2f8d51 · outbound

This paper cites Linear Mode Connectivity in Multitask and Continual Learning.

Rethinking Expert Training for Model Merging with Prompt Learning Linear Mode Connectivity in Multitask and Continual Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.796450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f0ade5c-a901-4939-9ca8-242a8ac833a7 · outbound

This paper cites Reading digits in natural images with unsupervised feature learning.

Rethinking Expert Training for Model Merging with Prompt Learning Reading digits in natural images with unsupervised feature learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.800769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47fbe36b-418a-4603-bb43-3fe9fd16a4f1 · outbound

This paper cites Automated Flower Classification over a Large Number of Classes.

Rethinking Expert Training for Model Merging with Prompt Learning Automated Flower Classification over a Large Number of Classes

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.804519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a87aaddf-a58d-4c5d-861d-f6d27e4142f5 · outbound

This paper cites Bag- danov, Simone Calderara, and Joost van de Weijer.

Rethinking Expert Training for Model Merging with Prompt Learning Bag- danov, Simone Calderara, and Joost van de Weijer

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.807875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94ba8af9-0517-4e7b-8a0e-39226817be8e · outbound

This paper cites Parkhi, Andrea Vedaldi, Andrew Zisserman, and C.

Rethinking Expert Training for Model Merging with Prompt Learning Parkhi, Andrea Vedaldi, Andrew Zisserman, and C

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.811530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed045f31-7c48-4b97-99e7-bbc3dd052994 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Rethinking Expert Training for Model Merging with Prompt Learning Learning transferable visual models from natural language supervision

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.815594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a764d376-30b6-4cfa-b9ec-72cbc65043db · outbound

This paper cites Transporting task vectors across different architectures without training.International Conference on Machine Learning, 2026.

Rethinking Expert Training for Model Merging with Prompt Learning Transporting task vectors across different architectures without training.International Conference on Machine Learning, 2026

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.819309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f517fe6-b61c-46d4-a5b3-dee3d863397a · outbound

This paper cites Manning, A.

Rethinking Expert Training for Model Merging with Prompt Learning Manning, A

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.823112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fe1fb36-730d-4495-a1c5-f8e02dddd9eb · outbound

This paper cites an unresolved cited work.

Rethinking Expert Training for Model Merging with Prompt Learning Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.826361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88bcfb14-fdc1-4a16-84c7-17db2d71b181 · outbound

This paper cites Model merging with svd to tie the knots.International Conference on Learning Repre- sentations, 2025.

Rethinking Expert Training for Model Merging with Prompt Learning Model merging with svd to tie the knots.International Conference on Learning Repre- sentations, 2025

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.829720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff0aad3e-7868-42f9-a4ae-7eca41ff5b69 · outbound

This paper cites Veeling, Jasper Linmans, Jim Winkens, Taco Co- hen, and Max Welling.

Rethinking Expert Training for Model Merging with Prompt Learning Veeling, Jasper Linmans, Jim Winkens, Taco Co- hen, and Max Welling

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.833296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42fdfbca-3a1b-46e3-86ae-700e8a82fda1 · outbound

This paper cites Model soups: averaging weights of multi- ple fine-tuned models improves accuracy without increas- ing inference time.

Rethinking Expert Training for Model Merging with Prompt Learning Model soups: averaging weights of multi- ple fine-tuned models improves accuracy without increas- ing inference time

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.836714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98e0dd4f-b70b-4b6c-9ff3-108726c22407 · outbound

This paper cites Fashion- mnist: a novel image dataset for benchmarking machine learning algorithms, 2017.

Rethinking Expert Training for Model Merging with Prompt Learning Fashion- mnist: a novel image dataset for benchmarking machine learning algorithms, 2017

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.840291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07bf9822-204a-4ec0-b138-4087915ae211 · outbound

This paper cites Sun database: Exploring a large col- lection of scene categories.International Journal of Com- puter Vision, 2016.

Rethinking Expert Training for Model Merging with Prompt Learning Sun database: Exploring a large col- lection of scene categories.International Journal of Com- puter Vision, 2016

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.843561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be83c9e0-a05e-4540-8975-bb1f90b3e605 · outbound

This paper cites TIES-merging: Resolving interference when merging models.

Rethinking Expert Training for Model Merging with Prompt Learning TIES-merging: Resolving interference when merging models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.847130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef37f863-20bb-4607-b320-04eeb0f87afb · outbound

This paper cites Adamerging: Adap- tive model merging for multi-task learning.

Rethinking Expert Training for Model Merging with Prompt Learning Adamerging: Adap- tive model merging for multi-task learning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.850354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1317691c-7ad3-476a-83d4-b1592e92fd52 · outbound

This paper cites Model merg- ing in llms, mllms, and beyond: Methods, theories, appli- cations, and opportunities.ACM Computing Surveys, 58(8): 1–41, 2026.

Rethinking Expert Training for Model Merging with Prompt Learning Model merg- ing in llms, mllms, and beyond: Methods, theories, appli- cations, and opportunities.ACM Computing Surveys, 58(8): 1–41, 2026

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.853735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68cbefc1-f95f-4c8e-a895-3200f706c377 · outbound

This paper cites Conditional prompt learning for vision-language mod- els.

Rethinking Expert Training for Model Merging with Prompt Learning Conditional prompt learning for vision-language mod- els

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.856885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21bda87-142e-4f7a-8dcf-7c87833ea963 · outbound

This paper cites Learning to prompt for vision-language models.Inter- national Journal of Computer Vision, 2022.

Rethinking Expert Training for Model Merging with Prompt Learning Learning to prompt for vision-language models.Inter- national Journal of Computer Vision, 2022

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-31T14:14:14.860481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11369e3e-a4ea-4eaf-92f2-a77d8b77bf53 · outbound

This paper cites De- mystifying mergeability: Interpretable properties to predict model merging success.International Conference on Ma- chine Learning, 2026.

Rethinking Expert Training for Model Merging with Prompt Learning De- mystifying mergeability: Interpretable properties to predict model merging success.International Conference on Ma- chine Learning, 2026

Reference 46

Resolution: malformed identifier; no resolver link, observed 2026-07-31T14:14:14.863736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.