Paper Citation Record · LEDGER

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models

As of 23 July 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2605.17653.

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

pith.paper-citation-record.v1
2605.17653 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T13:58:55.899958Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-23T06:31:01.910684+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

38 of 38 outbound references displayed

verified exact24
verified fuzzy8
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch5

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f454a062-4362-4319-9d36-fb2482168c23 · outbound

This paper cites Composer: A search framework for hybrid neural architecture design.arXiv preprint arXiv:2510.00379.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Composer: A search framework for hybrid neural architecture design.arXiv preprint arXiv:2510.00379

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.542050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 245748d5-74d5-4bed-acde-5401e8f8a8ae · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.584469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 265c75c0-fe12-46f6-ab5a-447bf7c606b9 · outbound

This paper cites SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.559331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 6a798b53-f60d-4ac7-821e-15873659d257 · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Pythia: A suite for analyzing large language models across training and scaling

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T14:03:21.285635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5752a7c0-9f73-44b7-bb53-621501972941 · outbound

This paper cites Eyeriss v2: A flexible accelerator for emerging deep neural networks on mobile devices.IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 9(2):292–308.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Eyeriss v2: A flexible accelerator for emerging deep neural networks on mobile devices.IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 9(2):292–308

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T14:03:21.280222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 699f9b74-2138-4ae5-9a4b-78d1d70e1324 · outbound

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

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models BoolQ: Exploring the surprising difficulty of natural yes/no questions

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T14:03:21.282912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation a6e6eb28-7048-4e65-ab03-5618a201d1ff · outbound

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

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.537023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 0738569c-ba2c-4615-ab2e-6dd38e770aa0 · outbound

This paper cites and Pratap, A.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models and Pratap, A

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.237109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation b9fd3401-d6eb-464b-8225-b582a326ba57 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.546266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation c62bd50b-8f30-4b14-8baa-e616ce2a0147 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.580465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 85520e9a-b14c-4937-bad8-ccb048a42cc0 · outbound

This paper cites In: ACM/IEEE Design Automation Con- ference.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models In: ACM/IEEE Design Automation Con- ference

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T14:03:20.267723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 3c51bfaf-0e7d-4185-af90-a4ca1c2af7fa · outbound

This paper cites Jet-nemotron: Efficient language model with post neural architecture search.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Jet-nemotron: Efficient language model with post neural architecture search

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.555289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 8f8aea15-1d14-4fde-b631-5fd2efe1f791 · outbound

This paper cites Training Compute-Optimal Large Language Models.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Training Compute-Optimal Large Language Models

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T14:03:20.587995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 98073453-e083-40c0-afba-e9e15e0897d5 · outbound

This paper cites The MiniPile Challenge for Data-Efficient Language Models.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models The MiniPile Challenge for Data-Efficient Language Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.502894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation f00d71ef-4f62-4d27-a411-b6408ce28f75 · outbound

This paper cites Emer, and Saman P.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Emer, and Saman P

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T14:03:20.232416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 226e53a4-89e9-4e5e-8adf-2163eb5378a2 · outbound

This paper cites MELTing Point: Mobile evaluation of language transformers.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models MELTing Point: Mobile evaluation of language transformers

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.247356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation eb2689d7-2f6d-48f3-af2a-f5511c73072c · outbound

This paper cites Transformers in Speech Processing: A Survey.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Transformers in Speech Processing: A Survey

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.567896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 528299c8-ee40-4e5c-b2ae-f9b979041b16 · outbound

This paper cites Mobilellm: Optimizing sub-billion parameter language models for on-device use cases.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Mobilellm: Optimizing sub-billion parameter language models for on-device use cases

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T14:03:21.274536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 24c938b5-d8a1-4bd5-a924-17a5ee49cb3d · outbound

This paper cites MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.576536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 96a6c150-4b57-4b3c-b9c4-c4d85efb6ae9 · outbound

This paper cites OpenELM: An Efficient Language Model Family with Open Training and Inference Framework.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models OpenELM: An Efficient Language Model Family with Open Training and Inference Framework

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.512545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation d6f035fe-a64a-4d01-9b9b-55ceb843e131 · outbound

This paper cites Ying, Anurag Mukkara, Rangharajan Venkatesan, Brucek Khailany, Stephen W.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Ying, Anurag Mukkara, Rangharajan Venkatesan, Brucek Khailany, Stephen W

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T14:03:21.271549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation c7a5d863-3547-4dd4-9818-ac887b45f09c · outbound

This paper cites Parashar et al.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Parashar et al

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T14:03:20.261701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 19c52e5a-c2b9-4a5a-a79e-9efebffe1a61 · outbound

This paper cites Hare, and Geoff V.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Hare, and Geoff V

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.225281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 30267bba-655b-4a12-a4ff-393bf88449a5 · outbound

This paper cites The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.507164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 947dfc33-844b-4adc-97af-099ff6d83087 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Fast Transformer Decoding: One Write-Head is All You Need

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.528485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 70276278-33ce-491f-9f6e-6854e5403ea5 · outbound

This paper cites HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.516245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation fe3671b2-7049-4047-a71d-bd39ad74bb7a · outbound

This paper cites An 11.16µj/token edge SLM decoder accelerator with scal- able ring-based configuration for token-level pipelining in 16 nm FinFET.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models An 11.16µj/token edge SLM decoder accelerator with scal- able ring-based configuration for token-level pipelining in 16 nm FinFET

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T14:03:21.262946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 55d2b65a-71c2-48a7-9a95-acf290cf1dec · outbound

This paper cites Qwen2.5 Technical Report.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Qwen2.5 Technical Report

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.519582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 13e9ea31-424f-4830-9936-a5afff4f09ce · outbound

This paper cites Thomas, Rom N.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Thomas, Rom N

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T14:03:21.268744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation b72d3640-b9cd-4966-a62f-d20ea2cf0a40 · outbound

This paper cites Simultaneous planning and execution for quadro- tors flying through a narrow gap under disturbance.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Simultaneous planning and execution for quadro- tors flying through a narrow gap under disturbance

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.255583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation cb5ea27a-354b-4116-89ce-5afc2f4f6021 · outbound

This paper cites Attention Is All You Need.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Attention Is All You Need

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.571637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation bbf602cb-026f-49af-bef0-dc48d8b4bcf8 · outbound

This paper cites HAT: Hardware-Aware Transformers for Efficient Natural Language Processing.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.550972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 5cacdc25-ad92-4f2d-9b66-a47112dea8fd · outbound

This paper cites Crowdsourcing Multiple Choice Science Questions.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Crowdsourcing Multiple Choice Science Questions

Reference 35

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T14:03:20.532549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 0985eea9-059f-4604-ab3f-cc11231b0d6b · outbound

This paper cites Conformer-based speech recognition on extreme edge-computing devices.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Conformer-based speech recognition on extreme edge-computing devices

Reference 36

Resolution: verified exact; doi, observed 2026-05-20T14:03:20.241505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation b562e77b-c3ae-4b49-8c86-20b44dff5d3f · outbound

This paper cites Zeus: Understanding and optimizing GPU energy consumption of DNN training.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Zeus: Understanding and optimizing GPU energy consumption of DNN training

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T14:03:21.265609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 2cc53c94-ce99-4f45-9307-fff09a0f0ac0 · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:03:20.563387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 22d69211-ca82-44fe-a18e-d700c1bd060d · outbound

This paper cites Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:03:20.524249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Observation 53ac1877-e907-420c-9363-ac986d39475b · outbound

This paper cites MAC precision.

LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models MAC precision

Reference 40

Resolution: malformed identifier; raw_fallback, observed 2026-05-20T14:03:21.277225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-23T06:31:01.910684+00:00.

Pith citing papers

No inbound Pith citation observations are available.