Paper Citation Record · LEDGER

RL with KL penalties is better viewed as Bayesian inference

As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 20 inbound Pith citation observations for arXiv:2205.11275.

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

pith.paper-citation-record.v1
2205.11275 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 20 of 20 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:32:52.272951Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T00:27:29.845324Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 20b0241a-bf09-4e85-a708-b778b1c3e90b · inbound

Scaling Laws for Reward Model Overoptimization cites this paper.

Scaling Laws for Reward Model Overoptimization RL with KL penalties is better viewed as Bayesian inference

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-19T09:04:53.301252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 55a032d8-32db-48b3-affc-f5fd8119b9bf · inbound

Time-Reversal Provides Unsupervised Feedback to LLMs cites this paper.

Time-Reversal Provides Unsupervised Feedback to LLMs RL with KL penalties is better viewed as Bayesian inference

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T23:21:06.618515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6138706-4deb-459f-b813-80733664939a · inbound

Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models cites this paper.

Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models RL with KL penalties is better viewed as Bayesian inference

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-11T22:57:01.736400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ec41a30-ebf6-429c-b8b5-57a62ecd6fc5 · inbound

InfAlign: Inference-aware language model alignment cites this paper.

InfAlign: Inference-aware language model alignment RL with KL penalties is better viewed as Bayesian inference

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T23:57:54.300472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70857bde-aac4-4a66-8db7-21e81c66403f · inbound

A General Framework for Inference-time Scaling and Steering of Diffusion Models cites this paper.

A General Framework for Inference-time Scaling and Steering of Diffusion Models RL with KL penalties is better viewed as Bayesian inference

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T20:56:43.817398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51d2c4b0-c08c-4c05-84c8-1ee3ce9edd31 · inbound

CoDe: Blockwise Control for Denoising Diffusion Models cites this paper.

CoDe: Blockwise Control for Denoising Diffusion Models RL with KL penalties is better viewed as Bayesian inference

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T17:10:17.082630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9c9f8f1-eae8-40c6-9d6d-824d3087514b · inbound

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization cites this paper.

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization RL with KL penalties is better viewed as Bayesian inference

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-16T10:32:52.272951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 876999fe-af79-4977-ba31-ae9939d891db · inbound

Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training cites this paper.

Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training RL with KL penalties is better viewed as Bayesian inference

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T21:49:27.830463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f055b0c-aa79-4eea-ab72-558e90452701 · inbound

Discovering Algorithms with Computational Language Processing cites this paper.

Discovering Algorithms with Computational Language Processing RL with KL penalties is better viewed as Bayesian inference

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T20:26:01.136484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93333f7d-8616-41bb-b553-deae042a3f7d · inbound

Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis cites this paper.

Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis RL with KL penalties is better viewed as Bayesian inference

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T19:28:56.065982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aa4ea9d-4aa4-4680-b70c-b827d8e4e9b5 · inbound

A Survey of Reinforcement Learning For Economics cites this paper.

A Survey of Reinforcement Learning For Economics RL with KL penalties is better viewed as Bayesian inference

Reference 1960

Resolution: unresolved; no resolver link, observed 2026-08-02T18:34:52.804048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ea9c9d4-48f6-481e-a9dd-79f0ddbaec96 · inbound

Reinforcement Learning via Value Gradient Flow cites this paper.

Reinforcement Learning via Value Gradient Flow RL with KL penalties is better viewed as Bayesian inference

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:20:25.619008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4abcc714-8349-4261-8f2f-1f1c616a831f · inbound

Exponential families from a single KL identity cites this paper.

Exponential families from a single KL identity RL with KL penalties is better viewed as Bayesian inference

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:11:28.247915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ab0a2075-e8f6-41e5-8d5e-75bfff6214c4 · inbound

Binary Rewards and Reinforcement Learning: Fundamental Challenges cites this paper.

Binary Rewards and Reinforcement Learning: Fundamental Challenges RL with KL penalties is better viewed as Bayesian inference

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:31:08.663028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c4ed330b-c778-45c0-8bda-697343dad096 · inbound

On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective cites this paper.

On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective RL with KL penalties is better viewed as Bayesian inference

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:36:26.798482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8ac82a3c-dbd6-4e2f-8485-cfeba45aae1e · inbound

The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives cites this paper.

The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives RL with KL penalties is better viewed as Bayesian inference

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:52:08.903060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation db64787e-ea9d-4737-881f-b2258609c6e5 · inbound

A Unifying Lens on Reward Uncertainty in RLHF cites this paper.

A Unifying Lens on Reward Uncertainty in RLHF RL with KL penalties is better viewed as Bayesian inference

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:27:29.846581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dce67dbc-9dce-420e-8da5-547482ef1730 · inbound

Multi-Turn On-Policy Distillation with Prefix Replay cites this paper.

Multi-Turn On-Policy Distillation with Prefix Replay RL with KL penalties is better viewed as Bayesian inference

Reference 247

Resolution: unresolved; no resolver link, observed 2026-07-11T13:53:36.775836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf3d459f-d00b-45dc-80be-648e96eb1dc8 · inbound

Multi-Turn On-Policy Distillation with Prefix Replay cites this paper.

Multi-Turn On-Policy Distillation with Prefix Replay RL with KL penalties is better viewed as Bayesian inference

Reference 248

Resolution: unresolved; no resolver link, observed 2026-08-02T08:41:01.139311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba7f66a-6485-4d5e-a4f5-ce4d07460d7d · inbound

Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration cites this paper.

Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration RL with KL penalties is better viewed as Bayesian inference

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-15T14:33:57.124460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.