Paper Citation Record · LEDGER

Post-Training Statistical Calibration for Higher Activation Sparsity

As of 15 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 3 inbound Pith citation observations for arXiv:2412.07174.

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

pith.paper-citation-record.v1
2412.07174 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T19:10:12.377428Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T09:15:32.395442Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T09:16:19.701023Z

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy8
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 280d328a-dc58-4e13-a3b5-aa1a30dc5311 · outbound

This paper cites ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models.

Post-Training Statistical Calibration for Higher Activation Sparsity ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.260196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b14fe271-994e-4c4a-ae18-d8aff161c048 · outbound

This paper cites LLM in a flash: Efficient Large Language Model Inference with Limited Memory.

Post-Training Statistical Calibration for Higher Activation Sparsity LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.264153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bfddecf-95b6-401d-b927-d0ba398bb673 · outbound

This paper cites The Falcon Series of Open Language Models.

Post-Training Statistical Calibration for Higher Activation Sparsity The Falcon Series of Open Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.268008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 741fa0cf-3356-4663-bde0-974a038ae995 · outbound

This paper cites an unresolved cited work.

Post-Training Statistical Calibration for Higher Activation Sparsity Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.271746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9bb9ded-0e67-41fb-b47a-b8d38ff12b29 · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

Post-Training Statistical Calibration for Higher Activation Sparsity PaLM: Scaling Language Modeling with Pathways

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.275572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81964990-eb6e-43de-9558-bb0a383b7bed · outbound

This paper cites Imagenet: A large- scale hierarchical image database.

Post-Training Statistical Calibration for Higher Activation Sparsity Imagenet: A large- scale hierarchical image database

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.279811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dda6c5f-b1af-48bb-83d1-fe773bd21e12 · outbound

This paper cites Lighteval: A lightweight framework for llm evaluation, 2023.

Post-Training Statistical Calibration for Higher Activation Sparsity Lighteval: A lightweight framework for llm evaluation, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.284338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4551c7b6-0d29-4b4a-98da-3cb1700cdaac · outbound

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

Post-Training Statistical Calibration for Higher Activation Sparsity GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.287699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c7da6ca-bfa4-457a-a5c5-3d027ec7d514 · outbound

This paper cites A framework for few-shot language model evaluation, 12 2023.

Post-Training Statistical Calibration for Higher Activation Sparsity A framework for few-shot language model evaluation, 12 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.291129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6067ffdc-672b-4dc0-99fb-f755b92b40e1 · outbound

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

Post-Training Statistical Calibration for Higher Activation Sparsity Learning both Weights and Connections for Efficient Neural Network

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:10:12.730667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 589ea3f2-8c77-4d3e-821d-8c556ed22efa · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Post-Training Statistical Calibration for Higher Activation Sparsity Gonzalez, Hao Zhang, and Ion Stoica

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.298674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b86ad54-ae76-4bc1-b3cf-e6a01e55f0b4 · outbound

This paper cites CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models.

Post-Training Statistical Calibration for Higher Activation Sparsity CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.302032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d80816d0-855f-4164-ba16-0401249383fc · outbound

This paper cites The Lazy Neuron Phenomenon: On Emergence Of Activation Sparsity In Transformers.

Post-Training Statistical Calibration for Higher Activation Sparsity The Lazy Neuron Phenomenon: On Emergence Of Activation Sparsity In Transformers

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:10:12.714141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e40f70d6-d7ae-4fa9-b141-9647ef6e383d · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

Post-Training Statistical Calibration for Higher Activation Sparsity AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.309454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a78cbcf-03e9-4a46-978a-5ae2c09a7981 · outbound

This paper cites Deja Vu: contextual sparsity for efficient LLMs at inference time.

Post-Training Statistical Calibration for Higher Activation Sparsity Deja Vu: contextual sparsity for efficient LLMs at inference time

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:10:12.701532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 85e6ce89-48de-4cf2-aacd-118596a22083 · outbound

This paper cites Pointer sentinel mixture models, 2016.

Post-Training Statistical Calibration for Higher Activation Sparsity Pointer sentinel mixture models, 2016

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.317143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 825df76c-bb36-4846-b8e9-cc07ad8cc63a · outbound

This paper cites del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, and Mehrdad Farajtabar.

Post-Training Statistical Calibration for Higher Activation Sparsity del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, and Mehrdad Farajtabar

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:10:12.682179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a94a3930-be6e-499c-bcab-10ddee45852d · outbound

This paper cites Orca-math: Unlocking the potential of slms in grade school math, 2024.

Post-Training Statistical Calibration for Higher Activation Sparsity Orca-math: Unlocking the potential of slms in grade school math, 2024

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.326032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8485e8a-0fd2-4802-b0a7-f9ca729e54d2 · outbound

This paper cites Openwebmath: An open dataset of high-quality mathematical web text, 2023.

Post-Training Statistical Calibration for Higher Activation Sparsity Openwebmath: An open dataset of high-quality mathematical web text, 2023

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.329933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 911e61d7-7439-4691-9c25-c6a3b35ca5dd · outbound

This paper cites Efficiently Scaling Transformer Inference.

Post-Training Statistical Calibration for Higher Activation Sparsity Efficiently Scaling Transformer Inference

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:10:12.650597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 93d3aefc-7c4d-4009-a316-2c35da09ef00 · outbound

This paper cites an unresolved cited work.

Post-Training Statistical Calibration for Higher Activation Sparsity Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.336891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d959ad66-c66f-4c14-917e-09f71bf583b9 · outbound

This paper cites Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs | Databricks Blog, May 2023.

Post-Training Statistical Calibration for Higher Activation Sparsity Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs | Databricks Blog, May 2023

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:10:12.627181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 977626c5-0a1a-4478-aebc-1c0d1db9c45e · outbound

This paper cites GLU Variants Improve Transformer.

Post-Training Statistical Calibration for Higher Activation Sparsity GLU Variants Improve Transformer

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.344332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 423c1915-f1b1-41e7-a341-62d0aa957ba9 · outbound

This paper cites ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models.

Post-Training Statistical Calibration for Higher Activation Sparsity ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.348098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f08e0f2-686f-4e68-9801-49991e20567e · outbound

This paper cites PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU.

Post-Training Statistical Calibration for Higher Activation Sparsity PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.351877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5bd577f-38f8-46c3-bacf-4e60031728d6 · outbound

This paper cites Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters.

Post-Training Statistical Calibration for Higher Activation Sparsity Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.355895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1226f33a-7336-4176-a183-958964c1dfab · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Post-Training Statistical Calibration for Higher Activation Sparsity A Simple and Effective Pruning Approach for Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.359831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ded954f3-7b1b-497a-a301-0e1f4513897e · outbound

This paper cites Deit iii: Revenge of the vit.

Post-Training Statistical Calibration for Higher Activation Sparsity Deit iii: Revenge of the vit

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:10:12.613789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e01fcfe7-ba03-41a7-a36a-616b253977c0 · outbound

This paper cites Gpt-j-6b: A 6 billion parameter autoregressive language model, 2021.

Post-Training Statistical Calibration for Higher Activation Sparsity Gpt-j-6b: A 6 billion parameter autoregressive language model, 2021

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.367166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6938c64-803d-4286-b241-804edeab7372 · outbound

This paper cites an unresolved cited work.

Post-Training Statistical Calibration for Higher Activation Sparsity Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-11T19:10:12.594960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 192a652e-c373-431c-94d7-2132955e7f7e · outbound

This paper cites Orca: A distributed serving system for Transformer-Based generative models.

Post-Training Statistical Calibration for Higher Activation Sparsity Orca: A distributed serving system for Transformer-Based generative models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:10:12.583618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1ca77669-3b2e-4445-a7c7-eb92c47a144c · outbound

This paper cites ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs.

Post-Training Statistical Calibration for Higher Activation Sparsity ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T19:10:12.377428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation dda4dc23-5b3d-4cf9-9abb-97e25ee1380e · inbound

Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches cites this paper.

Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches Post-Training Statistical Calibration for Higher Activation Sparsity

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-18T13:41:25.932269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c84d0f38-33e9-44c4-bf7c-65b2fdb329d6 · inbound

Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes cites this paper.

Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes Post-Training Statistical Calibration for Higher Activation Sparsity

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.653782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d5c2466b-e4b1-45a9-b5a6-169903a8ddc4 · inbound

Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes cites this paper.

Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes Post-Training Statistical Calibration for Higher Activation Sparsity

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:16:19.703261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.