Paper Citation Record · LEDGER

MAR: Efficient Large Language Models via Module-aware Architecture Refinement

As of 24 July 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2601.21503.

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

pith.paper-citation-record.v1
2601.21503 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-16T10:12:35.951089Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-24T06:31:00.690269+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-16T10:12:35.951089Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-16T10:12:43.035170Z

Reference resolution

35 of 35 outbound references displayed

verified exact12
verified fuzzy20
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b6c36d28-c5ef-4281-b1ab-3cccada53fa2 · outbound

This paper cites MAR: Efficient Large Language Models via Module-aware Architecture Refinement.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement MAR: Efficient Large Language Models via Module-aware Architecture Refinement

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T10:12:43.037581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 6d2fea0b-4b34-4c8b-9f12-bc079eeeae48 · outbound

This paper cites an unresolved cited work.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Unresolved cited work

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.144007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation b42b4323-5b85-4bb9-ba5f-2d70f4926953 · outbound

This paper cites Data and experimental settings We use Llamba-1B, the Mamba variant of LLaMA-3.2-1B, as the starting point for the second stage of the MAR framework.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Data and experimental settings We use Llamba-1B, the Mamba variant of LLaMA-3.2-1B, as the starting point for the second stage of the MAR framework

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.138779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 2051fa14-2b0d-44e7-9bcf-a9600637b9b8 · outbound

This paper cites In the first stage, SSMs are introduced to achieve linear-time sequence modeling; in the sec- ond, activation spiking is applied to reduce the computational cost of FFNs.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement In the first stage, SSMs are introduced to achieve linear-time sequence modeling; in the sec- ond, activation spiking is applied to reduce the computational cost of FFNs

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.130828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation b0a63496-7ce3-4682-a028-7db113e7ead0 · outbound

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

MAR: Efficient Large Language Models via Module-aware Architecture Refinement LLaMA: Open and Efficient Foundation Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-16T10:12:42.991859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 7c711df8-92a9-48bd-aea8-d92dccd595c0 · outbound

This paper cites Qwen3 Technical Report.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Qwen3 Technical Report

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-16T10:12:43.045827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 0172d989-17d1-4603-a04c-08b78ed49957 · outbound

This paper cites DeepSeek-V3 Technical Report.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement DeepSeek-V3 Technical Report

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-16T10:12:42.999801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 409e4ccd-e82e-41cf-bc7a-dd3c5b01e777 · outbound

This paper cites Lawyer LLaMA Technical Report.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Lawyer LLaMA Technical Report

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:12:43.010647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 56845ef4-9282-4c5e-914d-099aa6a4a954 · outbound

This paper cites Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T10:12:43.015746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 8a513e8f-4d20-4076-9908-bbbb4e6f7b22 · outbound

This paper cites The Mamba in the Llama: Distilling and accelerating hybrid models.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement The Mamba in the Llama: Distilling and accelerating hybrid models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.097914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation ec33ad3c-8615-4c6e-b1e7-617c83b6d550 · outbound

This paper cites SmoothQuant: Accurate and effi- cient post-training quantization for large language models.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement SmoothQuant: Accurate and effi- cient post-training quantization for large language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.117587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 2d036904-7760-4448-a948-a4f5a26f7754 · outbound

This paper cites ABKD: Pursuing a proper allocation of the probability mass in knowledge distillation via α-β-divergence.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement ABKD: Pursuing a proper allocation of the probability mass in knowledge distillation via α-β-divergence

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.100738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation d3811262-8bba-4cbf-95d9-e19345704dd6 · outbound

This paper cites FlashAttention: Fast and memory-efficient exact attention with IO-awareness.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement FlashAttention: Fast and memory-efficient exact attention with IO-awareness

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.149409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 5713a856-6ac5-48c6-bb7b-ca7d5fe20d09 · outbound

This paper cites Linformer: Self-Attention with Linear Complexity.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Linformer: Self-Attention with Linear Complexity

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-16T10:12:43.053863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 9bd3c436-3782-4739-b0ac-2c163593406a · outbound

This paper cites Efficiently mod- eling long sequences with structured state spaces.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Efficiently mod- eling long sequences with structured state spaces

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.146849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 2bf076b8-c20c-404f-b0b1-6a02d055ab04 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-16T10:12:43.028490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation b4e89406-b88d-4609-9a38-250fbb10f18b · outbound

This paper cites Attention is all you need.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Attention is all you need

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.127889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 2fd88c32-d7b5-4ba0-bdaa-eeb02765e86c · outbound

This paper cites Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:12:43.033292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 173d2ba8-d934-4f28-9fa5-ac560944e2b2 · outbound

This paper cites Networks of spiking neurons: the third gen- eration of neural network models.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Networks of spiking neurons: the third gen- eration of neural network models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.133392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 4d9e0c9a-7b5c-423d-bb4d-10b828e92a14 · outbound

This paper cites Deep learning in spiking neural networks.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Deep learning in spiking neural networks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.119999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation b3882111-a731-4e9d-bf74-074cc7bab6d4 · outbound

This paper cites Spikformer: When spiking neural network meets transformer.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Spikformer: When spiking neural network meets transformer

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.109128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation f5f3ac7b-cf25-41c8-982b-240c9154246c · outbound

This paper cites SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:12:42.980517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 29fbdd29-ce48-41bc-bc93-69df90352ab9 · outbound

This paper cites Ternary Spike: Learning ternary spikes for spiking neural networks.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Ternary Spike: Learning ternary spikes for spiking neural networks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.135873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 777ae68e-6444-4b2c-9c84-9c16349c07ef · outbound

This paper cites GenQA: Generating Millions of Instructions from a Handful of Prompts.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement GenQA: Generating Millions of Instructions from a Handful of Prompts

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:12:43.041776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation a92e98eb-af6f-4e2b-939d-f5ad253da31b · outbound

This paper cites Openhermes 2.5: An open dataset of synthetic data for generalist llm assistants.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Openhermes 2.5: An open dataset of synthetic data for generalist llm assistants

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.114859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 9d2dfd73-df24-4083-aa5c-dcc34b52f500 · outbound

This paper cites Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:12:43.050066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation f5d29993-0b41-4713-8a33-aad6d35b0c29 · outbound

This paper cites Spike-temporal latent representation for energy-efficient event-to-video reconstruction.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Spike-temporal latent representation for energy-efficient event-to-video reconstruction

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T10:12:43.024360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 7cb6bdd8-67b5-487f-9972-bac0d3031a37 · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement TinyLlama: An Open-Source Small Language Model

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-16T10:12:43.004656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation a4f288fb-ca1d-4027-8ff1-7966341ec3f3 · outbound

This paper cites SpikeLLM: Scaling up spiking neural network to large language models via saliency-based spiking.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement SpikeLLM: Scaling up spiking neural network to large language models via saliency-based spiking

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.103520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 4c67de33-1e8c-450f-ad36-54a713f7e982 · outbound

This paper cites PIQA: Reasoning about physical commonsense in natural lan- guage.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement PIQA: Reasoning about physical commonsense in natural lan- guage

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.106461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation da8e25e7-61dc-44d0-84ff-11ac2d484934 · outbound

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

MAR: Efficient Large Language Models via Module-aware Architecture Refinement BoolQ: Exploring the surprising difficulty of natural yes/no questions

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.122839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 09b200d6-3d56-4bf4-abe2-2abab7d04292 · outbound

This paper cites WinoGrande: An adversarial winograd schema challenge at scale.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement WinoGrande: An adversarial winograd schema challenge at scale

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.141246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 5e229752-007d-4441-92e2-6f18acbfae7e · outbound

This paper cites HellaSwag: Can a machine really finish your sentence?.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement HellaSwag: Can a machine really finish your sentence?

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.125504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 4d0f186a-f1fb-42a6-9589-6854d7ca4715 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

MAR: Efficient Large Language Models via Module-aware Architecture Refinement Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-16T10:12:43.019876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Observation 06e91b4b-3930-462f-a944-e0504cc00b60 · outbound

This paper cites 1.1 computing’s energy problem (and what we can do about it).

MAR: Efficient Large Language Models via Module-aware Architecture Refinement 1.1 computing’s energy problem (and what we can do about it)

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T10:12:43.112157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-24T06:31:00.690269+00:00.

Pith citing papers

Observation b6c36d28-c5ef-4281-b1ab-3cccada53fa2 · inbound