Pith. sign in

Paper Citation Record · LEDGER

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking

As of 21 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 3 inbound Pith citation observations for arXiv:2502.01667.

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

pith.paper-citation-record.v1
2502.01667 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T18:55:14.749369Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T04:36:13.562345Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T02:11:15.563841Z

Reference resolution

13 of 13 outbound references displayed

  • verified exact0
  • verified fuzzy2
  • unresolved11
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 945dad9d-c1d5-4b65-8b50-7656528e41fd · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.698903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.698903Z digest=sha256:cc394bdac7dff4e1344c7b972b792d51149db55aea81a7ffda3b26dfd58b10e1

Observation 433a15ec-9943-498d-92e6-5ffe794d4747 · outbound

This paper cites Aligning Text-to-Image Models using Human Feedback.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking Aligning Text-to-Image Models using Human Feedback

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.716939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.716939Z digest=sha256:493306725c9f914b046a453644dc25ff6650a82c6839719f592e4219047fee8d

Observation 7ff31df5-0330-4e06-81aa-130ba46954b0 · outbound

This paper cites Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.721267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.721267Z digest=sha256:1738496bc7b2e6468ad0acb386ff0d871b492cd992e63a336b5c81ea7299220f

Observation a1b31773-2c03-4617-b886-7966a2aa280c · outbound

This paper cites Aligning Text-to-Image Diffusion Models with Reward Backpropagation.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking Aligning Text-to-Image Diffusion Models with Reward Backpropagation

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.729814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.729814Z digest=sha256:6c9dcf3d75a4a13695d8e57958cde512e8e35c343e9bb6b6f5b097029aa21973

Observation 840a7906-fad3-44d9-ad91-31b0138088e7 · outbound

This paper cites Defining and Characterizing Reward Hacking.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking Defining and Characterizing Reward Hacking

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.733622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.733622Z digest=sha256:e18239c5246bbf38d99c553f7de8f5106a9fa4386af827e48dc64be5a59e719f

Observation 8d6b33bf-3fec-43d2-9bf1-692c3fee2721 · outbound

This paper cites $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.737534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.737534Z digest=sha256:6ec4e4a22c12830d2321e8f2b1565dce19968a9efae1a7de8febd22e17182a1d

Observation 858e01d3-37e6-4493-bec4-79eece078925 · outbound

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

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.741389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.741389Z digest=sha256:29919fd8fb40fb2f004482baf6355424910ed5849a4674e747d1434aac56f12b

Observation 2f47b8ec-6f15-45c8-b224-56e9f7321be9 · outbound

This paper cites draw” for them. Otherwise, they should label each image with a “win.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking draw” for them. Otherwise, they should label each image with a “win

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:55:14.905671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T18:55:14.745241Z digest=sha256:5c7b1615a38f204a258efefce9d2a017394aacf28c134e366f6c7ac797934dd3

Observation 8c1abe16-c2d0-459c-b0f3-3b5318f0e260 · outbound

This paper cites The prompts are from the Pick-a-Pic dataset.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking The prompts are from the Pick-a-Pic dataset

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T18:55:14.893465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-09T18:55:14.749369Z digest=sha256:70e00a9cdfa03e361ca09da3cc76422e280a9bf2bef8c7076a201b262a7a9388

Observation 71ee1119-9219-45c5-8cba-044b0e8ef46a · outbound

This paper cites Imagen Video: High Definition Video Generation with Diffusion Models.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking Imagen Video: High Definition Video Generation with Diffusion Models

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.712504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.712504Z digest=sha256:d0df6c9ebc3082cbdabb1184e6e8bfb023a1f5f0c610e8de895c59a748eeb9f3

Observation d1a7150b-1240-4cd3-9283-f6c68d7e2d29 · outbound

This paper cites GPT-4 Technical Report.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking GPT-4 Technical Report

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.725815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.725815Z digest=sha256:d8c0894e5efab3c33d7dd78ba18e8b4cc06d831060f7f8a77c6c7f598b001843

Observation d07a524e-7ca7-4b88-af9b-401b38a86a46 · outbound

This paper cites Gradient Guidance for Diffusion Models: An Optimization Perspective.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking Gradient Guidance for Diffusion Models: An Optimization Perspective

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.703873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.703873Z digest=sha256:021822d1bda82b207607e807161d81cf0ac39344ac1e467f80141dff27dd15a1

Observation c54edfc0-f631-4b00-aa97-f5859962cff2 · outbound

This paper cites Classifier-Free Diffusion Guidance.

Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking Classifier-Free Diffusion Guidance

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-09T18:55:14.708261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T18:55:14.708261Z digest=sha256:2410bdbf313c6a6f65818c90f644446f123a7e6b28dd929ed8a73d07ce94b60d

Pith citing papers

Observation 4db1fb50-de6b-458a-9aae-e8c32b57898e · inbound

Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion cites this paper.

Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T04:36:13.562345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T04:36:13.562345Z digest=sha256:014764338b93ba5aa83a918e65e381dc12835e1aef866b7ace3158b7a1695576

Observation 6cb0ffd8-16d6-4209-9e19-775b9fdf14bf · inbound

Threshold-Guided Optimization for Visual Generative Models cites this paper.

Threshold-Guided Optimization for Visual Generative Models Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking

Reference 47

Resolution
verified exact
arxiv_id, observed 2026-05-11T17:46:07.962171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=arxiv_source observed=2026-05-08T17:14:36.632493Z digest=sha256:0b02daa109289ddeb5033ee81a14b785566e56eaafa5827952c1044634af5be0

Observation 4b007bb3-661e-42ef-8b3a-00ded0a14f6c · inbound

Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs cites this paper.

Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking

Reference 35

Resolution
verified exact
arxiv_id, observed 2026-05-12T02:11:15.565659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-12T02:10:27.595446Z digest=sha256:8ae718bb3b3277d04af51d388a3b8896ddb6d14ea54872b29c576be775a1a9c2