Paper Citation Record · LEDGER

Scalable-Softmax Is Superior for Attention

As of 11 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 16 inbound Pith citation observations for arXiv:2501.19399.

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

pith.paper-citation-record.v1
2501.19399 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T20:34:01.273009Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:41:54.830690Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T17:09:59.046151Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy17
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2ed10e6f-91e7-4e9f-ae4b-3f33a355d427 · outbound

This paper cites write newline.

Scalable-Softmax Is Superior for Attention write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.134673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b958027-fc05-4726-83fd-f03e1142615a · outbound

This paper cites Etc: Encoding long and structured inputs in transformers.

Scalable-Softmax Is Superior for Attention Etc: Encoding long and structured inputs in transformers

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.721755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ba82097c-5b3d-40ee-80d0-9979505729d3 · outbound

This paper cites Needle in a haystack - pressure testing llms, 2023.

Scalable-Softmax Is Superior for Attention Needle in a haystack - pressure testing llms, 2023

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.709283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 92477d2e-ba56-47c1-9b9b-52b202cd2518 · outbound

This paper cites Longformer: The Long-Document Transformer.

Scalable-Softmax Is Superior for Attention Longformer: The Long-Document Transformer

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.149151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af892ac0-26ae-4e92-9a58-f6922ec37907 · outbound

This paper cites an unresolved cited work.

Scalable-Softmax Is Superior for Attention Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-09T20:34:01.696917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b27334a6-9fb7-4152-b4ed-c1dc68e81729 · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

Scalable-Softmax Is Superior for Attention Generating Long Sequences with Sparse Transformers

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.160153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e666f589-e24b-4c15-9bc4-2e326da9c711 · outbound

This paper cites Redpajama: An open source recipe to reproduce llama training dataset, April 2023.

Scalable-Softmax Is Superior for Attention Redpajama: An open source recipe to reproduce llama training dataset, April 2023

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.684935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2e378df9-9919-4659-9baa-865950801315 · outbound

This paper cites GMAT: Global Memory Augmentation for Transformers.

Scalable-Softmax Is Superior for Attention GMAT: Global Memory Augmentation for Transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.170481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5084afc2-b111-4f59-a5a8-6eeef06233c2 · outbound

This paper cites Needle in a haystack - pressure testing llms, 2023.

Scalable-Softmax Is Superior for Attention Needle in a haystack - pressure testing llms, 2023

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.670341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 55b2139c-c9c9-4bba-9c9d-e91538b5d273 · outbound

This paper cites The impact of positional encoding on length generalization in transformers.

Scalable-Softmax Is Superior for Attention The impact of positional encoding on length generalization in transformers

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.656333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 42a47d50-98d9-4644-ae9a-52cec5fac23c · outbound

This paper cites Reformer: The Efficient Transformer.

Scalable-Softmax Is Superior for Attention Reformer: The Efficient Transformer

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.182826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbe4dab1-c88c-4c3c-9d77-8444c61fdecd · outbound

This paper cites Gradient-based learning applied to document recognition.

Scalable-Softmax Is Superior for Attention Gradient-based learning applied to document recognition

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.187475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 088bc4d1-82ce-41e8-9d7f-dff5b338909a · outbound

This paper cites World Model on Million-Length Video And Language With Blockwise RingAttention.

Scalable-Softmax Is Superior for Attention World Model on Million-Length Video And Language With Blockwise RingAttention

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.191643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fabc220-9369-4818-93e1-06316fc0aade · outbound

This paper cites Scaling laws of ro PE -based extrapolation.

Scalable-Softmax Is Superior for Attention Scaling laws of ro PE -based extrapolation

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.632605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c0c7beda-2a5e-4b4d-8d56-43c9b9386cb7 · outbound

This paper cites and Hutter, F.

Scalable-Softmax Is Superior for Attention and Hutter, F

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.620244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 80e93c09-6eeb-4279-a265-fa4c0baf0979 · outbound

This paper cites Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation.

Scalable-Softmax Is Superior for Attention Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.204290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c07752c3-592f-4efa-a1bc-8f42f540947f · outbound

This paper cites Language models are unsupervised multitask learners.

Scalable-Softmax Is Superior for Attention Language models are unsupervised multitask learners

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.608076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 672dcff2-cfd2-4416-9f5c-87c364774549 · outbound

This paper cites SQ u AD : 100,000+ questions for machine comprehension of text.

Scalable-Softmax Is Superior for Attention SQ u AD : 100,000+ questions for machine comprehension of text

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.594186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1a5ae387-fcab-438b-8b31-4ce5dcee1a3e · outbound

This paper cites Know what you don't know: Unanswerable questions for SQ u AD.

Scalable-Softmax Is Superior for Attention Know what you don't know: Unanswerable questions for SQ u AD

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.580066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ae3452d9-32d1-47c4-827d-ca61e191e457 · outbound

This paper cites Searching for Activation Functions.

Scalable-Softmax Is Superior for Attention Searching for Activation Functions

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.220920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03b547a5-d657-48d4-a3c3-832377568d2d · outbound

This paper cites Efficient content-based sparse attention with routing transformers.

Scalable-Softmax Is Superior for Attention Efficient content-based sparse attention with routing transformers

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.565825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 22a26b0f-8430-46a5-aed1-e915167855ad · outbound

This paper cites Self-attention with relative position representations.

Scalable-Softmax Is Superior for Attention Self-attention with relative position representations

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.552563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fc8e0108-2bb8-48fb-9c18-460b87a6c619 · outbound

This paper cites GLU Variants Improve Transformer.

Scalable-Softmax Is Superior for Attention GLU Variants Improve Transformer

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.233103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af07bdd1-1197-44fe-b133-9f926d5b3124 · outbound

This paper cites R., Hestness, J., and Dey, N.

Scalable-Softmax Is Superior for Attention R., Hestness, J., and Dey, N

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.537092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7896d758-26e6-412c-820a-1a804a63671a · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.

Scalable-Softmax Is Superior for Attention Roformer: Enhanced transformer with rotary position embedding

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.240997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f87f8846-8bc2-4896-8e5a-4a95b40b0be6 · outbound

This paper cites Adaptive attention span in transformers.

Scalable-Softmax Is Superior for Attention Adaptive attention span in transformers

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.515253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e7d417f5-166c-4484-b821-73942fafef59 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Scalable-Softmax Is Superior for Attention Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.249086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d767d1a9-4b1d-47ec-9edc-964290771642 · outbound

This paper cites N., Kaiser, ., and Polosukhin, I.

Scalable-Softmax Is Superior for Attention N., Kaiser, ., and Polosukhin, I

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.502711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c72e8e0f-57f3-4f34-b4ce-a6db9d23ebcd · outbound

This paper cites Length Generalization of Causal Transformers without Position Encoding.

Scalable-Softmax Is Superior for Attention Length Generalization of Causal Transformers without Position Encoding

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.257094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bbe99af-eec7-405e-b837-61811ca41f61 · outbound

This paper cites V., and Zhou, D.

Scalable-Softmax Is Superior for Attention V., and Zhou, D

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.490700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7cb6b1d2-436f-4fab-b038-103e2a046339 · outbound

This paper cites Differential Transformer.

Scalable-Softmax Is Superior for Attention Differential Transformer

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.265036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 451730d9-5fce-48c8-bec8-057ca56429ac · outbound

This paper cites A., Ainslie, J., Alberti, C., Ontanon, S., Pham, P., Ravula, A., Wang, Q., Yang, L., and Ahmed, A.

Scalable-Softmax Is Superior for Attention A., Ainslie, J., Alberti, C., Ontanon, S., Pham, P., Ravula, A., Wang, Q., Yang, L., and Ahmed, A

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:34:01.473502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8e252d1a-4a8f-4e76-9075-1c1ec35fb147 · outbound

This paper cites and Sennrich, R.

Scalable-Softmax Is Superior for Attention and Sennrich, R

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.273009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6280ffc3-a12f-40fe-9030-78aab512c9ec · inbound

On the Mathematical Impossibility of Safe Universal Approximators cites this paper.

On the Mathematical Impossibility of Safe Universal Approximators Scalable-Softmax Is Superior for Attention

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T20:41:54.830690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecce2904-108a-4489-bac0-607d95f91640 · inbound

AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs cites this paper.

AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs Scalable-Softmax Is Superior for Attention

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T17:05:55.007461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8ec1c17-07c2-4575-b098-96245eb944d3 · inbound

Critical attention scaling in long-context transformers cites this paper.

Critical attention scaling in long-context transformers Scalable-Softmax Is Superior for Attention

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:28.867756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad89e38-fc74-4506-91b7-74b7c349c60d · inbound

Ministral 3 cites this paper.

Ministral 3 Scalable-Softmax Is Superior for Attention

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T19:12:24.763656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 547c0705-9c85-459c-bb4d-3885f7f86b6c · inbound

Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling cites this paper.

Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling Scalable-Softmax Is Superior for Attention

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-03T09:57:48.435605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation febb80e5-4542-49f1-b831-16c14a806b94 · inbound

MemDLM: Memory-Enhanced DLM Training cites this paper.

MemDLM: Memory-Enhanced DLM Training Scalable-Softmax Is Superior for Attention

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T00:43:24.547738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8214c335-6e25-4887-94e1-bca7aca29e4e · inbound

Screening Is Enough cites this paper.

Screening Is Enough Scalable-Softmax Is Superior for Attention

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-13T22:18:20.924558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7e276543-d219-40ab-870a-e97c1ee32e87 · inbound

ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models cites this paper.

ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models Scalable-Softmax Is Superior for Attention

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:26:28.046243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3a902776-13d8-420a-9934-45d5a0eca3c9 · inbound

Phoenix-VL 1.5 Medium Technical Report cites this paper.

Phoenix-VL 1.5 Medium Technical Report Scalable-Softmax Is Superior for Attention

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:01:24.890914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 87dc7db5-a504-499b-8cda-600fe95b4f51 · inbound

A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention cites this paper.

A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention Scalable-Softmax Is Superior for Attention

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T19:57:53.542250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 059d601f-3e12-4ecd-b912-7690e1872ae0 · inbound

TabPFN-3: Technical Report cites this paper.

TabPFN-3: Technical Report Scalable-Softmax Is Superior for Attention

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:10:06.047420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 45c62d5c-a0b1-49e2-907c-bd68b278b9b6 · inbound

TabPFN-3: Technical Report cites this paper.

TabPFN-3: Technical Report Scalable-Softmax Is Superior for Attention

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-01T14:25:46.516167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 48068909-0dd8-46d2-a385-e779d598b381 · inbound

Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor cites this paper.

Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor Scalable-Softmax Is Superior for Attention

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:19:42.039766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d54cc909-4148-41a9-af19-ec29a218b84a · inbound

ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory cites this paper.

ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory Scalable-Softmax Is Superior for Attention

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-04T17:09:59.047893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5924af4a-ecc5-4c0c-a99f-4170508d4130 · inbound

ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory cites this paper.

ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory Scalable-Softmax Is Superior for Attention

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-30T09:44:37.730997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 91be52e2-032d-4042-a936-f8b56196e403 · inbound

Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale cites this paper.

Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale Scalable-Softmax Is Superior for Attention

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:48:55.216961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.