Paper Citation Record · LEDGER

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs

As of 13 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 1 inbound Pith citation observation for arXiv:2607.10803.

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

pith.paper-citation-record.v1
2607.10803 v1

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-14T09:09:29.470093Z

measured 67 of 67 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T07:54:47.781434Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

66 of 66 outbound references displayed

verified exact0
verified fuzzy0
unresolved66
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation acbff4c0-f61e-45bd-8141-9a8ae7ec292a · outbound

This paper cites Memory Aware Synapses: Learning What (not) to Forget.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Memory Aware Synapses: Learning What (not) to Forget

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 937190fa-5f95-4310-913a-cd7e648a6429 · outbound

This paper cites Systematic Outliers in Large Language Models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Systematic Outliers in Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1427567c-07df-4445-bf22-1ef01d7b17dd · outbound

This paper cites LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd290a39-4b23-4974-acea-41660138cd5f · outbound

This paper cites Layer Normalization.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Layer Normalization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c371f5f-9e12-4294-9cb3-3e04ba5f8c50 · outbound

This paper cites Exposing the Illusion of Erasure in Knowledge Editing for LLMs.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Exposing the Illusion of Erasure in Knowledge Editing for LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e84134f6-beae-42e4-868e-d2f00547f4a8 · outbound

This paper cites Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71e9ce2b-d8fc-491a-af0d-9bad6243e772 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Evaluating Large Language Models Trained on Code

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79cd675a-0068-45a0-811f-3a5d4c27d548 · outbound

This paper cites Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5f8dc71-1fdd-4e75-9c26-aa491adeee6c · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Training Verifiers to Solve Math Word Problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 252e2b41-cd3d-4333-a40b-2b6f525b233d · outbound

This paper cites Evaluating the Ripple Effects of Knowledge Editing in Language Models.Transactions of the Association for Computational Linguistics, 2024.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Evaluating the Ripple Effects of Knowledge Editing in Language Models.Transactions of the Association for Computational Linguistics, 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb370e07-eb6e-4fbb-b140-635260e71c46 · outbound

This paper cites Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbd8cb77-bd5f-4b3e-b5fa-ecc3cd2ccbd3 · outbound

This paper cites Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d622269a-8ac5-4048-a131-06684e64518a · outbound

This paper cites Sharp Minima Can Generalize For Deep Nets.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Sharp Minima Can Generalize For Deep Nets

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 930413c4-f1cc-444c-a355-e2e7bf8516a7 · outbound

This paper cites Dolan and Chris Brockett.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Dolan and Chris Brockett

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8170ba8-a3cf-4660-ae68-63ce9d7b66b4 · outbound

This paper cites A Primer on the Inner Workings of Transformer-based Language Models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs A Primer on the Inner Workings of Transformer-based Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac3bcfe5-4192-4de7-b603-0f4c67207ddd · outbound

This paper cites Sharpness-Aware Minimization for Efficiently Improving Generalization.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Sharpness-Aware Minimization for Efficiently Improving Generalization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a7b82fc-0aaa-416a-a82b-52a17c39baba · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pretrained Transformers.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs GPTQ: Accurate Post-Training Quantization for Generative Pretrained Transformers

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1d96ac6-3ecc-4878-ae7c-46e5d24722a8 · outbound

This paper cites The State of Sparsity in Deep Neural Networks.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs The State of Sparsity in Deep Neural Networks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c924bf0-e685-4409-99c3-6b889108c494 · outbound

This paper cites an unresolved cited work.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e0edd43-9172-4bdf-9a35-44ac8b8ef3c0 · outbound

This paper cites The Language Model Evaluation Harness, 2024.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs The Language Model Evaluation Harness, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0738d2cc-5c7d-49a6-983f-ea5dc5c26e96 · outbound

This paper cites Defying Catastrophic Forgetting via Influence Function.Artificial Intelligence, 2025.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Defying Catastrophic Forgetting via Influence Function.Artificial Intelligence, 2025

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71cfe44-5cd6-4e50-96ee-4c8db55df961 · outbound

This paper cites OLMES: A Standard for Language Model Evaluations.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs OLMES: A Standard for Language Model Evaluations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b631f53b-9efa-44dd-b28d-58e3a35a5d63 · outbound

This paper cites Rebuilding ROME: Resolving Model Collapse during Sequential Model Editing.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Rebuilding ROME: Resolving Model Collapse during Sequential Model Editing

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5380c239-e041-4428-8ec0-7374f44ed928 · outbound

This paper cites Learning both Weights and Connections for Efficient Neural Networks.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Learning both Weights and Connections for Efficient Neural Networks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3678281-ca44-4cdf-9388-4f7f0198ae5f · outbound

This paper cites an unresolved cited work.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97ef87ea-8b52-4af4-b60b-e0f55530affc · outbound

This paper cites Aging with Grace: Lifelong Model Editing with Discrete K-Value Adaptors.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Aging with Grace: Lifelong Model Editing with Discrete K-Value Adaptors

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aedce6b-2d06-4de8-b13f-a5fb1aef84ca · outbound

This paper cites an unresolved cited work.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 196f2282-f878-4d92-9826-a24bad7365d1 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Training Compute-Optimal Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50116817-4fae-4b81-bce6-6c4fd2a6e894 · outbound

This paper cites SliM-LLM: Salience-driven mixed-precision quantization for large language models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs SliM-LLM: Salience-driven mixed-precision quantization for large language models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4afbe4e-b649-43dc-8974-94d876ad3061 · outbound

This paper cites Scaling Laws for Neural Language Models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Scaling Laws for Neural Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef36aa31-3510-4b98-ba60-4ddfee6cd1c3 · outbound

This paper cites Overcoming Catastrophic Forgetting in Neural Networks.Proceedings of the National Academy of Sciences, 2017.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Overcoming Catastrophic Forgetting in Neural Networks.Proceedings of the National Academy of Sciences, 2017

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eade333b-9249-4147-b478-747ce9100b86 · outbound

This paper cites Denker, and Sara A.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Denker, and Sara A

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26a3fa4f-8a09-46f5-b37b-35ed0f389431 · outbound

This paper cites an unresolved cited work.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be4623e2-8e84-4947-b205-793fb71aafb5 · outbound

This paper cites Zero-Shot Relation Extraction via Reading Comprehension.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Zero-Shot Relation Extraction via Reading Comprehension

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b81cb7db-62ec-4657-a099-0a5bb21833f0 · outbound

This paper cites Continual Learning and Private Unlearning.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Continual Learning and Private Unlearning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 024dff74-4e16-4540-ba45-76caab260444 · outbound

This paper cites Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5d9a914-f2c7-411a-885f-654eba36eb71 · outbound

This paper cites Mahoney, and Yaoqing Yang.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Mahoney, and Yaoqing Yang

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e693639c-0aee-4f2e-8534-26c2a243b526 · outbound

This paper cites Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad451a59-0f68-4216-a082-4286ceba4f05 · outbound

This paper cites Zico Kolter.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Zico Kolter

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c02d38b-3390-45dd-b8bf-26a37fece954 · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Locating and Editing Factual Associations in GPT

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 600408dc-0802-4a60-be87-3076035fd086 · outbound

This paper cites Large Language Models: A Survey.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Large Language Models: A Survey

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fadac09-1258-4ba5-ad46-703f312f547e · outbound

This paper cites Pruning Convolutional Neural Networks for Resource Efficient Inference.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Pruning Convolutional Neural Networks for Resource Efficient Inference

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b07c52f8-abb8-471b-ab1e-44728ab1e25a · outbound

This paper cites Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee002291-73f3-4dcb-865e-bc549d59d9fa · outbound

This paper cites GPT-4 Technical Report.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs GPT-4 Technical Report

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1119230-e1f2-43be-a94a-05b9a980f4fe · outbound

This paper cites AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba7d629d-937a-4fa4-ac80-c569bd5bff51 · outbound

This paper cites How Many Parameters Does Your Task Really Need? Task Specific Pruning with LLM-Sieve.arXiv preprint arXiv:2505.18350, 2025.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs How Many Parameters Does Your Task Really Need? Task Specific Pruning with LLM-Sieve.arXiv preprint arXiv:2505.18350, 2025

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cba4075-eed7-4f01-b5bf-731fa440d9ba · outbound

This paper cites PB-LLM: Partially binarized large language models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs PB-LLM: Partially binarized large language models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6a3e49b-c22d-45c6-8fbf-fa11eef1c80c · outbound

This paper cites Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29b67a78-bf47-417d-8102-85d3dbb4ede8 · outbound

This paper cites The Curse of Recursion: Training on Generated Data Makes Models Forget.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs The Curse of Recursion: Training on Generated Data Makes Models Forget

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16a5bc28-4057-43b6-a5c0-2d4cd7ab1015 · outbound

This paper cites Zico Kolter.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Zico Kolter

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d8a29d5-d406-431f-8ef6-470666ae5ecf · outbound

This paper cites Optimal Brain Apoptosis.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Optimal Brain Apoptosis

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 392d3533-5598-42cf-be26-f21a7c8065be · outbound

This paper cites Gemma 3 Technical Report.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Gemma 3 Technical Report

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76995ef8-2f68-44be-8ec1-cf610335c67f · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs LLaMA: Open and Efficient Foundation Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c46f2f-e68e-4c7f-85cb-2b6e1995b8fd · outbound

This paper cites First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e95365c-4dd8-41b5-8aa5-bb6895b37487 · outbound

This paper cites an unresolved cited work.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c78896ad-c058-429b-8b38-12f18b0a66da · outbound

This paper cites Why Language Models Collapse when Trained on Recursively Generated Text.arXiv preprint arXiv:2412, 2024.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Why Language Models Collapse when Trained on Recursively Generated Text.arXiv preprint arXiv:2412, 2024

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26f310bf-5224-47a1-93d6-ca022cef8166 · outbound

This paper cites EasyEdit: An Easy-to-Use Knowledge Editing Framework for Large Language Models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs EasyEdit: An Easy-to-Use Knowledge Editing Framework for Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff225daf-f6d0-48b1-a266-1af6e4bf2b09 · outbound

This paper cites Qwen3 Technical Report.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Qwen3 Technical Report

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c408f8-f367-453b-9b08-9f4ed3d0e657 · outbound

This paper cites Kübler, Rupak Vignesh Swaminathan, Athanasios Mouchtaris, Sravan Babu Bodapati, et al.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Kübler, Rupak Vignesh Swaminathan, Athanasios Mouchtaris, Sravan Babu Bodapati, et al

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1154b6f-946d-488a-93be-17cbceb4ff80 · outbound

This paper cites Editing Large Language Models: Problems, Methods, and Opportunities.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Editing Large Language Models: Problems, Methods, and Opportunities

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2aaa2076-b158-4ec2-8df1-1f917c5d4554 · outbound

This paper cites Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df09822d-f87f-4087-9165-2454837673a1 · outbound

This paper cites Continual Learning Through Synaptic Intelligence.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Continual Learning Through Synaptic Intelligence

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c05dccb6-4bfb-400d-9d01-6eca85b0a92d · outbound

This paper cites Boosting Large Language Models with Mask Fine-Tuning.arXiv preprint arXiv:2503.22764, 2025.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Boosting Large Language Models with Mask Fine-Tuning.arXiv preprint arXiv:2503.22764, 2025

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68f0f5a-3aba-4b30-95c1-39f855fc7ba4 · outbound

This paper cites A Comprehensive Study of Knowledge Editing for Large Language Models.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs A Comprehensive Study of Knowledge Editing for Large Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1644d03-58e1-4e80-bf75-d5b30cd052ca · outbound

This paper cites SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale.arXiv preprint arXiv:2512.10922, 2025.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale.arXiv preprint arXiv:2512.10922, 2025

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e610d93c-4d6f-4776-b6bf-69e1100cb007 · outbound

This paper cites an unresolved cited work.

Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs Unresolved cited work

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-14T09:09:29.470093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d69bab3d-e5ee-4fe5-9909-76139a27b499 · inbound

Reference Traces for Auditing Invisible Weight Updates and Guiding Exact-Budget Protection cites this paper.

Reference Traces for Auditing Invisible Weight Updates and Guiding Exact-Budget Protection Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-02T07:54:47.781434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.