Paper Citation Record · LEDGER

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning

As of 9 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2601.04710.

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

pith.paper-citation-record.v1
2601.04710 v2

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T12:03:29.855120Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

45 of 45 outbound references displayed

verified exact0
verified fuzzy0
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8bc418db-0987-4213-b43e-509f1c8cfa1e · outbound

This paper cites Language models are few-shot learners,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Language models are few-shot learners,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:23.576295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 696ba634-0f5a-4d13-9be6-3f2fceb5edf7 · outbound

This paper cites Gpt-4 technical report,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Gpt-4 technical report,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:23.701919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d33d36c0-f368-4953-aa5c-4f176d24b834 · outbound

This paper cites Learning represen- tations by back-propagating errors,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Learning represen- tations by back-propagating errors,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:23.869659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8d04519-89f3-40fc-bb94-ae4be3d26745 · outbound

This paper cites LoRA: Low-rank adaptation of large language models,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning LoRA: Low-rank adaptation of large language models,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:23.967612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67093e2c-8266-4998-854a-a30b1d8540d5 · outbound

This paper cites Parameter-efficient transfer learning for NLP,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Parameter-efficient transfer learning for NLP,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:24.145588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae92a206-f088-4086-978a-e7b97c424e1c · outbound

This paper cites Prefix-tuning: Optimizing continuous prompts for generation,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Prefix-tuning: Optimizing continuous prompts for generation,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:24.316834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba402227-bb18-4163-9a4b-0c628bff9e78 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning OPT: Open Pre-trained Transformer Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:24.487626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46aac17f-f4e4-4aa1-b4e5-58ece3de79b7 · outbound

This paper cites Fine-tuning language models with just forward passes,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Fine-tuning language models with just forward passes,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:24.665069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2906712c-4349-4afb-b3f8-800a2410b007 · outbound

This paper cites Sparse mezo: Less parameters for better performance in eroth-order llm fine- tuning,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Sparse mezo: Less parameters for better performance in eroth-order llm fine- tuning,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:24.867629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4d38d21-802d-4667-9c0a-76a3c69c5ea2 · outbound

This paper cites Zeroth-order fine-tuning of LLMs with extreme sparsity,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Zeroth-order fine-tuning of LLMs with extreme sparsity,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:24.993744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7309bff-d0ec-4792-9861-15c047fb8e2d · outbound

This paper cites Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:25.119547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e35bc05-9a69-4ba5-b518-511e6b25e5bc · outbound

This paper cites AdaZeta: Adaptive zeroth-order tensor-train adaption for memory- efficient large language models fine-tuning,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning AdaZeta: Adaptive zeroth-order tensor-train adaption for memory- efficient large language models fine-tuning,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:25.263870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d4a2c37-f464-408f-9364-7f5a1a219d59 · outbound

This paper cites Multivariate stochastic approximation using a simultaneous perturbation gradient approximation,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Multivariate stochastic approximation using a simultaneous perturbation gradient approximation,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:25.397365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a44133d8-de06-4cc2-9d46-4785b661356f · outbound

This paper cites Completely derandomized self- adaptation in evolution strategies,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Completely derandomized self- adaptation in evolution strategies,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:25.522758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61b9ca1d-36b1-42db-98c2-6a4341b0f1e0 · outbound

This paper cites Black-box tuning for language-model-as-a-service,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Black-box tuning for language-model-as-a-service,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:25.716331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed2f91a0-8344-422a-9646-ecbd8dc6be7c · outbound

This paper cites BBTv2: Towards a gradient-free future with large language models,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning BBTv2: Towards a gradient-free future with large language models,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:25.888334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2830cba-177a-4f66-81b7-65ebba365443 · outbound

This paper cites Derivative-free optimization for low-rank adaptation in large language models,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Derivative-free optimization for low-rank adaptation in large language models,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:26.014227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d326a68-20bb-44e4-b59a-0e462889b87f · outbound

This paper cites ZeRO-Offload: Democratizing Billion-Scale Model Training.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning ZeRO-Offload: Democratizing Billion-Scale Model Training

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:26.187156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73f91e4e-3624-4c19-ab60-c319fa7219c1 · outbound

This paper cites Bpipe: Memory-balanced pipeline parallelism for training large language models,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Bpipe: Memory-balanced pipeline parallelism for training large language models,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:26.305970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 896a477e-4aca-4b48-9fdb-9bf1717064c7 · outbound

This paper cites Deepzero: Scaling up zeroth- order optimization for deep model training,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Deepzero: Scaling up zeroth- order optimization for deep model training,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:26.399307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3527265-8822-48ce-831b-999f566a6af5 · outbound

This paper cites Distributed zero-order algorithms for nonconvex multiagent optimization,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Distributed zero-order algorithms for nonconvex multiagent optimization,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:26.513343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7c96db9-373c-48bd-9421-26a9105925f9 · outbound

This paper cites A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:26.677740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c1a4bd9-e06e-4f37-83bc-626209b86c01 · outbound

This paper cites signsgd via zeroth-order oracle,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning signsgd via zeroth-order oracle,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:26.813019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf3eeccb-650d-4691-a66f-711753fb82f1 · outbound

This paper cites Gradientless descent: High-dimensional zeroth-order optimization,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Gradientless descent: High-dimensional zeroth-order optimization,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:26.956125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd711158-2af0-4374-870b-0eebc6e45b89 · outbound

This paper cites Simple random search of static linear policies is competitive for reinforcement learning,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Simple random search of static linear policies is competitive for reinforcement learning,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:27.087220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78c3204b-ec1a-456c-b6f8-1c50300a415e · outbound

This paper cites The Forward-Forward Algorithm: Some Preliminary Investigations.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning The Forward-Forward Algorithm: Some Preliminary Investigations

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:27.178394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5e657a4-ca73-4f1b-9d9b-c5a804fac06c · outbound

This paper cites Variance-reduced zeroth-order methods for fine-tuning language models,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Variance-reduced zeroth-order methods for fine-tuning language models,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:27.299542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08ca4452-2714-4049-b2a3-e2d06e9623e9 · outbound

This paper cites Revisiting zerothorder optimization for memory efficient llm fine-tuning: A benchmark,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Revisiting zerothorder optimization for memory efficient llm fine-tuning: A benchmark,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:27.501623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21f1afbd-021d-4acd-9e87-164fb2bfc519 · outbound

This paper cites Zo-adamu optimizer: Adapting perturbation by the momentum and uncertainty in zeroth order optimization,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Zo-adamu optimizer: Adapting perturbation by the momentum and uncertainty in zeroth order optimization,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:27.663867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0842c1f4-5674-48f7-a645-9ce510842efd · outbound

This paper cites Zeroth-Order Fine-Tuning of LLMs in Random Subspaces.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Zeroth-Order Fine-Tuning of LLMs in Random Subspaces

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:27.808098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e133883c-4883-4340-bab8-39cb29b82e3e · outbound

This paper cites Superglue: A stickier benchmark for generalpurpose language understanding systems,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Superglue: A stickier benchmark for generalpurpose language understanding systems,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:27.967476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e12b8003-e3a4-4306-b519-4c0dc69d3975 · outbound

This paper cites The commitment- bank: Investigating projection in naturally occurring discourse,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning The commitment- bank: Investigating projection in naturally occurring discourse,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:28.085186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c70c3bc6-6cbc-463c-aec7-769300cdce7e · outbound

This paper cites Choice of plausible alternatives: An evaluation of commonsense causal reasoning,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Choice of plausible alternatives: An evaluation of commonsense causal reasoning,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:28.212167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4411d07-4e20-4756-a356-51829a3c6b1a · outbound

This paper cites Looking beyond the surface: A challenge set for reading comprehen- sion over multiple sentences,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Looking beyond the surface: A challenge set for reading comprehen- sion over multiple sentences,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:28.330678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1068c54f-0488-48f8-a79d-5cd31b668a87 · outbound

This paper cites Benchmarking applied seman- tic inference: The PASCAL recognising textual entailment challenges,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Benchmarking applied seman- tic inference: The PASCAL recognising textual entailment challenges,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:28.508791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1118262-c3ff-4e62-8f2d-e61762201c6b · outbound

This paper cites WiC: the word-in-context dataset for evaluating context-sensitive meaning representations,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning WiC: the word-in-context dataset for evaluating context-sensitive meaning representations,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:28.657093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7322c0ac-dff2-4b8a-8767-3dbdae653b86 · outbound

This paper cites The winograd schema challenge,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning The winograd schema challenge,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:28.799032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e1bc26a-3874-4524-bcd1-656a9000f92d · outbound

This paper cites BoolQ: Exploring the surprising difficulty of natural yes/no questions,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning BoolQ: Exploring the surprising difficulty of natural yes/no questions,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:28.928444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c682244-44f9-4d3b-a008-32f97543207e · outbound

This paper cites ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:29.016881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e045f2a-1459-4c21-9fe8-abec9ed32d0a · outbound

This paper cites Recursive deep models for semantic compositionality over a sentiment treebank,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Recursive deep models for semantic compositionality over a sentiment treebank,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:29.140934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ad5f1d5-d8c1-418c-ab9e-1bab2a9658c9 · outbound

This paper cites SQuAD: 100,000+ questions for machine comprehension of text,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning SQuAD: 100,000+ questions for machine comprehension of text,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:29.269886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3577886-fb09-4580-b28c-0a33eae32e67 · outbound

This paper cites DROP: A reading comprehension benchmark requiring discrete reason- ing over paragraphs,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning DROP: A reading comprehension benchmark requiring discrete reason- ing over paragraphs,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:29.402276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad1b310-b187-4f8f-a30c-e12bbb12aedf · outbound

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

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:29.522036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b586d719-a031-437b-b2da-b0a42280ea3a · outbound

This paper cites Making pre-trained language models better few-shot learners,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Making pre-trained language models better few-shot learners,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:29.730924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e0f5b96-1ada-4443-a66c-f72a4f8501e0 · outbound

This paper cites Exploiting cloze-questions for few-shot text classification and natural language inference,.

Steering the Noise: Turning Random Perturbations into Effective Descent for Memory-Efficient LLM Fine-Tuning Exploiting cloze-questions for few-shot text classification and natural language inference,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T12:03:29.855120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.