Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-12T03:44:09.156934Z
Paper Citation Record · LEDGER
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding
As of 5 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2605.09375.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
22 of 22 outbound references displayed
- verified exact12
- verified fuzzy2
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch8
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation ad691436-92e0-4f5d-8e43-7fae2bf54446 · outbound
This paper cites The Llama 3 Herd of Models.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding The Llama 3 Herd of Models
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:06:35.826799Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 21521193-4df6-4fbc-8560-64070aec0d63 · outbound
This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:06:35.818712Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation fb0cda2b-1be5-4e89-b731-a780c5242b57 · outbound
This paper cites In: 2024 IEEE International Solid-State Circuits Conference (ISSCC).
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding In: 2024 IEEE International Solid-State Circuits Conference (ISSCC)
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T03:46:21.266864Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e89014a4-d505-45f6-9e0c-d6cc4a00faa8 · outbound
This paper cites Chen, Phil C.
Reference 4
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T03:46:21.271836Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation faa03761-8e7f-41b3-8142-7debcbe9a663 · outbound
This paper cites Chen, Phil C.
Reference 5
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T03:46:21.261800Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1d54404d-e0e4-4259-bdd5-427f82877c22 · outbound
This paper cites LLM-CIM: A 28nm 126.7 TOPS/W Input-LUT-Based Digital CIM Macro with Reconfigurable Matrix Multiplication and Nonlinear Operation Modes for LLMs.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding LLM-CIM: A 28nm 126.7 TOPS/W Input-LUT-Based Digital CIM Macro with Reconfigurable Matrix Multiplication and Nonlinear Operation Modes for LLMs
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T03:46:21.248843Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b6b93be1-ae6c-40e3-b723-e0c4cb33192c · outbound
This paper cites LLM-CIM: A 28nm 126.7 TOPS/W Input-LUT-Based Digital CIM Macro with Reconfigurable Matrix Multiplication and Nonlinear Operation Modes for LLMs.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding LLM-CIM: A 28nm 126.7 TOPS/W Input-LUT-Based Digital CIM Macro with Reconfigurable Matrix Multiplication and Nonlinear Operation Modes for LLMs
Reference 7
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T03:46:21.240092Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 67108ed4-3724-4fef-b297-266b4c1e8cdb · outbound
This paper cites Fast Inference from Transformers via Speculative Decoding.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding Fast Inference from Transformers via Speculative Decoding
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:52:00.384886Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8f48313d-678b-4deb-8be0-c6f05213344d · outbound
This paper cites EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T00:15:49.524886Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3bb9ab90-db7d-4073-b44c-f6e3879dd651 · outbound
This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:06:35.728482Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 12734c7c-0744-44f0-922e-c1f47028c63b · outbound
This paper cites QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Reference 11
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:06:35.739344Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d0a2d94d-27f0-4435-9a9c-d69c0481b990 · outbound
This paper cites SpinQuant: LLM quantization with learned rotations.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding SpinQuant: LLM quantization with learned rotations
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T15:52:34.845430Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e6681262-e60b-4534-8ad5-a8144c0b6cae · outbound
This paper cites RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight- Activation Quantization.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight- Activation Quantization
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T18:21:45.420857Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 424cd955-7580-4e79-ac30-f35a5dca4cb6 · outbound
This paper cites Knowledge-Centric Hallucination Detection.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding Knowledge-Centric Hallucination Detection
Reference 14
- Resolution
- verified exact
- doi, observed 2026-05-12T03:46:21.251628Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b1cc9dbf-d093-449f-86da-9fecb5d035e4 · outbound
This paper cites PEARL: Parallel Speculative Decoding with Adaptive Draft Length.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding PEARL: Parallel Speculative Decoding with Adaptive Draft Length
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:06:35.778873Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 589f52d5-9c73-4a11-a409-d9a274ea8539 · outbound
This paper cites A Library of Hadamard Matrices.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding A Library of Hadamard Matrices
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T18:21:45.425633Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation cffa07f2-e394-4c2c-b743-8eb9454b7f60 · outbound
This paper cites GPTVQ: The Blessing of Dimensionality for LLM Quantization.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding GPTVQ: The Blessing of Dimensionality for LLM Quantization
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:06:35.747950Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1b511755-7aba-4676-894e-3b8fe2672e51 · outbound
This paper cites VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
Reference 18
- Resolution
- verified exact
- doi, observed 2026-05-12T03:46:21.244099Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0de6ade0-9d54-4cbb-a906-cdbddb5dc7fa · outbound
This paper cites MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:06:35.697571Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 59d974bf-9fd7-4ba9-8778-7713a9bf597e · outbound
This paper cites MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:06:35.708278Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e24bc3cb-5181-43bb-a55d-2cce71e61427 · outbound
This paper cites Chen, Phil C.
Reference 21
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T03:46:21.235136Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4a5b26df-3d77-4de7-9a99-72617e9ea09a · outbound
This paper cites Kill the Program Counter: Reconstructing Program Behavior in the Processor Cache Hierarchy.
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding Kill the Program Counter: Reconstructing Program Behavior in the Processor Cache Hierarchy
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T03:46:21.256864Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Pith citing papers
No inbound Pith citation observations are available.