Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z
Paper Citation Record · LEDGER
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
As of 24 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 3 inbound Pith citation observations for arXiv:2605.11855.
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 2026-08-23T06:30:58.430688+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-06-30T22:21:16.608148Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-01T14:05:46.329040Z
Reference resolution
8 of 8 outbound references displayed
- verified exact1
- verified fuzzy2
- unresolved0
- parse uncertain0
- malformed identifier1
- metadata mismatch4
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation f801afe6-90cc-4a4e-a2a1-44a660fc4702 · outbound
This paper cites Learning long-term dependencies with gradient descent is difficult.IEEE Transactions on Neural Networks, 5(2):157–166.
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications Learning long-term dependencies with gradient descent is difficult.IEEE Transactions on Neural Networks, 5(2):157–166
Reference 1
- Resolution
- metadata mismatch
- doi, observed 2026-06-30T22:25:06.652910Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 93ef9c6d-0d9f-4132-8249-8dd5d24eeea6 · outbound
This paper cites Blelloch, G.
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.887133Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation ea096822-f591-4d9e-9218-cf2e35309f53 · outbound
This paper cites Quantization.IEEE Transactions on Information Theory, 44(6):2325–2383.
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications Quantization.IEEE Transactions on Information Theory, 44(6):2325–2383
Reference 3
- Resolution
- metadata mismatch
- doi, observed 2026-06-30T22:25:06.655036Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation dfb76a74-50c7-46a3-b773-a7168a6a6402 · outbound
This paper cites Parallelizing Linear Recurrent Neural Nets Over Sequence Length.
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications Parallelizing Linear Recurrent Neural Nets Over Sequence Length
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T22:25:06.657972Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 24fae74e-505c-4fee-b327-b32981dfcd53 · outbound
This paper cites Improving performance of recurrent neural network with relu nonlinearity.
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications Improving performance of recurrent neural network with relu nonlinearity
Reference 5
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T14:15:47.533268Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation d4639f6a-b1dd-4d51-a8ba-f821f7019a61 · outbound
This paper cites Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition.
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
Reference 6
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T14:15:47.535964Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 83cdc675-3812-428b-8585-174eb2dbbbb5 · outbound
This paper cites Note that m and d are independent: the recurrent cell projects from m to d internally, and projects back tomfor the output.
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications Note that m and d are independent: the recurrent cell projects from m to d internally, and projects back tomfor the output
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.885220Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 90482daa-011a-4254-bdef-4ff2b7a5b0bd · outbound
This paper cites zero” through “nine.
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications zero” through “nine
Reference 8
- Resolution
- malformed identifier
- raw_fallback, observed 2026-07-07T15:13:53.883212Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Pith citing papers
Observation f643a099-21f5-4501-918b-51e39f02f841 · inbound
A Fully Tunable Ultra-Low Power Current-Mode Memory Cell in Standard CMOS Technology cites this paper.
A Fully Tunable Ultra-Low Power Current-Mode Memory Cell in Standard CMOS Technology Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
Reference 30
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T22:49:10.382527Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 12d539eb-3f11-4a3e-a77e-eef0518c872c · inbound
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations cites this paper.
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
Reference 112
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T22:09:07.180174Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 829ff608-e770-4445-8365-83534abb830a · inbound
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations cites this paper.
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
Reference 112
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T14:05:46.330633Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.