Paper Citation Record · LEDGER

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration

As of 6 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2604.15944.

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

pith.paper-citation-record.v1
2604.15944 v2

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T07:56:53.425178Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

29 of 29 outbound references displayed

verified exact5
verified fuzzy22
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c7a48857-63db-4d82-b64a-86a83b88054a · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.696373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7a366cfa-5fe8-4376-a8f9-4ad51d34b5b8 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T07:57:15.104073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 42684467-3c7c-4cc1-94cd-e2c67140bd76 · outbound

This paper cites Attention is all you need.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Attention is all you need

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.687305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5735380a-a411-4385-a838-2bff4c200f62 · outbound

This paper cites Conversational agents in ther- apeutic interventions for neurodevelopmental disorders: a survey.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Conversational agents in ther- apeutic interventions for neurodevelopmental disorders: a survey

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.683994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9bbb8867-9020-4642-a549-921bd0954091 · outbound

This paper cites 15.3 a 351tops/w and 372.4gops compute-in- memory sram macro in 7nm finfet cmos for machine-learning appli- cations.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration 15.3 a 351tops/w and 372.4gops compute-in- memory sram macro in 7nm finfet cmos for machine-learning appli- cations

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.690734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 04579998-d4a4-407d-8b88-19934b3ab402 · outbound

This paper cites A 32.2 tops/w sram compute-in-memory macro employing a linear 8-bit c-2c ladder for charge domain computation in 22nm for edge inference.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration A 32.2 tops/w sram compute-in-memory macro employing a linear 8-bit c-2c ladder for charge domain computation in 22nm for edge inference

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.675937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 08329236-e3ce-4f16-9d1a-2e9c68a16c48 · outbound

This paper cites A 5-nm 254-tops/w 221-tops/mm2 fully-digital computing-in-memory macro supporting wide-range dynamic-voltage- frequency scaling and simultaneous mac and write operations.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration A 5-nm 254-tops/w 221-tops/mm2 fully-digital computing-in-memory macro supporting wide-range dynamic-voltage- frequency scaling and simultaneous mac and write operations

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.153373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 14f8c743-57bf-4d32-8eea-7bae5deec114 · outbound

This paper cites A 4nm 6163-tops/w/b4790−tops/mm 2/bsram based digital-computing-in-memory macro supporting bit-width flexibility and simultaneous mac and weight update.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration A 4nm 6163-tops/w/b4790−tops/mm 2/bsram based digital-computing-in-memory macro supporting bit-width flexibility and simultaneous mac and weight update

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.673416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f8afbb2a-7146-43f8-b10d-9e28d130b6c5 · outbound

This paper cites 34.4 a 3nm, 32.5tops/w, 55.0tops/mm2 and 3.78mb/mm2 fully-digital compute-in- memory macro supporting int12 × int12 with a parallel-mac architecture and foundry 6t-sram bit cell.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration 34.4 a 3nm, 32.5tops/w, 55.0tops/mm2 and 3.78mb/mm2 fully-digital compute-in- memory macro supporting int12 × int12 with a parallel-mac architecture and foundry 6t-sram bit cell

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.140422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f28c7c8d-03a1-4bc6-931d-29fad6436752 · outbound

This paper cites A 12nm 121-tops/w 41.6- tops/mm2 all digital full precision sram-based compute-in-memory with configurable bit-width for ai edge applications.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration A 12nm 121-tops/w 41.6- tops/mm2 all digital full precision sram-based compute-in-memory with configurable bit-width for ai edge applications

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.146583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8c5e4a3a-4b76-47ce-9c2d-5f10a1ba02b1 · outbound

This paper cites Trancim: Full-digital bitline-transpose cim-based sparse transformer accelerator with pipeline/parallel reconfigurable modes.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Trancim: Full-digital bitline-transpose cim-based sparse transformer accelerator with pipeline/parallel reconfigurable modes

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.143605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7ddbd662-b0be-4f30-bc47-06feaf1f6843 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-10T07:57:15.114761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 459d3548-a8dd-4a3b-9ba6-7bb3221b20e3 · outbound

This paper cites Language models are unsupervised multitask learners.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Language models are unsupervised multitask learners

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.156484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d6f2dfc4-11b9-42de-8577-3e59b1d3c584 · outbound

This paper cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-13T00:14:58.269455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 431c1525-8904-44cc-9e97-8d137d5a0425 · outbound

This paper cites Full Stack Optimization of Transformer Inference: a Survey.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Full Stack Optimization of Transformer Inference: a Survey

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-10T07:57:15.117402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 64d57c70-21fe-4bbf-a3e0-6ccd05eca8fd · outbound

This paper cites Online normalizer calculation for softmax.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Online normalizer calculation for softmax

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-10T07:57:15.119940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b18b11c9-1f3b-4560-be0d-7a933c803067 · outbound

This paper cites A 28-nm 28.8- tops/w attention-based nn processor with correlative cim ring architecture and dataflow-reshaped digital-assisted cim array.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration A 28-nm 28.8- tops/w attention-based nn processor with correlative cim ring architecture and dataflow-reshaped digital-assisted cim array

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.678682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 583729cc-a69a-4c4e-a52b-ffa00b04fd76 · outbound

This paper cites An energy-efficient transformer processor exploiting dynamic weak relevances in global attention.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration An energy-efficient transformer processor exploiting dynamic weak relevances in global attention

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.670965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a5740cbe-69ad-4a1e-abf1-8765d9004d9e · outbound

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

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Ita: An energy-efficient attention and softmax accelerator for quantized transformers

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.135297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b0b2d8a1-16ad-46c6-8ed4-a4d717d88b52 · outbound

This paper cites Hardware implementation of softmax function based on piecewise lut.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Hardware implementation of softmax function based on piecewise lut

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.149507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 34e0a73a-48de-4567-9fb0-9e71385e0aa8 · outbound

This paper cites Efficient Softmax Approximation for Deep Neural Networks with Attention Mechanism.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Efficient Softmax Approximation for Deep Neural Networks with Attention Mechanism

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-10T07:57:15.109584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 33daf076-82d4-4a29-90c8-250d923983b7 · outbound

This paper cites Multcim: Digital computing-in-memory-based multimodal transformer accelerator with attention-token-bit hybrid sparsity.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Multcim: Digital computing-in-memory-based multimodal transformer accelerator with attention-token-bit hybrid sparsity

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.667721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 82319f84-53b2-4e65-9dd7-0fc0120e2dc7 · outbound

This paper cites Cimformer: A systolic cim-array-based transformer accelerator with token-pruning-aware attention reformulating and principal possibility gathering.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Cimformer: A systolic cim-array-based transformer accelerator with token-pruning-aware attention reformulating and principal possibility gathering

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.681762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0a77357e-6c8b-4bc4-9876-f069b2c92621 · outbound

This paper cites I-bert: Integer-only bert quantization.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration I-bert: Integer-only bert quantization

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:10:07.693588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 825fdac9-8d21-462f-a0e7-2dbf199ac134 · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Flashattention: Fast and memory-efficient exact attention with io-awareness

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.132021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 88e9b45c-5e94-4ea6-80bb-6c7edcad0ef4 · outbound

This paper cites 23.8 an 88.36tops/w bit-level-weight-compressed large-language- model accelerator with cluster-aligned int-fp-gemm and bi-dimensional workflow reformulation.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration 23.8 an 88.36tops/w bit-level-weight-compressed large-language- model accelerator with cluster-aligned int-fp-gemm and bi-dimensional workflow reformulation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.123331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 864bb530-d765-449f-b90e-4ec17a0bd043 · outbound

This paper cites Tinyllama: An open-source small language model.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration Tinyllama: An open-source small language model

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.126157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 040ffb11-8307-4b80-b93d-751a02cef9dd · outbound

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

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration A framework for few-shot language model evaluation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T12:05:06.128966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 031e8921-0d43-4a84-968b-518c26773c28 · outbound

This paper cites He, B., Yin, L., Zhen, H.-L., Liu, S., Wu, H., Zhang, X., Yuan, M., and Ma, C.

CIMple: Standard-cell SRAM-based CIM with LUT-based split softmax for attention acceleration He, B., Yin, L., Zhen, H.-L., Liu, S., Wu, H., Zhang, X., Yuan, M., and Ma, C

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T07:57:15.106869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

No inbound Pith citation observations are available.