Paper Citation Record · LEDGER

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models

As of 4 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2605.06070.

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

pith.paper-citation-record.v1
2605.06070 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-08T14:16:55.945455Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+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

43 of 43 outbound references displayed

verified exact12
verified fuzzy31
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5f5b3b81-1e4c-4364-b325-10d6827dc961 · outbound

This paper cites A general theoretical paradigm to understand learning from human preferences.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models A general theoretical paradigm to understand learning from human preferences

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.412722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ec1b893c-abd4-4653-afb9-bb44f553707b · outbound

This paper cites Improving image generation with better captions.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Improving image generation with better captions

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.388935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5521c809-cbdb-445d-b464-69a977195e03 · outbound

This paper cites Flux.https://github.com/black-forest-labs/flux.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Flux.https://github.com/black-forest-labs/flux

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.404342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 68e4d14d-be81-419d-bead-e515744f43c5 · outbound

This paper cites Rank analysis of incomplete block designs: I.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Rank analysis of incomplete block designs: I

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.397283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d04aa348-0a63-4502-83fd-894967313d06 · outbound

This paper cites Getting it right: Improving spatial consistency in text-to-image models.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Getting it right: Improving spatial consistency in text-to-image models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.384728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation dc56eb4a-9228-4224-9c1e-971487087908 · outbound

This paper cites PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-12T20:38:53.511834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation db8749f2-ac0a-4512-807f-ed314c8112d1 · outbound

This paper cites Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.393260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ebb6822d-9445-4050-9fdd-4ba2ef133b2e · outbound

This paper cites Diffusion models in vision: A survey.IEEE transactions on pattern analysis and machine intelligence, 45 (9):10850–10869.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Diffusion models in vision: A survey.IEEE transactions on pattern analysis and machine intelligence, 45 (9):10850–10869

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.400942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4a33e5ab-48d6-4ad1-bb9e-295e63f2edaf · outbound

This paper cites Diffusion-sdpo: Safeguarded direct preference optimization for diffusion models.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Diffusion-sdpo: Safeguarded direct preference optimization for diffusion models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:41:12.215672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d3f91091-249c-4662-8fd7-2456a092b47e · outbound

This paper cites Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.409142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f72747d1-10f4-4996-ba31-33669d44ee40 · outbound

This paper cites Margin- aware preference optimization for aligning diffusion models without reference.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Margin- aware preference optimization for aligning diffusion models without reference

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.455564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6bc1ae61-9448-40f4-8d10-7239fdf29003 · outbound

This paper cites John wiley & sons.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models John wiley & sons

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.451822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0be4d1ea-602b-409a-8ebe-8040a316057c · outbound

This paper cites Elucidating the design space of diffusion-based generative models.Advances in neural information processing systems, 35: 26565–26577.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Elucidating the design space of diffusion-based generative models.Advances in neural information processing systems, 35: 26565–26577

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.433742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4658ae27-2910-4f83-9f5e-2b30728b10c7 · outbound

This paper cites Scalable ranked preference optimization for text-to-image generation.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Scalable ranked preference optimization for text-to-image generation

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.444833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 39b3ad83-2438-436b-a699-e9e4574be719 · outbound

This paper cites Pick-a-pic: An open dataset of user preferences for text-to-image generation.Advances in neural information processing systems, 36:36652–36663.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Pick-a-pic: An open dataset of user preferences for text-to-image generation.Advances in neural information processing systems, 36:36652–36663

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.469390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8a743779-e94e-4605-96c6-ffd7498d8458 · outbound

This paper cites arXiv preprint arXiv:2507.07510 , year=.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models arXiv preprint arXiv:2507.07510 , year=

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:41:12.151668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 74d5a422-4e92-474a-9d2a-3b536359e33b · outbound

This paper cites Align- ing diffusion models by optimizing human utility.Advances in Neural Information Processing Systems, 37:24897–24925.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Align- ing diffusion models by optimizing human utility.Advances in Neural Information Processing Systems, 37:24897–24925

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.462985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cc9bc20c-2e28-4861-a575-c6b2e3f79480 · outbound

This paper cites K-sort eval: Efficient preference evaluation for visual genera- tion via corrected vlm-as-a-judge.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models K-sort eval: Efficient preference evaluation for visual genera- tion via corrected vlm-as-a-judge

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.466264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c5726001-85b7-48c0-ae9c-d61204f8121d · outbound

This paper cites K-sort arena: Efficient and reliable benchmarking for generative models via k-wise human preferences.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models K-sort arena: Efficient and reliable benchmarking for generative models via k-wise human preferences

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.440740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 42836f56-de22-4aab-a351-6116e3089ba9 · outbound

This paper cites Flow Matching for Generative Modeling.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Flow Matching for Generative Modeling

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:41:12.145120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6054ba67-3f2f-4386-b8aa-7c3393b94121 · outbound

This paper cites Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:41:12.158173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation dfb3a2a3-8f6f-478a-8baa-fc43ffc0d84f · outbound

This paper cites Hpsv3: Towards wide-spectrum hu- man preference score.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Hpsv3: Towards wide-spectrum hu- man preference score

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.437527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3a5b050b-1d52-4000-a131-5b81e3e749ee · outbound

This paper cites Scalable diffusion models with transformers.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Scalable diffusion models with transformers

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.459345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fd4e28b6-614d-4349-8cb6-605d89cdb507 · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:41:12.191002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 45aa5059-00e1-4323-896d-c3d1d789cbb4 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Learning transferable visual models from natural language supervision

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.430478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d98c7217-949e-41a8-bce8-9e51dcca37a5 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Direct preference optimization: Your language model is secretly a reward model

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.419907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a05ffff9-9e02-43a7-9423-35f9a95a0df3 · outbound

This paper cites High- resolution image synthesis with latent diffusion models.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models High- resolution image synthesis with latent diffusion models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.423678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d6c7e423-e72c-48c7-8f23-cc9bd4ec895d · outbound

This paper cites LAION-Aesthetics: Predicting the aesthetic quality of images.https://laion.ai/blog/laion-aesthetics/.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models LAION-Aesthetics: Predicting the aesthetic quality of images.https://laion.ai/blog/laion-aesthetics/

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.426900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 94d33e79-16fb-4d24-bfa0-aa38d920690c · outbound

This paper cites Proximal Policy Optimization Algorithms.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Proximal Policy Optimization Algorithms

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:41:12.196535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3410b3e5-293f-4f09-a933-a54a2c7cf25c · outbound

This paper cites Freeu: Free lunch in diffusion u-net.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Freeu: Free lunch in diffusion u-net

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.472677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 659d5408-c724-4187-8d8c-83cf3ac29f6a · outbound

This paper cites Generative modeling by estimating gradients of the data distribution.Advances in neural information processing systems, 32.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Generative modeling by estimating gradients of the data distribution.Advances in neural information processing systems, 32

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.476268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 25e42aa1-2447-4e5c-875c-58a9fa9b1a3f · outbound

This paper cites Score-Based Generative Modeling through Stochastic Differential Equations.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Score-Based Generative Modeling through Stochastic Differential Equations

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:41:12.207170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9f65322f-d660-4a04-91f1-483c959e1e97 · outbound

This paper cites Learning to summarize with human feedback.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Learning to summarize with human feedback

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.481687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e4309012-79f7-4679-90f5-52099cccacdd · outbound

This paper cites A law of comparative judgment.Psychological Review, 34(4):273–286.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models A law of comparative judgment.Psychological Review, 34(4):273–286

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.484837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4d361d38-9bcc-4b4a-8c77-e76f6b6034e8 · outbound

This paper cites Diffusion model alignment using direct preference optimization.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Diffusion model alignment using direct preference optimization

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.491791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1ed71ad3-e810-46f1-be42-3f64e689b482 · outbound

This paper cites Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:41:12.201925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 308c885c-0c13-4f08-9fd2-76e43774f0ad · outbound

This paper cites Imagereward: Learning and evaluating human preferences for text-to-image generation.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Imagereward: Learning and evaluating human preferences for text-to-image generation

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.495686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 619d2178-fad2-404c-a8d8-26456627a8a4 · outbound

This paper cites DanceGRPO: Unleashing GRPO on Visual Generation.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models DanceGRPO: Unleashing GRPO on Visual Generation

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:28:29.121023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7c1b180c-1c1b-4319-b3a8-56410e42991d · outbound

This paper cites Diffusion models: A comprehensive survey of methods and applications.ACM computing surveys, 56(4):1–39.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Diffusion models: A comprehensive survey of methods and applications.ACM computing surveys, 56(4):1–39

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.448740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ad1800b5-4116-404a-88ee-ffe54c02184d · outbound

This paper cites Scaling Autoregressive Models for Content-Rich Text-to-Image Generation.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:49:31.747550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a5238165-3f2e-4b53-8f5b-47f134f229a0 · outbound

This paper cites Self-rewarding language models.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Self-rewarding language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.416137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ce1a2567-d07c-4980-970c-b64a3f6ad9ef · outbound

This paper cites Dspo: Direct score preference optimization for diffusion model alignment.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models Dspo: Direct score preference optimization for diffusion model alignment

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T11:42:15.487958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5e79b816-d7ec-4ae6-bdf2-2448f1997217 · outbound

This paper cites we did not observe stable improvement when training from public implementations on Pick-a-Pic.

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models we did not observe stable improvement when training from public implementations on Pick-a-Pic

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:41:12.167678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

No inbound Pith citation observations are available.