Paper Citation Record · LEDGER

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference

As of 17 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2602.15206.

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

pith.paper-citation-record.v1
2602.15206 v2

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T22:59:38.022401Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

19 of 19 outbound references displayed

verified exact2
verified fuzzy0
unresolved15
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c23f11f1-2fd9-4976-8cd6-1aa4647a3a10 · outbound

This paper cites an unresolved cited work.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Unresolved cited work

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-08-02T22:59:38.022401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd1ee73f-9612-41ad-ac88-2d0b75328dbb · outbound

This paper cites Decoupled Weight Decay Regularization.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Decoupled Weight Decay Regularization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:37.082536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f846c9cd-60c5-40d8-9c43-cb51d9fb91f2 · outbound

This paper cites URL https://doi.org/10.1145/3623384.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference URL https://doi.org/10.1145/3623384

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:37.379875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 268e2b95-fc1e-44cd-a3ed-ac98b11670dc · outbound

This paper cites RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-08-02T23:04:09.648070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ecc515b6-c2dd-428d-85e2-c4b2f8ccd695 · outbound

This paper cites Vivek Myers, Erdem Bıyık, Nima Anari, and Dorsa Sadigh.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Vivek Myers, Erdem Bıyık, Nima Anari, and Dorsa Sadigh

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:37.604747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35cae80d-7fd8-4431-8600-5ccbf5b974b7 · outbound

This paper cites Training language models to follow instructions with human feedback.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Training language models to follow instructions with human feedback

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:37.730664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01800d95-c7cd-43c8-8e6c-b74caafb3306 · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:37.894011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2246660-9ab4-48c7-9e67-7fdeef9e3261 · outbound

This paper cites 13 A Implementation Details A.1 Model Architecture The reward encoder qθ and Q-value estimator Qϕ were implemented as two-layer MLPs with Leaky ReLU activations.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference 13 A Implementation Details A.1 Model Architecture The reward encoder qθ and Q-value estimator Qϕ were implemented as two-layer MLPs with Leaky ReLU activations

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:37.960668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c228a7f-f9e2-4010-9580-9aea33351a72 · outbound

This paper cites Shaunak A.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Shaunak A

Reference 1980

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:37.216647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d06f97f8-0610-4967-b1b9-6aab1ab2e25b · outbound

This paper cites ISBN 978-1-58113-838-2.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference ISBN 978-1-58113-838-2

Reference 2004

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:35.977656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8244124f-9067-429d-b58d-6bfdd43df72a · outbound

This paper cites ISBN 978-1-60558-658-8.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference ISBN 978-1-60558-658-8

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:36.914817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b57aefb9-b22b-45d8-a9d1-09c2763386ab · outbound

This paper cites Auto-Encoding Variational Bayes.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Auto-Encoding Variational Bayes

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:36.704749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e40ae02c-c435-419f-a524-3fa31e9516e3 · outbound

This paper cites Unsolved Problems in ML Safety.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Unsolved Problems in ML Safety

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:36.474748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f29625-6a8f-4974-87b8-5875edba4c1e · outbound

This paper cites Reward-rational (implicit) choice: A unifying formalism for reward learning.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Reward-rational (implicit) choice: A unifying formalism for reward learning

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:36.591876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b1e099b-a8b8-4ce1-870c-a28b782a31ad · outbound

This paper cites Learning Multimodal Rewards from Rankings.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Learning Multimodal Rewards from Rankings

Reference 2021

Resolution: verified exact; local_arxiv, observed 2026-08-02T23:04:09.540088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c9328504-8c06-47f4-9c62-3db756a303e8 · outbound

This paper cites doi: 10.1177/02783649211041652.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference doi: 10.1177/02783649211041652

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:36.202256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eb5badb-d0db-496c-8459-160db2383dc8 · outbound

This paper cites doi: 10.1609/aaai.v37i5.25740.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference doi: 10.1609/aaai.v37i5.25740

Reference 2023

Resolution: verified exact; doi, observed 2026-08-02T23:04:09.842539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f93f15a9-5612-410e-a186-8e7972475d65 · outbound

This paper cites Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Mané.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Mané

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:36.074912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b6b0a61-a1ed-4f96-ac42-0b337c3049d6 · outbound

This paper cites Scalable Bayesian inverse reinforcement learning.

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference Scalable Bayesian inverse reinforcement learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T22:59:36.291389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.