Pith. sign in

Paper Citation Record · LEDGER

HRP: High-Rank Preheating for Superior LoRA Initialization

As of 8 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 0 inbound Pith citation observations for arXiv:2502.07739.

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

pith.paper-citation-record.v1
2502.07739 v3

Coverage vector

measured 62 of 62 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T11:51:10.457246Z

measured 62 of 62 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

62 of 62 outbound references displayed

  • verified exact5
  • verified fuzzy13
  • unresolved43
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d78085e1-0f15-4c17-a251-65b1de83c4ea · outbound

This paper cites GPT-4 Technical Report.

HRP: High-Rank Preheating for Superior LoRA Initialization GPT-4 Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:09.935617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:09.935617Z digest=sha256:cd66cb777e3aa7b702fd234b5b4cbb4a203b23b9a689024891ae3dbc8dc8dc37

Observation 003ee60f-5673-4d56-a477-a643e2fd7e61 · outbound

This paper cites LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters.

HRP: High-Rank Preheating for Superior LoRA Initialization LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:09.942047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:09.942047Z digest=sha256:da67a404421f65384ff2edcd9a77c9312caecbde9ac097cde51a7aa4a088bb2c

Observation 9ca2d721-629a-4124-bc2b-51d635eccc00 · outbound

This paper cites LoRA Learns Less and Forgets Less.

HRP: High-Rank Preheating for Superior LoRA Initialization LoRA Learns Less and Forgets Less

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:09.948149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:09.948149Z digest=sha256:f963d60ef5faa997aef86035c0f8b5a3cffb939b502c26c9212ce413d2ec201c

Observation 2eef8ede-ca9c-493b-a11b-54fb3d867758 · outbound

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

HRP: High-Rank Preheating for Superior LoRA Initialization On the Opportunities and Risks of Foundation Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:09.953937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:09.953937Z digest=sha256:1a3b87966aa25ebf2613d2be1c2b5d0624df348873f3a0610ff8e79f82e298c7

Observation 7ed829f0-8d4c-475d-8d88-f8bd760f3237 · outbound

This paper cites OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models.

HRP: High-Rank Preheating for Superior LoRA Initialization OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:09.959188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:09.959188Z digest=sha256:a9ccc064963486a95672709d0b34f37650a256271c9489f35894aa361d982c1a

Observation e3a2e738-3acc-45df-9555-dcd3f241ef68 · outbound

This paper cites Nonconvex optimization meets low-rank matrix factorization: An overview.

HRP: High-Rank Preheating for Superior LoRA Initialization Nonconvex optimization meets low-rank matrix factorization: An overview

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:09.966211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:09.966211Z digest=sha256:1462790fde130d766546d26ba5aacdda9a0c72b6feaa29f4f877677609893195

Observation 4f377922-c9ea-4771-b9cf-7c787e9f960d · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

HRP: High-Rank Preheating for Superior LoRA Initialization Training Verifiers to Solve Math Word Problems

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:09.974232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:09.974232Z digest=sha256:c376e94fd35565e3ee2dcb550bf81553f25733f47cc87c536175d25851732595

Observation 04a07925-a921-4de9-acd4-727ca4ebc31a · outbound

This paper cites Metainit: Initializing learning by learning to initialize.

HRP: High-Rank Preheating for Superior LoRA Initialization Metainit: Initializing learning by learning to initialize

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.910666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:09.981609Z digest=sha256:35c413303cb1090b0ab74982518cc5fd59f14c26e8ad1de548e27863712f1c16

Observation 1b9af9ac-46c9-4b81-812f-0fd32e2c7673 · outbound

This paper cites The approximation of one matrix by another of lower rank.

HRP: High-Rank Preheating for Superior LoRA Initialization The approximation of one matrix by another of lower rank

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:09.987470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:09.987470Z digest=sha256:45a6799330aa6bf150b7bdf431b674bd6e04568853f68b0d4a235d240a882416

Observation 55270172-619f-4622-b037-69b06f973298 · outbound

This paper cites Low rank adaptation for stable domain adaptation of vision transformers.

HRP: High-Rank Preheating for Superior LoRA Initialization Low rank adaptation for stable domain adaptation of vision transformers

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.878544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:09.995920Z digest=sha256:f0a69fac12c16e2b217bf57551dd280f352d8ed8aed2b3cda6e4390e265c2890

Observation 363998b1-fdef-4514-9024-7338286c035d · outbound

This paper cites A Theoretical Survey on Foundation Models.

HRP: High-Rank Preheating for Superior LoRA Initialization A Theoretical Survey on Foundation Models

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-08-08T11:51:11.394978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.007479Z digest=sha256:584865058ca4281d9793cbd1ca2b6c8e4b840e89ee37c08b09d10fff0f678e42

Observation 1f9eb1e0-4068-4d7e-8482-aca49966c0d8 · outbound

This paper cites Towards Theoretical Understandings of Self-Consuming Generative Models.

HRP: High-Rank Preheating for Superior LoRA Initialization Towards Theoretical Understandings of Self-Consuming Generative Models

Reference 12

Resolution
verified exact
local_arxiv, observed 2026-08-08T11:51:11.367432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.017476Z digest=sha256:77cbc0730a143635bd31e1318d902ec4bcb898d17bfd12cc80a5e2e31c0c1f4a

Observation 06292aff-f686-4025-9956-db01956e5d61 · outbound

This paper cites Understanding the difficulty of training deep feedfor- ward neural networks.

HRP: High-Rank Preheating for Superior LoRA Initialization Understanding the difficulty of training deep feedfor- ward neural networks

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.026624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.026624Z digest=sha256:fd1032d82cdf6489168abb7a296985ec2cabc3fbcf62a0b615da4adff67c00fa

Observation 50844b88-a383-412c-8985-949153816344 · outbound

This paper cites The Llama 3 Herd of Models.

HRP: High-Rank Preheating for Superior LoRA Initialization The Llama 3 Herd of Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.039299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.039299Z digest=sha256:5b595865421e6c61cbfbcc7f68c8278bec36702c46a494d0d73094fd64b8a554

Observation 8df582e0-ed47-4ba1-9433-599bbb0e72c0 · outbound

This paper cites The Impact of Initialization on LoRA Finetuning Dynamics.

HRP: High-Rank Preheating for Superior LoRA Initialization The Impact of Initialization on LoRA Finetuning Dynamics

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.047333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.047333Z digest=sha256:5d993b5b85888c781e73309c522eb277c97f25f698e62049f649ab47c7099e4e

Observation 134b7460-80df-43db-9627-e5bb8e90c354 · outbound

This paper cites LoRA+: Efficient Low Rank Adaptation of Large Models.

HRP: High-Rank Preheating for Superior LoRA Initialization LoRA+: Efficient Low Rank Adaptation of Large Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.059236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.059236Z digest=sha256:cb0d6e66a5d5094281d833e99486bf7e02e5e28987d55ae3da90c0b786f84db9

Observation 851492bc-9bc1-415e-ac5d-8847100c14a0 · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.

HRP: High-Rank Preheating for Superior LoRA Initialization Delving deep into rectifiers: Surpassing human-level performance on imagenet classification

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.066550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.066550Z digest=sha256:c5add8d8e9bffafc9feff48584c1da5853f0496878f12e38b19f4f1dc2cc1a8c

Observation c2c1008d-715d-4844-a503-398cc5e761c5 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

HRP: High-Rank Preheating for Superior LoRA Initialization Measuring Mathematical Problem Solving With the MATH Dataset

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.073244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.073244Z digest=sha256:98342e4a50c5724aae57920a376068acf5788c20ea56f3c4d3c7e7c93b7f526d

Observation d2c02794-18ff-43d1-8609-03e38786fd08 · outbound

This paper cites The gronwall inequality.

HRP: High-Rank Preheating for Superior LoRA Initialization The gronwall inequality

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.839190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.080289Z digest=sha256:53de3e98fc5504f8d0edfca1a3a24087e4ea792c143ef79700438a82b133b685

Observation 391a5a18-0db7-4416-9f98-f9391fb8e0c5 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

HRP: High-Rank Preheating for Superior LoRA Initialization LoRA: Low-Rank Adaptation of Large Language Models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.089374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.089374Z digest=sha256:e4a788d838dd4cb29abef83b7e7ae5cd86db1b0506874b3425637e8ce7d9d09a

Observation a41f7d7b-7040-44d1-9484-7601dfe22f2f · outbound

This paper cites Enhancing Adversarial Robustness of Vision-Language Models through Low-Rank Adaptation.

HRP: High-Rank Preheating for Superior LoRA Initialization Enhancing Adversarial Robustness of Vision-Language Models through Low-Rank Adaptation

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.097799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.097799Z digest=sha256:4fafc0de515cdc179965ee8a1e31528c5f5f97a24591f8fb617ef7482d114e6f

Observation fc812965-49fe-42ae-88c5-fb51f43a0586 · outbound

This paper cites A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA.

HRP: High-Rank Preheating for Superior LoRA Initialization A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.106714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.106714Z digest=sha256:9e309035454951ad13c2521a0eb2fe89a28817392b628b87e13a1de85ac98b34

Observation 5e036f4b-1cc4-42b9-a915-efbefba94605 · outbound

This paper cites VeRA: Vector-based Random Matrix Adaptation.

HRP: High-Rank Preheating for Superior LoRA Initialization VeRA: Vector-based Random Matrix Adaptation

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.127136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.127136Z digest=sha256:ad7cc0c0f09e00120f1d1c09c4abf87486572a2ac05b222e4cbade84aaefc8b5

Observation 07bebc56-6a0d-4ce1-a516-e22093423f1c · outbound

This paper cites Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution.

HRP: High-Rank Preheating for Superior LoRA Initialization Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.133982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.133982Z digest=sha256:cecb449476713da059f03f334fa9da75ed58540aea41b6634df5ed9c67671149

Observation 9e07cd81-3687-4bd8-8c4b-746f0309813f · outbound

This paper cites On the Crucial Role of Initialization for Matrix Factorization.

HRP: High-Rank Preheating for Superior LoRA Initialization On the Crucial Role of Initialization for Matrix Factorization

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.141504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.141504Z digest=sha256:cf30fa1565a9e0e403c1f05de597f8b07eb5aa0d6e9d0c7859b932ce1a485055

Observation 3e5d7fcc-a844-421e-bda2-36a11b4a59ce · outbound

This paper cites Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning.

HRP: High-Rank Preheating for Superior LoRA Initialization Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.151103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.151103Z digest=sha256:f93ac948a71c3cf4568b72c40acd822215130bddb335dbfafca884333913c012

Observation 2d9558d8-70f7-4622-88cb-96ab2b9e6fbe · outbound

This paper cites DoRA: Weight-Decomposed Low-Rank Adaptation.

HRP: High-Rank Preheating for Superior LoRA Initialization DoRA: Weight-Decomposed Low-Rank Adaptation

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.158578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.158578Z digest=sha256:fc96bf1baadcd032800c150e94fa128f1f51a499e3a8f84142f10d002976e9fd

Observation c8bf0e7c-cf1b-46ba-a3b8-fb4cb8f702ab · outbound

This paper cites Decoupled weight decay regularization, 2019.

HRP: High-Rank Preheating for Superior LoRA Initialization Decoupled weight decay regularization, 2019

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.169443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.169443Z digest=sha256:8a87a86856fdecd64628dff0750b7f7a2608328bd5ebd2f0a00767d36f0dab1d

Observation 89aabb06-e1ac-4319-82fa-7989181a9b0c · outbound

This paper cites Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation.

HRP: High-Rank Preheating for Superior LoRA Initialization Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.182586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.182586Z digest=sha256:c13739763ce9b5ebf6fa06141d1b691a5fda3547c49f7900408661750ec66d63

Observation 9a49474e-1d39-4312-be70-7f9993f53e3c · outbound

This paper cites A survey on lora of large language models.

HRP: High-Rank Preheating for Superior LoRA Initialization A survey on lora of large language models

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.799786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.191445Z digest=sha256:773a6767293930e0fa2209b11f74d701a632fee33742bd2abed273b65e623ca1

Observation 21fb92ca-c8e9-4d03-b369-e30ca3d555af · outbound

This paper cites PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models.

HRP: High-Rank Preheating for Superior LoRA Initialization PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.201271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.201271Z digest=sha256:61049620e0c8044b0780437ba42cd164cf1b167c5ee02b9c40441150a59ebd71

Observation 06b7100f-60e7-4fc7-bd24-eb7bc1d4548f · outbound

This paper cites On the explicit role of initialization on the convergence and implicit bias of overparametrized linear networks.

HRP: High-Rank Preheating for Superior LoRA Initialization On the explicit role of initialization on the convergence and implicit bias of overparametrized linear networks

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.780155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.210611Z digest=sha256:0ae83f23cc509b2700d817ae56f075e866272199912fea284fc8864617570ee4

Observation f88975d3-78c1-46a6-8658-9253fa0d5b5a · outbound

This paper cites All you need is a good init.

HRP: High-Rank Preheating for Superior LoRA Initialization All you need is a good init

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.218992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.218992Z digest=sha256:ba4f6fc4187d443016d6131358104d77fe52f72258985c983a946e806d4022b9

Observation c2d13bcb-0cae-4416-8e14-eaf8f0a48f83 · outbound

This paper cites Global convergence and stability of stochastic gradient descent.

HRP: High-Rank Preheating for Superior LoRA Initialization Global convergence and stability of stochastic gradient descent

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.764250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.228381Z digest=sha256:52a710ac45cfce382816a4f69e7b5dee589df1471df99f4c0e52a2e9294dcda5

Observation 53eb7a48-0809-41aa-9a9d-3f48faabb5b5 · outbound

This paper cites Initialization using update approximation is a silver bullet for extremely efficient low-rank fine-tuning.

HRP: High-Rank Preheating for Superior LoRA Initialization Initialization using update approximation is a silver bullet for extremely efficient low-rank fine-tuning

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.237689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.237689Z digest=sha256:9cbf4d777462783f5ad40d24b658f09b715c694050129a02f78f5a853bd6792b

Observation 73072fbe-8237-491c-8429-5c6a14701dcd · outbound

This paper cites an unresolved cited work.

HRP: High-Rank Preheating for Superior LoRA Initialization Unresolved cited work

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.244933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.244933Z digest=sha256:d9514ae684e29c2b183f64d0d62f0aa9ce71d6d488ecee0394f2e151b9a4aff8

Observation 1cd322c7-f24f-4f1e-82c3-9220f1f8caaf · outbound

This paper cites Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying.

HRP: High-Rank Preheating for Superior LoRA Initialization Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.259651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.259651Z digest=sha256:f45595df4729196fe1169a2cfc6adaa0d1c4b0e070f0e4bd239b38427b842378

Observation e6857a70-32f6-4768-9ff3-482cbf80d310 · outbound

This paper cites Exact solutions to the nonlinear dynamics of learning in deep linear neural networks.

HRP: High-Rank Preheating for Superior LoRA Initialization Exact solutions to the nonlinear dynamics of learning in deep linear neural networks

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.272377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.272377Z digest=sha256:a846a8c28dda23815f09880f89e3715dd3d10e607fd108eb38f900e82dcd586e

Observation e0bfd0a2-3432-46db-bbdb-d24c886570ae · outbound

This paper cites ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation.

HRP: High-Rank Preheating for Superior LoRA Initialization ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation

Reference 39

Resolution
verified exact
local_arxiv, observed 2026-08-08T11:51:10.783356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.285417Z digest=sha256:d555312d4c66ccd7a2bb5aba4593d0d93579cf4e5c290f09df0d596370cb6b2c

Observation 47cfa5de-1d89-48ba-8830-5eb1b12a2bc6 · outbound

This paper cites Understanding the dynamics of gradient flow in overparameterized linear models.

HRP: High-Rank Preheating for Superior LoRA Initialization Understanding the dynamics of gradient flow in overparameterized linear models

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.738000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.292761Z digest=sha256:3c88f7c205df0bb20b50d00e21084d546e0bf55ef51df2b8696616ec86ac5103

Observation aece3599-8be2-48a2-8c8c-d90ce4ea84ac · outbound

This paper cites Gemma, 2024.

HRP: High-Rank Preheating for Superior LoRA Initialization Gemma, 2024

Reference 41

Resolution
parse uncertain
no resolver link, observed 2026-08-08T11:51:10.298966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.298966Z digest=sha256:daf10c5c0a7fd56e27e8ef5251f30dc707521351d569a81e4e3a4dff4f97b82b

Observation 46e47c93-22b0-4933-8e0e-03718129a6d2 · outbound

This paper cites Qwen3, April 2025.

HRP: High-Rank Preheating for Superior LoRA Initialization Qwen3, April 2025

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.706555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.306585Z digest=sha256:8b8f7193651bd41f0de6e9f8c02f9451ae3856dc6db15a24f78e3f6f58508129

Observation 605b1842-b3cd-438b-b301-2aeb51d8ab32 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

HRP: High-Rank Preheating for Superior LoRA Initialization Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.314277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.314277Z digest=sha256:8642b0270868c56ec8b61e737186ca28b75a6f29a58d3d36560218b0d6fbab89

Observation 910fe790-be67-4c51-a11d-2a325a3eaa25 · outbound

This paper cites RSVDPACK: An implementation of randomized algorithms for computing the singular value, interpolative, and CUR decompositions of matrices on multi-core and GPU architectures.

HRP: High-Rank Preheating for Superior LoRA Initialization RSVDPACK: An implementation of randomized algorithms for computing the singular value, interpolative, and CUR decompositions of matrices on multi-core and GPU architectures

Reference 44

Resolution
verified exact
local_arxiv, observed 2026-08-08T11:51:10.737815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.327030Z digest=sha256:6505a263a84258d86c2e4cd002b5cc4aaa9ecc591b4df6feb2f82c6c75ebee46

Observation 69f927ee-778f-4ee1-8fb2-f988c66b1cb6 · outbound

This paper cites GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.

HRP: High-Rank Preheating for Superior LoRA Initialization GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.336035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.336035Z digest=sha256:3ccbd1f2f579c6be46d95a5e03364c1d3733a81fc8c2fdb24a533762bf6beb29

Observation 70d69d17-4c1b-4d6f-bd02-2a9155093fbb · outbound

This paper cites Pufferfish: Communication- efficient models at no extra cost.

HRP: High-Rank Preheating for Superior LoRA Initialization Pufferfish: Communication- efficient models at no extra cost

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.689185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.344163Z digest=sha256:3ed48c9f445514a90a9409e401dda58badfa2f7c23af945062d73296793fb805

Observation 92cd651b-c34c-4aeb-946f-19324625ff71 · outbound

This paper cites Cuttlefish: Low-rank model training without all the tuning.

HRP: High-Rank Preheating for Superior LoRA Initialization Cuttlefish: Low-rank model training without all the tuning

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.670340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.350927Z digest=sha256:b3af936f3c451c30be418517759a6f61343c0c315547728495f26f97d80d202b

Observation 16c7bea6-2db8-42e7-8c08-7b110304cfd2 · outbound

This paper cites LoRA-GA: Low-Rank Adaptation with Gradient Approximation.

HRP: High-Rank Preheating for Superior LoRA Initialization LoRA-GA: Low-Rank Adaptation with Gradient Approximation

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.356322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.356322Z digest=sha256:2f59bf746392f9ece6a6bba668189112ba3f807f11d15468c3222f8a1b6e1fde

Observation 6ba59ee3-fbbb-4d8e-9613-eca5e0f47e52 · outbound

This paper cites Implicit Regularization Makes Overparameterized Asymmetric Matrix Sensing Robust to Perturbations.

HRP: High-Rank Preheating for Superior LoRA Initialization Implicit Regularization Makes Overparameterized Asymmetric Matrix Sensing Robust to Perturbations

Reference 49

Resolution
verified exact
local_arxiv, observed 2026-08-08T11:51:10.670710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.361596Z digest=sha256:b89868470d1efbf4809a04b8b8ed3767cd077d34b3c6b38619c80610355c655e

Observation 4d2440e1-5467-40fe-a287-2a3902ad38b2 · outbound

This paper cites Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning.

HRP: High-Rank Preheating for Superior LoRA Initialization Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.367578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.367578Z digest=sha256:382ee344addcd077beff70134277b080a3177e3e2781cf5d78874ac672e4f291

Observation e22cd51e-d268-492c-94dd-c342b7f3b830 · outbound

This paper cites Towards theoretically inspired neural initialization optimization.

HRP: High-Rank Preheating for Superior LoRA Initialization Towards theoretically inspired neural initialization optimization

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.654365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.373841Z digest=sha256:657a9794272414c96dc3e8bc7b3531472bb888934f35db788cce444d7be00330

Observation 4b5debd4-1245-4c42-9332-da9fb09804c8 · outbound

This paper cites Global convergence of gradient descent for asymmetric low-rank matrix factorization.

HRP: High-Rank Preheating for Superior LoRA Initialization Global convergence of gradient descent for asymmetric low-rank matrix factorization

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.636740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.380158Z digest=sha256:70eb7a1d0282f7a848b510bd725da0727c9f0cf65f038d9febfd7ad6319c4df5

Observation 78c3e74a-8cac-4703-a39b-3ee0c80e60a6 · outbound

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

HRP: High-Rank Preheating for Superior LoRA Initialization MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.387445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.387445Z digest=sha256:6ef9a3b9f9dde7eba15778880dbad7a412787e22576e237bc3e9ef59178bfa77

Observation ecc18705-64e5-405e-b2f4-86c2f65579a2 · outbound

This paper cites The Expressive Power of Low-Rank Adaptation.

HRP: High-Rank Preheating for Superior LoRA Initialization The Expressive Power of Low-Rank Adaptation

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.397272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.397272Z digest=sha256:536de71cf5d3379b957d22cbd79a3f40a97e427595e8e01b8e27eadf093aac7e

Observation 5757111b-d92f-4edb-bf8e-3df4cc52fd73 · outbound

This paper cites AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning.

HRP: High-Rank Preheating for Superior LoRA Initialization AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.406460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.406460Z digest=sha256:4756beefd45079f2d16055e347e378dae3ae07d31b3767f21e8826b6e85112b9

Observation 41f64ce0-11a0-45e9-8d5a-32f7248d4bc7 · outbound

This paper cites Gradinit: Learning to initialize neural networks for stable and efficient training.

HRP: High-Rank Preheating for Superior LoRA Initialization Gradinit: Learning to initialize neural networks for stable and efficient training

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.413134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.413134Z digest=sha256:964258c99e76fdb6ba38ab37766b586e2c1f6d720eabf847fbc73b54ea6c59d9

Observation b2e6ad81-fa2c-45ab-a33c-de9b21d48279 · outbound

This paper cites Asymmetry in Low-Rank Adapters of Foundation Models.

HRP: High-Rank Preheating for Superior LoRA Initialization Asymmetry in Low-Rank Adapters of Foundation Models

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-08T11:51:10.421410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:51:10.421410Z digest=sha256:833b8804dac3beb0658da4b3337f14655d6d67a41f31079aff9100436f22b2fc

Observation 1e53aac3-b5e1-4557-b4bc-ae6ee6a44433 · outbound

This paper cites an unresolved cited work.

HRP: High-Rank Preheating for Superior LoRA Initialization Unresolved cited work

Reference 58

Resolution
unresolved
raw_fallback, observed 2026-08-08T11:51:11.603534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.429022Z digest=sha256:efce5a1c9e0ba7fe622711a262d1e1df118950f2e1da582b4d69e2edf6bbff1d

Observation 131178c3-9cca-4d28-836a-90e9ce0af0e3 · outbound

This paper cites an unresolved cited work.

HRP: High-Rank Preheating for Superior LoRA Initialization Unresolved cited work

Reference 59

Resolution
unresolved
raw_fallback, observed 2026-08-08T11:51:11.584401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.435196Z digest=sha256:4c9680abc9375c643cca03d0f6eb9df7e752bb3f367ad16caa0c679dd6fc499e

Observation 262c365c-d727-4536-b9ea-61b17775ad5c · outbound

This paper cites an unresolved cited work.

HRP: High-Rank Preheating for Superior LoRA Initialization Unresolved cited work

Reference 60

Resolution
unresolved
raw_fallback, observed 2026-08-08T11:51:11.565162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.441859Z digest=sha256:c47d612f94d217115ef70f2af4ec3c6493f31a024c4ad70f465ad93c0f60877d

Observation 55955c17-825e-4802-9410-c4b1071fafd8 · outbound

This paper cites an unresolved cited work.

HRP: High-Rank Preheating for Superior LoRA Initialization Unresolved cited work

Reference 61

Resolution
unresolved
raw_fallback, observed 2026-08-08T11:51:11.546646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.449915Z digest=sha256:1afddb25158220f243570d37b42754a488628acd6376861d42188140db10d790

Observation f485d9bc-e6d3-4c50-b59a-beb6fc29c47c · outbound

This paper cites tilde” variables as those from Asymmetric LoRA, while the without “tilde.

HRP: High-Rank Preheating for Superior LoRA Initialization tilde” variables as those from Asymmetric LoRA, while the without “tilde

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:51:11.529347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-08-08T11:51:10.457246Z digest=sha256:0b2c92580c9d13e8c6375ea27cc63a5d3a8a18daee36fa92d6a20569a6125fa6

Pith citing papers

No inbound Pith citation observations are available.