Paper Citation Record · LEDGER

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks

As of 14 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2602.17254.

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

pith.paper-citation-record.v1
2602.17254 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T22:21:56.408830Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T15:48:34.312616Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T16:33:39.630527Z

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy0
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 322e5e0a-a9c6-483c-90c4-2f4cde2f6d4d · outbound

This paper cites Evensky, Joseph P.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Evensky, Joseph P

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:52.134044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f46b8c8-d753-4284-8cf3-2a5a2025c5e3 · outbound

This paper cites Adiga and G.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Adiga and G

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:52.209068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a79478f-ba98-46ff-aa4b-ad572f96904d · outbound

This paper cites Chris Erway, José E.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Chris Erway, José E

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:52.276309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89e47ed5-3236-42f6-a737-bad7d72ed947 · outbound

This paper cites Language models are few-shot learners.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Language models are few-shot learners

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:52.352631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77ae33fe-32dc-4d75-ac49-a1291f5cfcde · outbound

This paper cites Efficient algorithms for all-to-all communications in multi-port message-passing systems.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Efficient algorithms for all-to-all communications in multi-port message-passing systems

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:52.427315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3b71ee7-e723-4cc3-b115-7889a8fb6152 · outbound

This paper cites Synthesizing optimal collective algorithms.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Synthesizing optimal collective algorithms

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:52.539553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d231c2d-ccda-4cbc-8d77-5c6e196dc8b2 · outbound

This paper cites Syccl: Exploiting symmetry for efficient collective communication scheduling.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Syccl: Exploiting symmetry for efficient collective communication scheduling

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:52.657307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 887b1f97-7035-4e1b-91eb-fcd292762609 · outbound

This paper cites Collective communication on architectures that support simultaneous communication over multiple links.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Collective communication on architectures that support simultaneous communication over multiple links

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:52.818036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 496e95d0-d97a-4207-a0b5-d60a0f18ec2a · outbound

This paper cites InSC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pages 386–400, 2018.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks InSC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pages 386–400, 2018

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:52.918258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0cb7cc1-a1db-4d3f-bc0c-b0946d11ba86 · outbound

This paper cites Canary: Congestion-aware in-network allreduce using dynamic trees.Future Generation Computer Systems, 152:70–82, 2024.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Canary: Congestion-aware in-network allreduce using dynamic trees.Future Generation Computer Systems, 152:70–82, 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:53.004734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a2aa6a8-989b-4526-90fa-d03c97e0a31a · outbound

This paper cites InProceedings of the 36th ACM International Conference on Supercomputing, ICS ’22.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks InProceedings of the 36th ACM International Conference on Supercomputing, ICS ’22

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:53.286790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05eb34e1-06b7-4708-929c-dbb649f90ed7 · outbound

This paper cites Distributed training of large language models on aws trainium.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Distributed training of large language models on aws trainium

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:53.442089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6b383cf-15d3-4baf-8fa8-3f9fc34afd9b · outbound

This paper cites an unresolved cited work.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:53.531861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f0434ef-4e3f-4f48-b5f4-561fb83c2890 · outbound

This paper cites Hammingmesh: A network topology for large-scale deep learning.Commun.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Hammingmesh: A network topology for large-scale deep learning.Commun

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:53.646442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e91d508-9329-404e-8ab9-b356dc4c3af2 · outbound

This paper cites Optimal bucket algorithms for large mpicollectivesontorusinterconnects.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Optimal bucket algorithms for large mpicollectivesontorusinterconnects

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:53.734139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cc1f96d-b1ed-4fd5-88c6-f0a90e039b2e · outbound

This paper cites A simulator for large-scale parallel computer architectures.International Journal of Distributed Systems and Technologies (IJDST), 1(2):57–73, 2010.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks A simulator for large-scale parallel computer architectures.International Journal of Distributed Systems and Technologies (IJDST), 1(2):57–73, 2010

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:53.791515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21c9782-6cd9-4dbc-899b-115fdb9b9860 · outbound

This paper cites Pat: a new algorithm for all-gather and reduce-scatter operations at scale, 2025.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Pat: a new algorithm for all-gather and reduce-scatter operations at scale, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:53.866620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f837824-bc38-4862-be69-e932e803e926 · outbound

This paper cites An optimisation of allreduce communication in message-passing systems.Parallel Computing, 107:102812, 2021.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks An optimisation of allreduce communication in message-passing systems.Parallel Computing, 107:102812, 2021

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:53.972623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1da77d29-20b5-4ea4-a8be-bf766bc98b10 · outbound

This paper cites Tpuv4:Anopticallyreconfigurablesupercomputerforma- chine learning with hardware support for embeddings.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Tpuv4:Anopticallyreconfigurablesupercomputerforma- chine learning with hardware support for embeddings

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.047483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45831edb-248b-4a05-a5fb-89fdfdc1c8cf · outbound

This paper cites Tpuv4:Anopticallyreconfigurablesupercomputerformachine learning with hardware support for embeddings.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Tpuv4:Anopticallyreconfigurablesupercomputerformachine learning with hardware support for embeddings

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.174744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 202d7521-bc28-4ca3-87b2-1401560ee836 · outbound

This paper cites An in-networkarchitectureforacceleratingshared-memorymultiprocessor collectives.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks An in-networkarchitectureforacceleratingshared-memorymultiprocessor collectives

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.272305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83274d9d-5e32-4da2-a8bd-7a79135295bf · outbound

This paper cites A Generalization of the Allreduce Operation.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks A Generalization of the Allreduce Operation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.349272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b172be75-4911-4f9c-9b8e-eacc76bb27ce · outbound

This paper cites Understanding com- munication characteristics of distributed training.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Understanding com- munication characteristics of distributed training

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.453625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a675e45-f4b2-4f27-b6d8-bdeebe112276 · outbound

This paper cites Resccl: Resource- efficient scheduling for collective communication.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Resccl: Resource- efficient scheduling for collective communication

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.560436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4109228a-2cbf-4c15-ba8c-54b8367fd1c1 · outbound

This paper cites Rethinking machine learning collective communication as a multi- commodityflowproblem.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Rethinking machine learning collective communication as a multi- commodityflowproblem

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.638758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bd17811-2af4-4c97-897c-8230a814d8d7 · outbound

This paper cites Paard: Proximity-aware all-reduce communication for dragonfly networks.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Paard: Proximity-aware all-reduce communication for dragonfly networks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.859808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e408c83-f66c-4233-968b-49fea9f0f0fc · outbound

This paper cites Efficient large-scale language model training on gpu clusters using megatron-lm.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Efficient large-scale language model training on gpu clusters using megatron-lm

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.982016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05f89a51-3c66-4b93-b1d3-af551d714ae6 · outbound

This paper cites Bandwidthoptimalall-reducealgorithms for clusters of workstations.Journal of Parallel and Distributed Computing, 69:117–124, 02 2009.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Bandwidthoptimalall-reducealgorithms for clusters of workstations.Journal of Parallel and Distributed Computing, 69:117–124, 02 2009

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.068145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3756497-7c6f-49a4-bfcf-87fd9f1d6f57 · outbound

This paper cites Automatic mpi counter profiling of all users: First results on a cray t3e 900-512.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Automatic mpi counter profiling of all users: First results on a cray t3e 900-512

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.142864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b23b78c1-5f05-46ce-8d1a-6ab2a1d1ed9b · outbound

This paper cites Optimization of collective reduction operations.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Optimization of collective reduction operations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.256086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fb3da22-3769-47ba-a9f0-1b358135b026 · outbound

This paper cites Rico-Gallego, Juan C.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Rico-Gallego, Juan C

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.342219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcd8cdb8-76c9-4019-b876-92003f1ff019 · outbound

This paper cites Generalisation of recursive doubling for allreduce: Now with simulation.Parallel Computing, 69:24–44, 2017.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Generalisation of recursive doubling for allreduce: Now with simulation.Parallel Computing, 69:24–44, 2017

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.416050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d5195c4-f741-4b89-8c96-1e3eac3d4715 · outbound

This paper cites Collective algorithms for multiported torus networks.ACM Trans.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Collective algorithms for multiported torus networks.ACM Trans

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.492669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e6d533-0dcb-4afa-b86b-6c58b5482aba · outbound

This paper cites Swing: Short-cutting rings for higher bandwidth allreduce.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Swing: Short-cutting rings for higher bandwidth allreduce

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.568421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ca4331c-49d2-48a3-b9e4-4af643c9956f · outbound

This paper cites TACCL: Guiding collective algorithm synthesis using communication sketches.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks TACCL: Guiding collective algorithm synthesis using communication sketches

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.661413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d9932b0-00c7-430e-a7b4-ce268ad05652 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.729564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 652c6504-58f1-4d9a-92c0-8cb7daca7882 · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks LaMDA: Language Models for Dialog Applications

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.804757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea0eb7c0-3e45-4338-94a2-d80e27e9ea27 · outbound

This paper cites Decomposing mpi collectives for exploiting multi-lane communication.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Decomposing mpi collectives for exploiting multi-lane communication

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:55.882781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61ce2e87-45a9-4a02-b617-374aa2d36497 · outbound

This paper cites Enabling next-generation ai work- loads: Announcing tpu v5p and ai hypercomputer.Google Cloud, December, 6, 2023.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Enabling next-generation ai work- loads: Announcing tpu v5p and ai hypercomputer.Google Cloud, December, 6, 2023

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:56.012272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f815212-b5e8-4517-a69b-9d1091ecf1d6 · outbound

This paper cites TopoOpt: Co-optimizing network topology and parallelization strategy for distributed training jobs.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks TopoOpt: Co-optimizing network topology and parallelization strategy for distributed training jobs

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:56.119673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea90c4cf-bed2-4309-a24d-27464a62b243 · outbound

This paper cites Efficient direct-connect topologies for collective communications, 2025.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Efficient direct-connect topologies for collective communications, 2025

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:56.197015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf80ddd8-8d1f-4441-b80e-2f0765f0889a · outbound

This paper cites Resiliencyatscale:Managinggoogle’stpuv4machine learning supercomputer.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Resiliencyatscale:Managinggoogle’stpuv4machine learning supercomputer

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:56.314548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f31d6a9-76f7-4ba5-ae78-5591f5702d43 · outbound

This paper cites Bruck’s data transmission follows the same pattern asTrivance, but in step𝑘 the communication distances are 3𝑘 and 2·3 𝑘, resulting in a total congestion of3·3 𝑘 per step.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Bruck’s data transmission follows the same pattern asTrivance, but in step𝑘 the communication distances are 3𝑘 and 2·3 𝑘, resulting in a total congestion of3·3 𝑘 per step

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:56.408830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a1f4b2-9619-448d-afc2-bafe0b4507a8 · outbound

This paper cites an unresolved cited work.

Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T22:21:54.744011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9ce84a0c-cfb6-4d44-a194-7c668820466e · inbound

Bridge: Optimizing Collective Communication Schedules in Reconfigurable Networks with Reusable Subrings cites this paper.

Bridge: Optimizing Collective Communication Schedules in Reconfigurable Networks with Reusable Subrings Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-13T01:18:02.798775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ef7de534-e9e6-476f-9f80-79a81e85f8aa · inbound

Revisiting Bruck: Phase-Efficient All-to-All Communication in Reconfigurable Networks cites this paper.

Revisiting Bruck: Phase-Efficient All-to-All Communication in Reconfigurable Networks Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-13T01:18:02.798775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.