Paper Citation Record · LEDGER

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs

As of 14 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2506.03077.

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

pith.paper-citation-record.v1
2506.03077 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:17:37.970701Z

measured 38 of 38 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-20T21:05:45.024226Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T21:09:02.660665Z

Reference resolution

37 of 37 outbound references displayed

verified exact1
verified fuzzy5
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ce1ef4b6-dc6c-438a-9191-552448c946c7 · outbound

This paper cites GPT-4 Technical Report.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:35.347052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a1bc54c-b3c1-4dc2-b9be-0a48a35291f0 · outbound

This paper cites Gqa: Training generalized multi-query transformer models from multi-head checkpoints.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Gqa: Training generalized multi-query transformer models from multi-head checkpoints

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:35.397085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6ac6422-7653-49a6-94ea-aa044d1ae0a8 · outbound

This paper cites Sparks of Artificial General Intelligence: Early experiments with GPT-4.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:35.485503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10f603e4-e3fe-44d3-a401-4caa62d4191a · outbound

This paper cites Training Deep Nets with Sublinear Memory Cost.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Training Deep Nets with Sublinear Memory Cost

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:35.549383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50e68872-b351-4f6b-a2ea-b6cbac7916b9 · outbound

This paper cites QLoRA: Efficient finetuning of quantized LLMs.Advances in Neural Information Processing Systems, 36, 2023.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs QLoRA: Efficient finetuning of quantized LLMs.Advances in Neural Information Processing Systems, 36, 2023

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:39.355374Z

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 8464f160-98df-44bf-a350-34d01d7099c4 · outbound

This paper cites The Llama 3 Herd of Models.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:35.688187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a0a08d-cd12-478e-94a9-8fe0c635447b · outbound

This paper cites Open R1: A fully open reproduction of deepseek-r1, January 2025.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Open R1: A fully open reproduction of deepseek-r1, January 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:39.178562Z

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 163b6c39-173b-471c-97ca-30fa4813e820 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:35.844677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 137bfbff-2e0c-4154-9c23-4dc4cf1a7223 · outbound

This paper cites LoRA: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs LoRA: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:35.915418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0645b24-f71c-4b25-ac34-00e689d4bd09 · outbound

This paper cites Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:35.974206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00f6e65c-b6cf-49aa-b499-8622ddf57d83 · outbound

This paper cites DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.055511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 086568fe-f6f3-4c8c-a795-a0e1505e67d2 · outbound

This paper cites OpenAI o1 System Card.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs OpenAI o1 System Card

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.128133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37f2a0e6-6d34-467f-a0e2-17d06eb95adb · outbound

This paper cites Adam: A Method for Stochastic Optimization.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Adam: A Method for Stochastic Optimization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.163838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 089afc44-e368-44c4-baf6-206e03341c14 · outbound

This paper cites Reducing activation recomputation in large transformer models.Proceedings of Machine Learning and Systems, 5:341–353, 2023.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Reducing activation recomputation in large transformer models.Proceedings of Machine Learning and Systems, 5:341–353, 2023

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.196477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6807fc2-30f5-4543-adcc-fee13ca3928d · outbound

This paper cites LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.286634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8316e377-e9ca-4bba-99fc-99db6a301f91 · outbound

This paper cites Sequence Parallelism: Long Sequence Training from System Perspective.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Sequence Parallelism: Long Sequence Training from System Perspective

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.333821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 887dea13-d8a6-49b2-9740-74bebe2764af · outbound

This paper cites Dora: Weight-decomposed low-rank adaptation.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Dora: Weight-decomposed low-rank adaptation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.385160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50d9730b-4d11-47c8-a9b9-7758bdcc25c5 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Understanding R1-Zero-Like Training: A Critical Perspective

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.477447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79163203-8efb-4bb8-93d8-a2665bac4e20 · outbound

This paper cites Decoupled weight decay regularization.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Decoupled weight decay regularization

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:39.038667Z

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 49f1994c-d8bb-466b-9e92-d43852bea311 · outbound

This paper cites Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:17:38.316476Z

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 01b96a64-3913-4b31-a9bb-d1fc8f587624 · outbound

This paper cites Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:38.876655Z

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 78272862-aaf3-446c-b57a-a27a901ed0f9 · outbound

This paper cites BAdam: A memory efficient full parameter optimization method for large language models.Advances in Neural Information Processing Systems, 37:24926–24958, 2024.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs BAdam: A memory efficient full parameter optimization method for large language models.Advances in Neural Information Processing Systems, 37:24926–24958, 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:17:38.708583Z

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 34fa238d-a471-43bd-a4d6-a585d826c1dc · outbound

This paper cites s1: Simple test-time scaling.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs s1: Simple test-time scaling

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.799677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c193548a-cf57-444e-b2fe-ac0e8e932dbe · outbound

This paper cites Tinyzero.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Tinyzero

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.886052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d289a50-00d3-4dce-b04c-517a15cf9229 · outbound

This paper cites ZeRO-Offload: Democratizing Billion-Scale Model Training.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs ZeRO-Offload: Democratizing Billion-Scale Model Training

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:36.966763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6697b25b-72d6-4cdc-8f82-5d4f06db5907 · outbound

This paper cites Trl: Transformer reinforce- ment learning.https://github.com/huggingface/trl, 2020.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Trl: Transformer reinforce- ment learning.https://github.com/huggingface/trl, 2020

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.023132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdfea2b3-f913-47a6-91c9-b5bd5bc89388 · outbound

This paper cites Reinforcement Learning for Reasoning in Large Language Models with One Training Example.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.098700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a6b81e-8e1b-4b63-8f3c-48e89439d978 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Chain-of-thought prompting elicits reasoning in large language models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.164737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec882aa4-946f-4bb0-924e-0ca1319546e9 · outbound

This paper cites Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.235199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa423f3e-9149-42c9-a053-5cb9e27e2421 · outbound

This paper cites an unresolved cited work.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.353885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a44ae5d8-89b5-4f76-af6a-b4533feaaa14 · outbound

This paper cites Qwen2.5 Technical Report.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Qwen2.5 Technical Report

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.412316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b920b99-fc98-4c36-a5b0-9bf5f8dff18a · outbound

This paper cites LIMO: Less is More for Reasoning.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs LIMO: Less is More for Reasoning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.467105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 093f2445-c691-4609-9806-fc18ae34f1e2 · outbound

This paper cites Demystifying Long Chain-of-Thought Reasoning in LLMs.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Demystifying Long Chain-of-Thought Reasoning in LLMs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.522534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d3da582-05a5-4454-8db3-fe030f03c885 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.613949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 845f3139-907f-4c8e-81c9-188f64adc75d · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.752175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bf4bb70-508f-4448-abfc-112fdcb2806b · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.858509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd5fd556-5431-438c-8f11-dcfccaef5494 · outbound

This paper cites GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.970701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5ff6b850-2079-4cb7-9d0e-ae335982c396 · inbound

Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking cites this paper.

Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-20T21:09:02.662223Z

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.