Paper Citation Record · LEDGER

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs

As of 11 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2502.00047.

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

pith.paper-citation-record.v1
2502.00047 v4

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T10:42:07.888794Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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 exact1
verified fuzzy13
unresolved14
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2a55578b-ad79-4193-9923-95b977a10d89 · outbound

This paper cites Q-S5: Towards Quantized State Space Models.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Q-S5: Towards Quantized State Space Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.698480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a003981a-9f31-4bdb-8b30-946a2b1242b0 · outbound

This paper cites an unresolved cited work.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-10T10:42:08.370770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d858835e-3102-4bb2-894a-ab0c491768f1 · outbound

This paper cites an unresolved cited work.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-10T10:42:08.391797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 697116fb-2189-40c0-a632-1b6bfc3fb3da · outbound

This paper cites Experiments where done on a NVIDIA GeForce RTX 3080 GPU.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Experiments where done on a NVIDIA GeForce RTX 3080 GPU

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.438076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 76b03f77-ca72-43f8-83d9-7bc3903219c7 · outbound

This paper cites Quantized Approximately Orthogonal Recurrent Neural Networks.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Quantized Approximately Orthogonal Recurrent Neural Networks

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-10T10:42:08.047788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 87ed2efb-221f-4f1d-b8ca-c21668801034 · outbound

This paper cites The experiments were conducted using the IMDB dataset, with similar trends observed across the other benchmarks, supporting the consistency of these conclusions.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs The experiments were conducted using the IMDB dataset, with similar trends observed across the other benchmarks, supporting the consistency of these conclusions

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.418143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 38c0f8ad-0060-4851-800a-bc749c12eb0a · outbound

This paper cites This is because HadamRNN better memorize than HadamRNN-ReLU.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs This is because HadamRNN better memorize than HadamRNN-ReLU

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.241676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 33662c01-248d-409d-a21d-063162a461a0 · outbound

This paper cites This finding, along with Appendix H.1, supports our choice to learn row switches only.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs This finding, along with Appendix H.1, supports our choice to learn row switches only

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.199481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 431ce30d-1425-4841-a6d7-0eee7545c230 · outbound

This paper cites an unresolved cited work.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-10T10:42:08.503101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fbd27977-3d57-48dd-8431-8f2f532e60b0 · outbound

This paper cites Zhang, Q.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Zhang, Q

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.478180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a6154ec1-a0b6-47ef-8e0e-52c835f3376a · outbound

This paper cites DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.797545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f328653-f278-48ee-ac92-45b0bfd71dbe · outbound

This paper cites Unitary Recurrent Neural Networks (URNNs) were introduced in Arjovsky et al.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Unitary Recurrent Neural Networks (URNNs) were introduced in Arjovsky et al

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.456663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 605c1baa-bbe6-442b-b12e-e1d8863a5d23 · outbound

This paper cites F M ORE BENCHMARKS In Appendix F.1, we provide a comparison of HadamRNN and quantized versions of BERT on the SST-2 and QQP benchmarks from GLUE (Wang et al., 2019).

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs F M ORE BENCHMARKS In Appendix F.1, we provide a comparison of HadamRNN and quantized versions of BERT on the SST-2 and QQP benchmarks from GLUE (Wang et al., 2019)

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.351890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fbd96d88-dc96-4673-b0db-481f754edf1d · outbound

This paper cites (2022)) 88.7 13 400 BiBERT (Qin et al.,.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs (2022)) 88.7 13 400 BiBERT (Qin et al.,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.313169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation db5e508f-b6e6-4410-a380-9bc31f5dea1f · outbound

This paper cites This result surpasses the smallest BiBERT, despite our model being more than 130 times smaller.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs This result surpasses the smallest BiBERT, despite our model being more than 130 times smaller

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.287556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ff16ec61-b480-43a9-b31c-5cbd271c1e68 · outbound

This paper cites an unresolved cited work.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Unresolved cited work

Reference 25

Resolution: malformed identifier; raw_fallback, observed 2026-08-10T10:42:08.260834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 05e98e88-17b9-4ab4-95e5-55005af2fbde · outbound

This paper cites Conversely, in the ReLU-ORNN case, the norm increases, possibly approaching0.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Conversely, in the ReLU-ORNN case, the norm increases, possibly approaching0

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.220894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 92d3f3bd-d513-45e5-aa1b-6eb4ec399f3f · outbound

This paper cites 29 Published as a conference paper at ICLR 2025 Table 10: Value of𝛼𝑊 and𝛼ℎ for activation quantification across the datasets and bitwidth.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs 29 Published as a conference paper at ICLR 2025 Table 10: Value of𝛼𝑊 and𝛼ℎ for activation quantification across the datasets and bitwidth

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.173371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 490a0888-9921-4936-9c64-68c0953ab764 · outbound

This paper cites In comparison, the smallest BiBERT model, distilled from a BERT pre-trained on a large dataset and with a network size 550 times larger, achieves85.4%.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs In comparison, the smallest BiBERT model, distilled from a BERT pre-trained on a large dataset and with a network size 550 times larger, achieves85.4%

Reference 256

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.333205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 874b4e14-6332-42d9-94af-51ab41e5d586 · outbound

This paper cites Effective Quantization Methods for Recurrent Neural Networks.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Effective Quantization Methods for Recurrent Neural Networks

Reference 1893

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.748234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2efec118-3030-4ceb-a565-9816cd3ce6ab · outbound

This paper cites Helfrich, D.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Helfrich, D

Reference 1978

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:42:08.543651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f1e7f8cd-ef51-4933-8ea8-cefa928447da · outbound

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

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 2001

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.734326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99945597-c8c2-404a-8623-1cb9ae615a30 · outbound

This paper cites Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.728028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b11ee7e-fc09-4f73-8575-ab97b55af089 · outbound

This paper cites an unresolved cited work.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Unresolved cited work

Reference 2017

Resolution: unresolved; raw_fallback, observed 2026-08-10T10:42:08.523570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 64b08c3a-af58-45ea-8a7d-d61474f870f7 · outbound

This paper cites Neural Networks with Few Multiplications.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Neural Networks with Few Multiplications

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.765280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a30a1905-4703-4a14-a87d-d5eeee28ca9d · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.721102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a52df254-b171-450b-9fe9-a2d359a9b27b · outbound

This paper cites LLM-QAT: Data-Free Quantization Aware Training for Large Language Models.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.771646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97321f2d-cdc4-4546-a510-53aeee7af956 · outbound

This paper cites Recurrent Neural Networks With Limited Numerical Precision.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Recurrent Neural Networks With Limited Numerical Precision

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-10T10:42:07.779606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79de15a4-635e-4045-b0b0-6ff2f9c14337 · outbound

This paper cites an unresolved cited work.

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-10T10:42:08.564883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

No inbound Pith citation observations are available.