Paper Citation Record · LEDGER

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types

As of 5 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2408.15339.

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

pith.paper-citation-record.v1
2408.15339 v4

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-23T21:22:36.970101Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+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 exact21
verified fuzzy1
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 75e67232-a357-44c1-9fe4-90ff766f4b75 · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.397187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e57c9ca4-ccc4-4766-9abe-a640002eceeb · outbound

This paper cites Training a helpful and harmless assistant with reinforcement learning from human feedback, 2022a.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Training a helpful and harmless assistant with reinforcement learning from human feedback, 2022a

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T21:23:28.456889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4c6e65cd-25be-4678-8647-54495b3e903c · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.366013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation aedee061-b3dc-493a-893f-f2657d3ce1f8 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Training Verifiers to Solve Math Word Problems

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.371734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6ab1016e-dcb4-40b5-b68f-a0f1c667a2ef · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Measuring Mathematical Problem Solving With the MATH Dataset

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.424359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dc63e7ba-1101-480c-a20d-a745edab1d73 · outbound

This paper cites ORPO: Monolithic Preference Optimization without Reference Model.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types ORPO: Monolithic Preference Optimization without Reference Model

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.403390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 95e49e35-dc8e-4cd3-b648-8af0b9c58686 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types LoRA: Low-Rank Adaptation of Large Language Models

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.500846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f32f8a9f-0d18-48f9-87c8-7c7e16123b04 · outbound

This paper cites Mistral 7B.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Mistral 7B

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T21:23:27.359297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2ebd1d91-ecbf-45fb-bfd3-e5688bb9c815 · outbound

This paper cites LiPO: Listwise Preference Optimization through Learning-to-Rank.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types LiPO: Listwise Preference Optimization through Learning-to-Rank

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.417555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 526fd740-085f-4992-a9f9-b3d9e4eebd52 · outbound

This paper cites Nash Learning from Human Feedback.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Nash Learning from Human Feedback

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.384210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c3328669-db3d-4546-a3b9-058deafc9d92 · outbound

This paper cites Nemotron-4 340B Technical Report.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Nemotron-4 340B Technical Report

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.437406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 710e60f8-dc94-4cbb-bbe3-e01e1a82361b · outbound

This paper cites PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.465151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3b9ffa27-5a71-4bac-ad08-adbca58e3303 · outbound

This paper cites From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.431660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 93c2f85c-31fb-4c8a-b53e-f10c6b3e8cd1 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.442405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fca72ce2-2f53-4be1-be10-2196cf86329d · outbound

This paper cites Offline Regularised Reinforcement Learning for Large Language Models Alignment.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Offline Regularised Reinforcement Learning for Large Language Models Alignment

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.507382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a6003053-d699-432c-98ff-7e1f2f765e5d · outbound

This paper cites an unresolved cited work.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-05-23T21:23:28.461031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b0894764-c8cd-48c4-9789-8e388b060228 · outbound

This paper cites Preference Ranking Optimization for Human Alignment.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Preference Ranking Optimization for Human Alignment

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.476519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 391ef5c6-cc14-465a-8d28-91bc4e34b19e · outbound

This paper cites MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.495114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3de95e35-1551-479b-9295-867dec474dbb · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Gemini: A Family of Highly Capable Multimodal Models

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.452991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cbd8afec-9ea4-41ba-b087-9325b32ea148 · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.390797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cac8fab4-4a54-4d55-a42e-1558f0187b6c · outbound

This paper cites Self-Play Preference Optimization for Language Model Alignment.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Self-Play Preference Optimization for Language Model Alignment

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.410682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3107b263-5fce-43a2-99a7-30228e15d883 · outbound

This paper cites Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.459223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d7d6c5fd-dc09-4622-953b-957c1f47e449 · outbound

This paper cites Self-Rewarding Language Models.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Self-Rewarding Language Models

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T21:23:27.377474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8fa9f457-f4b5-46d5-b3bf-c65a6b2866e0 · outbound

This paper cites RRHF: Rank Responses to Align Language Models with Human Feedback without tears.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types RRHF: Rank Responses to Align Language Models with Human Feedback without tears

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-23T21:23:27.482146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 078580d8-a1a5-4ca6-b1db-d8247483d942 · outbound

This paper cites Token-level Direct Preference Optimization.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Token-level Direct Preference Optimization

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:23:27.487999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 737e8445-6ce5-4896-920a-334a477100e6 · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T21:23:27.447863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b0c7040b-6999-42a1-9f27-9b5f1973a6a8 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types Instruction-Following Evaluation for Large Language Models

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-23T21:23:27.470716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

No inbound Pith citation observations are available.