Paper Citation Record · LEDGER

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

As of 21 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 4 inbound Pith citation observations for arXiv:2502.02797.

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

pith.paper-citation-record.v1
2502.02797 v2

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T11:12:08.289178Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T05:52:38.387523Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T07:18:07.045532Z

Reference resolution

38 of 38 outbound references displayed

verified exact2
verified fuzzy15
unresolved18
parse uncertain0
malformed identifier3
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c2ccc43e-9e2b-4e7c-925c-f5bb6aa4c785 · outbound

This paper cites HellaSwag presents a context followed by several plausible endings, and the model must choose the most appropriate continuation.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting HellaSwag presents a context followed by several plausible endings, and the model must choose the most appropriate continuation

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:16.058577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6d7fa0af-16b3-4db9-8843-7d4579950811 · outbound

This paper cites exp − ⟨r,z⟩ 2 α ! ⟨r,z⟩ 2 # r+ d−1X j=1 E.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting exp − ⟨r,z⟩ 2 α ! ⟨r,z⟩ 2 # r+ d−1X j=1 E

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:16.080018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fc444b66-8d68-4f14-9717-5498278db48a · outbound

This paper cites an unresolved cited work.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:12:16.035563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b9f055f2-d46f-46ec-bbc1-a89304aac1be · outbound

This paper cites The Llama 3 Herd of Models.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting The Llama 3 Herd of Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.165381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f256338-d201-4106-b555-34eb22ff346a · outbound

This paper cites an unresolved cited work.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:12:16.014017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 854a8fd4-5572-425b-b969-34600f2fd6d3 · outbound

This paper cites an unresolved cited work.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:12:16.002966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 50348aa0-de56-4d17-8122-64802b448311 · outbound

This paper cites an unresolved cited work.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:12:15.992760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ff7b63de-605d-4509-afb8-954cb436f66d · outbound

This paper cites an unresolved cited work.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:12:15.981055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d1137124-7b6e-47f1-9110-4e3af87fa5a3 · outbound

This paper cites org/CorpusID:215786151.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting org/CorpusID:215786151

Reference 9

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T11:12:15.715919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation edf95260-5ff9-4d74-a7bf-98bf98702169 · outbound

This paper cites Online Batch Selection for Faster Training of Neural Networks.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Online Batch Selection for Faster Training of Neural Networks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.188932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdf3674e-d94a-4e7f-ad11-9bcb54f29261 · outbound

This paper cites org/CorpusID:5324823.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting org/CorpusID:5324823

Reference 11

Resolution: verified exact; raw_fallback, observed 2026-08-09T11:12:09.791349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 412af3d0-4e8a-4aa3-90e3-163c718e1d68 · outbound

This paper cites Rajasegaran, J., Hayat, M., Khan, S.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Rajasegaran, J., Hayat, M., Khan, S

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:16.103297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f41b576d-52a8-43f4-bedf-996de2be4cde · outbound

This paper cites Progressive Neural Networks.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Progressive Neural Networks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.204038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 771fc37b-44ac-4711-90e8-e94bb3d7cec9 · outbound

This paper cites org/CorpusID:12253672.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting org/CorpusID:12253672

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.208134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99d97692-4d4d-4e3f-b9f0-c456f257e38b · outbound

This paper cites MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Reference 18

Resolution: malformed identifier; no resolver link, observed 2026-08-09T11:12:08.220099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f477e3-57e1-4cf2-bd67-b1c1b4467abd · outbound

This paper cites Following a similar setup as us, Biderman et al.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Following a similar setup as us, Biderman et al

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:16.069410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a8474ce1-bc1b-4281-87aa-3b3011465a60 · outbound

This paper cites an unresolved cited work.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:12:16.047304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6daab356-2370-40f1-b67c-bdd79792b22c · outbound

This paper cites PIQA presents a goal and two possible solutions, requiring models to choose the most appropriate solution that demonstrates an understanding of everyday physical interactions.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting PIQA presents a goal and two possible solutions, requiring models to choose the most appropriate solution that demonstrates an understanding of everyday physical interactions

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:16.024669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0c4ec655-c716-4224-af00-562ee86007e5 · outbound

This paper cites an unresolved cited work.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:12:15.969356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 09131df9-59a1-4024-90a3-d6029de9960a · outbound

This paper cites It is a widely used large-scale image classification dataset, consisting of over a million images spanning 1000 classes.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting It is a widely used large-scale image classification dataset, consisting of over a million images spanning 1000 classes

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:15.958626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7308244a-cde9-46bc-9e28-6d2a656b94fc · outbound

This paper cites It consists of 60,000 32x32 color images divided into ten classes, with 6,000 images per class.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting It consists of 60,000 32x32 color images divided into ten classes, with 6,000 images per class

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:15.946836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b9efab78-7e0e-425c-9894-dd53841d50ee · outbound

This paper cites This dataset is used for fine-grained image classification tasks.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting This dataset is used for fine-grained image classification tasks

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:15.934177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6d8d407e-5051-4bc6-b42f-ebc083f36932 · outbound

This paper cites an unresolved cited work.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:12:15.922736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 137723b8-1704-4e20-a93c-84ab1f940b38 · outbound

This paper cites This dataset is commonly used for fine-grained image classification and flower recognition tasks.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting This dataset is commonly used for fine-grained image classification and flower recognition tasks

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:15.911767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cf488483-90c7-4328-a29d-3a14f6ebb672 · outbound

This paper cites It provides a rich resource for fine-grained car classification task.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting It provides a rich resource for fine-grained car classification task

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:15.900306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 362cd836-dbf1-4197-9ac2-485d88f2f590 · outbound

This paper cites This dataset is widely used for fine-grained dog breed classification and recognition tasks.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting This dataset is widely used for fine-grained dog breed classification and recognition tasks

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:15.889747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b15b7d3e-923d-4d9c-a933-845dbb8d00d6 · outbound

This paper cites learning without forgetting.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting learning without forgetting

Reference 37

Resolution: malformed identifier; arxiv_id_nonexistent, observed 2026-08-09T11:12:09.618747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7329e9ca-7020-480f-a135-f2f3755f7d4e · outbound

This paper cites We use varying α∈[0,1] for WiSE-FT.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting We use varying α∈[0,1] for WiSE-FT

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:15.877828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4a07ffec-cf2a-40ba-ae5f-52c075750bf2 · outbound

This paper cites Robust fine-tuning of zero-shot models.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Robust fine-tuning of zero-shot models

Reference 715

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.212220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2a9bcb5-33a8-432d-ac1b-f24b15ac94e8 · outbound

This paper cites Program Synthesis with Large Language Models.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Program Synthesis with Large Language Models

Reference 2015

Resolution: malformed identifier; no resolver link, observed 2026-08-09T11:12:08.151280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 652fedc3-3e29-4a3d-ab20-63b95647d0a0 · outbound

This paper cites Soup to go: mitigating forgetting during continual learning with model averaging.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Soup to go: mitigating forgetting during continual learning with model averaging

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.181402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669d8da3-f5fc-4c34-a3dd-a28249ef1196 · outbound

This paper cites org/CorpusID:19243534.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting org/CorpusID:19243534

Reference 2017

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:16.114414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6375b629-10eb-4e90-82b5-d4b965620b82 · outbound

This paper cites org/CorpusID:3652214.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting org/CorpusID:3652214

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:16.091009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bceb9997-81d9-4e03-b133-b29e78819aa3 · outbound

This paper cites Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.196583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dc35d19-4a5f-42b8-9dae-830518ad121a · outbound

This paper cites Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.160998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0975d986-e081-4f49-9190-1d3485098c4e · outbound

This paper cites org/CorpusID:232427874.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting org/CorpusID:232427874

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:12:16.126050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 26d3063b-2bd8-4fac-8c5d-c7760eb26654 · outbound

This paper cites Biased Importance Sampling for Deep Neural Network Training.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Biased Importance Sampling for Deep Neural Network Training

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.177819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b50c536a-cea3-42cb-bcb6-2a261be1382f · outbound

This paper cites Mistral 7B.

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting Mistral 7B

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T11:12:08.170193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 80febf3b-4f6f-4f2d-bfb4-44f361f16f20 · inbound

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning cites this paper.

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T05:52:38.387523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d57dfe-4679-4273-a596-261ae3d82390 · inbound

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts cites this paper.

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:58.986795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f34a04a3-6780-4f9f-9e69-7b280cef8f84 · inbound

Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates cites this paper.

Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:18:07.047290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8e65ae95-452e-483c-bc48-f69654095d5b · inbound

UniGen-AR: Unifying Visual Generation with Auto-Regressive Modeling cites this paper.

UniGen-AR: Unifying Visual Generation with Auto-Regressive Modeling Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-31T22:25:12.430501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.