Paper Citation Record · LEDGER

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference

As of 8 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2507.09010.

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

pith.paper-citation-record.v1
2507.09010 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:14:34.248578Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy15
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 125dcfd3-a8ce-415c-aff3-bf46e1c0c658 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:30.679512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a46ac35-ff27-42bf-88d0-41f738ec937c · outbound

This paper cites Architecting an energy-efficient dram system for gpus,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Architecting an energy-efficient dram system for gpus,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:37.886190Z

Source-reported events for the cited work

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

Observation a25e08c6-6864-44fe-a9c9-88abd2013d9d · outbound

This paper cites Sparc: Token similarity-aware sparse attention transformer accelerator via row- wise clustering,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Sparc: Token similarity-aware sparse attention transformer accelerator via row- wise clustering,

Reference 3

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T18:14:34.814240Z

Source-reported events for the cited work

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

Observation 34755e6b-31d8-4b32-94d9-815620da707c · outbound

This paper cites Vs-quant: Per-vector scaled quantization for accurate low-precision neural network inference,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Vs-quant: Per-vector scaled quantization for accurate low-precision neural network inference,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:37.732439Z

Source-reported events for the cited work

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

Observation 3a0cdbe1-cfcc-48f5-b0d1-54c28458854c · outbound

This paper cites Transformers are ssms: generalized models and efficient algorithms through structured state space duality,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Transformers are ssms: generalized models and efficient algorithms through structured state space duality,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:37.500968Z

Source-reported events for the cited work

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

Observation 66c0df4d-6f78-4f89-ba81-79b91d88541e · outbound

This paper cites The Llama 3 Herd of Models.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:31.335666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3784dc49-c9c0-4a86-8470-cbfb4a3b2835 · outbound

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

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:31.524697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8bc71ae-75fa-4932-9ac9-b44e22b27322 · outbound

This paper cites Ita: An energy-efficient attention and softmax accelerator for quantized transformers,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Ita: An energy-efficient attention and softmax accelerator for quantized transformers,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:37.287077Z

Source-reported events for the cited work

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

Observation 6ae7e611-7543-4731-9974-a386988a59ee · outbound

This paper cites A 95.6-tops/w deep learning inference accelerator with per-vector scaled 4-bit quantization in 5 nm,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference A 95.6-tops/w deep learning inference accelerator with per-vector scaled 4-bit quantization in 5 nm,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:37.034304Z

Source-reported events for the cited work

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

Observation fdb2cc5d-6404-4b53-92de-dc385ed4ba1b · outbound

This paper cites A modular digital vlsi flow for high-productivity soc design,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference A modular digital vlsi flow for high-productivity soc design,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:36.873081Z

Source-reported events for the cited work

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

Observation b8d9e08d-f57f-4dab-931e-5d180b80849e · outbound

This paper cites an unresolved cited work.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:14:36.700328Z

Source-reported events for the cited work

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

Observation 0387f486-e94f-49c8-8ebe-fc057f5bc4cd · outbound

This paper cites QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:32.263418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation def74e63-7de3-44bf-a8cb-f29f4cb1ce2f · outbound

This paper cites Bucket getter: A bucket-based processing engine for low-bit block floating point (bfp) dnns,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Bucket getter: A bucket-based processing engine for low-bit block floating point (bfp) dnns,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:36.503663Z

Source-reported events for the cited work

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

Observation 16c20b43-0be1-4b68-9fb2-77ac679ae042 · outbound

This paper cites Pointer sentinel mixture models,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Pointer sentinel mixture models,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:32.553413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81e4aa70-d83f-4540-996b-5287005ee479 · outbound

This paper cites A 127.8 tops/w arbitrarily quantized 1-to-8b scalable-precision accelerator for general-purpose deep learning with reduction of storage, logic and latency waste,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference A 127.8 tops/w arbitrarily quantized 1-to-8b scalable-precision accelerator for general-purpose deep learning with reduction of storage, logic and latency waste,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:36.352125Z

Source-reported events for the cited work

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

Observation 68ca6f1a-0c32-4cd3-aa27-8741e8d6070b · outbound

This paper cites Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:32.895076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation defed1f5-5f58-4e28-b12b-ed08d7d6e9d7 · outbound

This paper cites Nvidia jetson orin nano,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Nvidia jetson orin nano,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:36.207990Z

Source-reported events for the cited work

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

Observation 70b8b192-fcd8-4095-a1ae-e25967db41e1 · outbound

This paper cites Fine-grained dram: Energy-efficient dram for extreme bandwidth systems,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Fine-grained dram: Energy-efficient dram for extreme bandwidth systems,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:35.961479Z

Source-reported events for the cited work

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

Observation 20372408-fd1a-45c2-a80b-55319903ab74 · outbound

This paper cites Fact: Ffn-attention co-optimized transformer architecture with eager correlation prediction,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Fact: Ffn-attention co-optimized transformer architecture with eager correlation prediction,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:35.792388Z

Source-reported events for the cited work

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

Observation 94c2d3bf-c2c2-4fa2-bfb2-d7bc4e72f9ce · outbound

This paper cites Mecla: Memory-compute-efficient llm accelerator with scaling sub-matrix partition,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Mecla: Memory-compute-efficient llm accelerator with scaling sub-matrix partition,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:35.605872Z

Source-reported events for the cited work

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

Observation 260f865f-bf22-41ba-941c-9f2c8516265b · outbound

This paper cites Microscaling Data Formats for Deep Learning.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Microscaling Data Formats for Deep Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:33.447407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bc362b9-8a4e-4af1-ba6e-438221315542 · outbound

This paper cites Roformer: En- hanced transformer with rotary position embedding,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Roformer: En- hanced transformer with rotary position embedding,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:33.587252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07c632fd-f886-4442-81de-7ebd830008e7 · outbound

This paper cites Retentive Network: A Successor to Transformer for Large Language Models.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Retentive Network: A Successor to Transformer for Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:33.692647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffd7964c-373e-45db-95dc-293c43766d5f · outbound

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

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:33.762234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f1cfe7-9c9c-4ac1-b62e-a6cc49823000 · outbound

This paper cites Sole: Hardware-software co-design of softmax and layernorm for efficient transformer inference,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Sole: Hardware-software co-design of softmax and layernorm for efficient transformer inference,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:35.383466Z

Source-reported events for the cited work

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

Observation 2079e212-5704-4a29-b94c-6110d504a9e2 · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Smoothquant: Accurate and efficient post-training quantization for large language models,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:14:33.974593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb639e50-da2a-4437-85b3-05ef8531e8da · outbound

This paper cites Llmcompass: Enabling efficient hardware design for large language model inference,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Llmcompass: Enabling efficient hardware design for large language model inference,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:35.216617Z

Source-reported events for the cited work

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

Observation be55cd61-3724-4471-a10a-d6df02d4d13d · outbound

This paper cites Atom: Low-bit quantization for efficient and accurate llm serving,.

Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference Atom: Low-bit quantization for efficient and accurate llm serving,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:14:35.002544Z

Source-reported events for the cited work

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

Pith citing papers

No inbound Pith citation observations are available.