Pith. sign in

Paper Citation Record · LEDGER

Minute-Long Videos with Dual Parallelisms

As of 18 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2505.21070.

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

pith.paper-citation-record.v1
2505.21070 v2

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:45:28.834534Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

30 of 30 outbound references displayed

  • verified exact0
  • verified fuzzy15
  • unresolved15
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 51c00cee-45eb-49f5-9bc9-48dfa9f2e2d0 · outbound

This paper cites Block diffusion: Interpolating between autoregressive and diffusion language models.

Minute-Long Videos with Dual Parallelisms Block diffusion: Interpolating between autoregressive and diffusion language models

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:31.503682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:26.871786Z digest=sha256:44b6ea39e802f4fa33e00628efb3373d1d3b658c863eba1f9587540d4fc9395f

Observation ff4af4ea-8194-45b7-9961-d30e7bc1b404 · outbound

This paper cites All are worth words: A vit backbone for diffusion models.

Minute-Long Videos with Dual Parallelisms All are worth words: A vit backbone for diffusion models

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:31.353496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:26.925869Z digest=sha256:9c2f6ec59856c8d02293043536125ab851ac2835d420b32a5dbecccf0422cd05

Observation 01359bea-e730-4d5b-835a-c139a1e7ebf4 · outbound

This paper cites Videocrafter1: Open diffusion models for high-quality video generation, 2023.

Minute-Long Videos with Dual Parallelisms Videocrafter1: Open diffusion models for high-quality video generation, 2023

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:26.996822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:26.996822Z digest=sha256:b397dc13d1aaa9ac50c4e589e7bfa1f33c9f62155736e05c9948cfd45b76cba2

Observation 22dc709b-07dc-49ea-9b00-48e187093ce0 · outbound

This paper cites Videocrafter2: Overcoming data limitations for high-quality video diffusion models.

Minute-Long Videos with Dual Parallelisms Videocrafter2: Overcoming data limitations for high-quality video diffusion models

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:31.181767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:27.084254Z digest=sha256:4e90c82ecd994aed5410f3e75f7c1ca2781576cc195ce552c825774a8401a86d

Observation 7a03318c-a321-4bdf-94b4-7a63581dd382 · outbound

This paper cites xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism.

Minute-Long Videos with Dual Parallelisms xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:27.138943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:27.138943Z digest=sha256:90c5d52384c53318bc1d42160d972bccbe473eee80827a19a427f65afdc0da0d

Observation 78fdaa28-44c8-426a-b085-67d4cf611067 · outbound

This paper cites PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference.

Minute-Long Videos with Dual Parallelisms PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:27.198549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:27.198549Z digest=sha256:f1e7060abee8c31ced5f541356db8ef18ba28c22db9856fa049fef1789183538

Observation 06f53c24-e72c-425d-bf15-82599715ce59 · outbound

This paper cites Denoising diffusion probabilistic models.

Minute-Long Videos with Dual Parallelisms Denoising diffusion probabilistic models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:27.250535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:27.250535Z digest=sha256:752aec6be7342fd559b2910bf9e30e373dee4f87f0b34285137eb98a7d74d5ae

Observation bed4473b-4274-433a-b82c-17209224877f · outbound

This paper cites Cogvideo: Large-scale pretraining for text-to-video generation via transformers.

Minute-Long Videos with Dual Parallelisms Cogvideo: Large-scale pretraining for text-to-video generation via transformers

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:31.050086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:27.311001Z digest=sha256:a012063c92d60110687727d90196b4fa13409e5a09af755f492ba984e9151281

Observation 4a0866f3-ecac-4575-9b70-7eb9789c21fa · outbound

This paper cites Gpipe: Efficient training of giant neural networks using pipeline parallelism.

Minute-Long Videos with Dual Parallelisms Gpipe: Efficient training of giant neural networks using pipeline parallelism

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:30.895833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:27.366494Z digest=sha256:8790a52693f5351abee3d03b224bb1f8fbd566aa38050450f1cc7074db762447

Observation b3feba87-8545-428c-aafd-fda62ae7a666 · outbound

This paper cites VBench: Comprehensive benchmark suite for video generative models.

Minute-Long Videos with Dual Parallelisms VBench: Comprehensive benchmark suite for video generative models

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:27.439067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:27.439067Z digest=sha256:816066c9c1121242bb89b0348aba185d4a6765854b6aff430eaf73970ee96d16

Observation c80ae0b7-2ca4-4c79-97a9-e3237c7ed67e · outbound

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

Minute-Long Videos with Dual Parallelisms DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:27.503078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:27.503078Z digest=sha256:7394cf188747e76e34da0d40598c4e66b014e65b381056069571941c8317165e

Observation ea15885b-467e-4456-88d6-62a0a2ae2ea6 · outbound

This paper cites Fifo-diffusion: Generating infinite videos from text without training.

Minute-Long Videos with Dual Parallelisms Fifo-diffusion: Generating infinite videos from text without training

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:30.742932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:27.553782Z digest=sha256:144c6e04007c758415fd41435593b493b93de34f189e0a74d2b157ef2951be13

Observation 6d58535e-b2b3-4bfe-ba15-85702bb57a68 · outbound

This paper cites HunyuanVideo: A Systematic Framework For Large Video Generative Models.

Minute-Long Videos with Dual Parallelisms HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:27.624670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:27.624670Z digest=sha256:4c66a9b934ff7481ba32bcfecb9f9d1300f2148dc40f9829adc290248c529fef

Observation 4c7a99e7-ca41-49cb-ab31-c6cfa78cd3f6 · outbound

This paper cites T2v-turbo: Breaking the quality bottleneck of video consistency model with mixed reward feedback.

Minute-Long Videos with Dual Parallelisms T2v-turbo: Breaking the quality bottleneck of video consistency model with mixed reward feedback

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:30.576901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:27.690239Z digest=sha256:41dfdd2a031e9e879384c55fea3be820efc8d3d99fdd430a6b61574191f7080c

Observation 87e36d89-bd69-4968-a874-ab0e2b9e3419 · outbound

This paper cites T2v-turbo-v2: Enhancing video generation model post-training through data, reward, and conditional guidance design.

Minute-Long Videos with Dual Parallelisms T2v-turbo-v2: Enhancing video generation model post-training through data, reward, and conditional guidance design

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:30.439169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:27.744974Z digest=sha256:b465070f3567586cacff8c58833db6ddf9586bd09ed7b8663a7ff0ea9fd335b3

Observation d12c7c96-f88c-4e95-ba7d-998d5c7205c8 · outbound

This paper cites Terapipe: Token-level pipeline parallelism for training large-scale language models.

Minute-Long Videos with Dual Parallelisms Terapipe: Token-level pipeline parallelism for training large-scale language models

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:30.270214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:27.842456Z digest=sha256:d25459921f94d27ab6775b28e2fc10e7defbe1fea31e799e450ef8cee0834e49

Observation 243e9872-d7e3-4df0-93d3-9ee414c14d82 · outbound

This paper cites Ring Attention with Blockwise Transformers for Near-Infinite Context.

Minute-Long Videos with Dual Parallelisms Ring Attention with Blockwise Transformers for Near-Infinite Context

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:27.910056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:27.910056Z digest=sha256:9f1bb5a4c38a9574bdcf20c12be2ea7c5c10747b93506e5f2ccf59b783872fde

Observation 0bf4c706-e724-448c-975e-e3618d5d9549 · outbound

This paper cites Scalable diffusion models with transformers.

Minute-Long Videos with Dual Parallelisms Scalable diffusion models with transformers

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:27.980773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:27.980773Z digest=sha256:70cacefd5c8ac64e70c40ba450501b807c7b547efccca764647a7c97ffcf72af

Observation 2e5a897e-57a6-4b54-862e-e9c1df1ae115 · outbound

This paper cites Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k.

Minute-Long Videos with Dual Parallelisms Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:28.060326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:28.060326Z digest=sha256:a2319b540a4c02f7c1b2c27a15bf26e344283765fdd0eb923eb63f0483dc3cb0

Observation 6f483f4b-a9af-4c53-80d5-3094463be792 · outbound

This paper cites Zero bubble (almost) pipeline parallelism.

Minute-Long Videos with Dual Parallelisms Zero bubble (almost) pipeline parallelism

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:30.130147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:28.134238Z digest=sha256:0db4dc9c8c50781dadb1ae63f68892e07bdbc2d3cbeeecd87d93ce08d0af3b92

Observation de7cfed2-61e4-4b04-b27e-2ceffcf8bb94 · outbound

This paper cites Freenoise: Tuning-free longer video diffusion via noise rescheduling.

Minute-Long Videos with Dual Parallelisms Freenoise: Tuning-free longer video diffusion via noise rescheduling

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:29.954717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:28.211950Z digest=sha256:8f92d2790b0da70867f9a22603f518df9c6d77a8907dba36d47b5264a6aacf86

Observation 96b5cd7a-cf6f-43e3-b66b-aa925253a59c · outbound

This paper cites Rolling diffusion models.

Minute-Long Videos with Dual Parallelisms Rolling diffusion models

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:29.745132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:28.293059Z digest=sha256:4fe7051a5bd30b78b9df8a81372ba0a65798b400d5dde553733815b2ba1458d1

Observation 707d5c50-9b0a-4232-99e6-e5a16a5d9608 · outbound

This paper cites Magi-1: Autoregressive video generation at scale, 2025.

Minute-Long Videos with Dual Parallelisms Magi-1: Autoregressive video generation at scale, 2025

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:28.354570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:28.354570Z digest=sha256:3385d2feb3cb77bffe69592cd083557644cdb6755ea26eec3435dddf635294ec

Observation eb28f25d-233d-4ce2-bf24-ec788f30317c · outbound

This paper cites Megatron-lm: Training multi-billion parameter language models using model parallelism, 2020.

Minute-Long Videos with Dual Parallelisms Megatron-lm: Training multi-billion parameter language models using model parallelism, 2020

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:28.429065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:28.429065Z digest=sha256:0be0b204db758c6d3986727dfb9966d4fde95769074b26a5e59b04447de79645

Observation f274b9db-7396-4107-b29e-ff9e647aadd9 · outbound

This paper cites Video-Infinity: Distributed Long Video Generation.

Minute-Long Videos with Dual Parallelisms Video-Infinity: Distributed Long Video Generation

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:28.480508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:28.480508Z digest=sha256:0fce9bc746acac5b1531bdda1fa0de5ee26cdee8d7943e09b606e9a414206577

Observation a785b0a2-d4c6-41d1-87c4-16cf1806ee4a · outbound

This paper cites Attention is all you need.

Minute-Long Videos with Dual Parallelisms Attention is all you need

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:29.567804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:28.553468Z digest=sha256:a3001bdd2cafa90e272d5b770a498e69469f0f7c7fcc771bcf1aad41823b41f4

Observation 5f01cfa0-ecad-4f7e-b1fc-0a7dfc54f6a1 · outbound

This paper cites Wan: Open and advanced large-scale video generative models, 2025.

Minute-Long Videos with Dual Parallelisms Wan: Open and advanced large-scale video generative models, 2025

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:29.397490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:28.627505Z digest=sha256:ebea75beed6e6d84136e8b3e5aec37ae58e84df9911e073df0611abc991028b2

Observation 776649de-6ff1-42e4-a669-9043ecb76cf9 · outbound

This paper cites Cogvideox: Text-to-video diffusion models with an expert transformer.

Minute-Long Videos with Dual Parallelisms Cogvideox: Text-to-video diffusion models with an expert transformer

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:45:29.249558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-07T13:45:28.695280Z digest=sha256:e01647429719871b9a6a6146b44ea573703420255cfdac4e121d2d7cac36b8d2

Observation 668457ec-3fe6-450b-ac49-16570d0d76c8 · outbound

This paper cites VideoMerge: Towards Training-free Long Video Generation.

Minute-Long Videos with Dual Parallelisms VideoMerge: Towards Training-free Long Video Generation

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:28.775696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:28.775696Z digest=sha256:7a28fd196a13c3a12e32ce264eee73df720c8890f42eaa39312c8d183ac803ea

Observation c46993f9-da4a-4aad-864d-d00016a162c2 · outbound

This paper cites Open-Sora: Democratizing Efficient Video Production for All.

Minute-Long Videos with Dual Parallelisms Open-Sora: Democratizing Efficient Video Production for All

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T13:45:28.834534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:45:28.834534Z digest=sha256:40a95fe21c48aeeb91f77a9cc5882c13f653126c228749762e2de6e49a52afe8

Pith citing papers

No inbound Pith citation observations are available.