Paper Citation Record · LEDGER

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

As of 17 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2607.17524.

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

pith.paper-citation-record.v1
2607.17524 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T17:47:43.553604Z

measured 27 of 27 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

27 of 27 outbound references displayed

verified exact0
verified fuzzy0
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3da58420-39b0-4edd-92a6-4a4ddfb8bae4 · outbound

This paper cites Survey of hallucination in natural language generation.ACM computing surveys, 55(12):1–38,.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Survey of hallucination in natural language generation.ACM computing surveys, 55(12):1–38,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.154463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41b6b21c-0365-4d8c-ac50-c5c6385ed9a1 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Understanding R1-Zero-Like Training: A Critical Perspective

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.428723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b061c23-3988-42e5-b43c-950eb3aa9a92 · outbound

This paper cites Gradient Imbalance in Direct Preference Optimization.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Gradient Imbalance in Direct Preference Optimization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.496853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 842db8ad-6ec5-4f84-9d4f-5cc4f302b195 · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.542364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbed606d-0c35-4571-98fd-1eacac1be6c2 · outbound

This paper cites Fine-grained Hallucination Detection and Editing for Language Models.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Fine-grained Hallucination Detection and Editing for Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.610917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0a87f47-dcf7-46dc-bbc3-a732970e3f33 · outbound

This paper cites doi: 10.1038/s41586-024-07335-x.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift doi: 10.1038/s41586-024-07335-x

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.699281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5817823-ff2c-4609-bd54-c90960077c26 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Proximal Policy Optimization Algorithms

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.779404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 688fed70-b9ff-4980-ad11-b4cc96599377 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.914703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaf141bd-b34e-4573-b83a-c96012071de3 · outbound

This paper cites Understanding factual errors in summarization: Errors, summarizers, datasets, error detectors.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Understanding factual errors in summarization: Errors, summarizers, datasets, error detectors

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.994642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6114e41b-8180-477a-9910-8ae39f55d535 · outbound

This paper cites Minicheck: Efficient fact-checking of llms on grounding documents.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Minicheck: Efficient fact-checking of llms on grounding documents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:42.112835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86d193b3-c1ce-40bf-bf0e-65c57c5fc782 · outbound

This paper cites Steering Language Models With Activation Engineering.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Steering Language Models With Activation Engineering

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:42.254879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5a3c139-f196-4cae-aa08-cd8e0f2cc00a · outbound

This paper cites LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:42.427244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77cfbb00-f862-4196-adfc-dc88b6390736 · outbound

This paper cites Neural Text Generation with Unlikelihood Training.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Neural Text Generation with Unlikelihood Training

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:42.511417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe38bd6-a41b-4e3d-a2aa-0fcbddf74436 · outbound

This paper cites Qwen3 Technical Report.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Qwen3 Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:42.664555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8419bea-dd29-4331-bf42-39254e5f7aab · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:42.786853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e631884d-355e-47d0-9e7c-6c823cd3d4cd · outbound

This paper cites Token-level Direct Preference Optimization.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Token-level Direct Preference Optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:42.921201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8069122d-7f13-4587-98ed-d1b5b9ffabb8 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Fine-Tuning Language Models from Human Preferences

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:43.057405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 909a909d-ff3e-4154-b870-0c392f81cb28 · outbound

This paper cites Specifically, instead of decomposing the summary into individual sentences, we directly evaluate the full summary using the Bespoke-MiniCheck-7B model.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Specifically, instead of decomposing the summary into individual sentences, we directly evaluate the full summary using the Bespoke-MiniCheck-7B model

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:43.165843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46016e8d-6493-46e3-9c48-a24819a1be9c · outbound

This paper cites an unresolved cited work.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:43.343218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fd21c68-a7c1-4fba-89f4-aeb74e2991da · outbound

This paper cites We report the total number of supervised tokens and the proportion of positive (factual) and negative (hallucinated) labels for each configuration.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift We report the total number of supervised tokens and the proportion of positive (factual) and negative (hallucinated) labels for each configuration

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:43.553604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3348cd36-1e17-4155-90d2-f7211246e2ce · outbound

This paper cites Spurious Rewards: Rethinking Training Signals in RLVR.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Spurious Rewards: Rethinking Training Signals in RLVR

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.835722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ad160cc-c056-47c0-8fff-665c7d7790fe · outbound

This paper cites Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:42.557783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0425af6-4c99-431e-b646-bc9bfe2fc42a · outbound

This paper cites Tldr: Token-level detective reward model for large vision language models.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Tldr: Token-level detective reward model for large vision language models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:40.966435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00bd0b4c-a756-45f3-9a03-77bb77936994 · outbound

This paper cites Programming refusal with conditional ac- tivation steering.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Programming refusal with conditional ac- tivation steering

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.295760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93b194f0-782d-486a-90bb-8781124eb519 · outbound

This paper cites doi: 10.18653/v1/2024.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift doi: 10.18653/v1/2024

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:40.898240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 841e4ae7-d903-4de7-98ee-5e41a1510015 · outbound

This paper cites The Llama 3 Herd of Models.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift The Llama 3 Herd of Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.056047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ee16ce7-4528-45de-8914-fca83a289185 · outbound

This paper cites Findings of the WMT 2024 shared task of the open language data initiative.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Findings of the WMT 2024 shared task of the open language data initiative

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:40.833651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.