Pith. sign in

Paper Citation Record · LEDGER

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget

As of 22 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2608.00916.

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

pith.paper-citation-record.v1
2608.00916 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:19:57.021979Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:29:38.808865Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-14T04:29:40.218615Z

Reference resolution

18 of 18 outbound references displayed

  • verified exact0
  • verified fuzzy3
  • unresolved15
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2b1b7386-c881-411e-88f2-7b4a3b618556 · outbound

This paper cites An analysis of the softmax cross entropy loss for learning-to-rank with binary relevance.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget An analysis of the softmax cross entropy loss for learning-to-rank with binary relevance

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:19:57.671133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-15T15:19:56.921058Z digest=sha256:e7af76efdf81770c1c1df3d97ba418a55e031c3ccf279b6064937b4eda31b20a

Observation 724eb3df-4316-4e26-a201-7e4e82e607f1 · outbound

This paper cites doi: 10.18653/v1/N19-1423.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget doi: 10.18653/v1/N19-1423

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.941134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.941134Z digest=sha256:8c22e4a30cbc0dd6477e673185acfc250724fa002413c853b2f1d6c086ae6852

Observation f94376d3-ab03-4212-bca5-fd212fccbdab · outbound

This paper cites ISBN 9798400702297.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget ISBN 9798400702297

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.962490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.962490Z digest=sha256:9126fadd45bf019463e66983242046ec62037240a161e308843f672d8b0022ee

Observation 8ce7cb27-774f-433e-b1a3-eb0960db8f56 · outbound

This paper cites doi: 10.18653/v1/2023.eacl-main.148.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget doi: 10.18653/v1/2023.eacl-main.148

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.972421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.972421Z digest=sha256:dd3c563373f33bc736d3cc8d659e23c28a572d462cfe8afb12aa881c130419e7

Observation 4089f6ae-94cf-411e-b9dd-ee1ff81b2fe7 · outbound

This paper cites Training Sparse Mixture Of Experts Text Embedding Models.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget Training Sparse Mixture Of Experts Text Embedding Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.977576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.977576Z digest=sha256:d3a4e28249324c8574538545ead8eeb48617660337980f40f5aaaee55c643d7c

Observation 9bf43e2a-61e5-4a9e-b407-11465ca84cab · outbound

This paper cites Nandan Thakur, Crystina Zhang, Xueguang Ma, and Jimmy Lin.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget Nandan Thakur, Crystina Zhang, Xueguang Ma, and Jimmy Lin

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:19:57.638192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-15T15:19:56.988218Z digest=sha256:8776d4c88c8bb52998ae21512e7002ebf27a1ee1574130a111389b8dd2c766c5

Observation a716e7cf-8718-4ab4-b8ed-99e36ae0cb47 · outbound

This paper cites ISBN 979-8-89176-335-7.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget ISBN 979-8-89176-335-7

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.994896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.994896Z digest=sha256:b5a1411c2c8b65a9520dca98ff59f0f18efc34d0fd9221b454a1acb8ab83e913

Observation 321a364c-51be-4e0e-98f7-85e9c8678442 · outbound

This paper cites Qwen3 Technical Report.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget Qwen3 Technical Report

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:57.006912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:57.006912Z digest=sha256:a940c441b0bcdb8f07b0ea242167eb6ecbddaac6ccbe6175b937d3a17daa6cc3

Observation 9b1b8dac-766d-4cd4-afec-cff2dec0d4d2 · outbound

This paper cites PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:57.011920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:57.011920Z digest=sha256:3f33485bad7ee4e95ec6f396344980bb6d9472c69ca2d13d1b68b523d99953bd

Observation 4eca2777-0553-4a31-9401-146dd8933b7e · outbound

This paper cites ISBN 9781450394086.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget ISBN 9781450394086

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:57.017313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:57.017313Z digest=sha256:0ea82845bf81a767e2bc2e4901683873ec6befb5cc65b07825ed7e91c69b1724

Observation c7bfd27f-81ba-4522-af7a-ec5a028f0ead · outbound

This paper cites BERT: Pre-training of deep bidirectional transformers for language understanding.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget BERT: Pre-training of deep bidirectional transformers for language understanding

Reference 2007

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T15:19:57.654346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-15T15:19:56.934607Z digest=sha256:1ddaeb36abb1e99304c22bd8a890f51aeb03fea316bbea1658c53d667663cd18

Observation bfa43bc7-bbbf-42f0-9c0c-4686a017515a · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget Distilling the Knowledge in a Neural Network

Reference 2015

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.951825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.951825Z digest=sha256:c529b8b2fb51256f63a5f42dfb26ccb2e724259b1c99991de698c97f12f76bc4

Observation 2af49506-06af-48f2-9bd3-8a93c4c9089e · outbound

This paper cites ISBN 9781450368810.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget ISBN 9781450368810

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.928509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.928509Z digest=sha256:84e8f0cf68f6902239fbe0a8307e4ba5b451ccb24e54233b149ce53432b4da25

Observation 87332fdc-d520-46f8-97fa-99fcb1c63f01 · outbound

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

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.982884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.982884Z digest=sha256:eee00dacb3507f63b5d446296534a944d29c3e49bce02b83d7d7cf8e88731c0b

Observation d6b9cbee-1daa-4f6c-a49a-aabec76e65a5 · outbound

This paper cites Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.957244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.957244Z digest=sha256:cec62c47d6bd3f46bd4cbeca727dc7e2a67abf7eb409632ada31d2edc7408e82

Observation d5b05c4b-3e3c-4f3a-a908-33f475905f8a · outbound

This paper cites ISBN 9781450394086.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget ISBN 9781450394086

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.946572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.946572Z digest=sha256:4a2e4a7fa8963ad90fbe366a059484d42d49fb5e3059eb96697194c7304624da

Observation 85299f75-fb8a-4c2b-beba-9b4b682a0eff · outbound

This paper cites ISBN 9798400715921.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget ISBN 9798400715921

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:56.967088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:56.967088Z digest=sha256:6c95bbb8a4dfe5e3c04664d686d7d03f6355a99c9203be0155f95277ff2d5631

Observation eac891cd-f4fd-465c-8daa-c98885814530 · outbound

This paper cites ISBN 9798400725999.

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget ISBN 9798400725999

Reference 2026

Resolution
unresolved
no resolver link, observed 2026-08-15T15:19:57.021979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T15:19:57.021979Z digest=sha256:e0bac835384c447474d30eb3f27e729bacf546a5bb5696a33fb909a60cdd9eee

Pith citing papers

Observation 59653820-817d-4b26-b635-45b43d6d1a2b · inbound

Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers cites this paper.

Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget

Reference 193

Resolution
verified exact
local_arxiv, observed 2026-08-14T04:29:40.227600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-14T04:29:38.808865Z digest=sha256:a4e9f422f0a4a28f739a7d4900fb7625723d576a4d097efcf3314c02ea8d7eea