Paper Citation Record · LEDGER

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework

As of 15 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2508.19922.

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

pith.paper-citation-record.v1
2508.19922 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:25:35.413399Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+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

35 of 35 outbound references displayed

verified exact2
verified fuzzy1
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a18df4d1-2a4a-4f59-89be-946cb227ce9a · outbound

This paper cites MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.308051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81fe9f80-9a14-4b24-8f60-2ed60bab5c1e · outbound

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

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.312027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a539f99c-50c9-4a24-b7c6-d7faa9d4fd88 · outbound

This paper cites Preference Learning Algorithms Do Not Learn Preference Rankings.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Preference Learning Algorithms Do Not Learn Preference Rankings

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.315451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02b61796-c069-4de0-a360-c9dcc584af3c · outbound

This paper cites UltraFeedback: Boosting Language Models with Scaled AI Feedback.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework UltraFeedback: Boosting Language Models with Scaled AI Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.318632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6400d7fb-8d6a-4e3d-801f-949194a5cdfe · outbound

This paper cites The Llama 3 Herd of Models.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework The Llama 3 Herd of Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.321876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 279e15d7-63e2-4505-9f30-9db1bbf888c4 · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.325156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfe92514-dd2a-4c20-b687-8c64e7bc27c7 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework KTO: Model Alignment as Prospect Theoretic Optimization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.328505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 768642e3-ae38-4c1a-ad18-aa5dbc1cc6a1 · outbound

This paper cites an unresolved cited work.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:25:35.837450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8fb3f77f-b479-4473-a490-2331c8df63c0 · outbound

This paper cites A Survey on LLM-as-a-Judge.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework A Survey on LLM-as-a-Judge

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.334486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43dfbf7a-46a8-45f1-8c41-50376056c31b · outbound

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

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework ORPO: Monolithic Preference Optimization without Reference Model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.337386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7de859b7-0815-4f8a-b1e1-53695a0ea7af · outbound

This paper cites From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.340576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98a8ee90-c487-4175-810e-7403af2fbc23 · outbound

This paper cites Gonzalez, Haotong Zhang, and Ion Stoica.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Gonzalez, Haotong Zhang, and Ion Stoica

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:25:35.828775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cf22cafc-b38e-42bd-a6d0-9e4780abe1ed · outbound

This paper cites RewardBench: Evaluating Reward Models for Language Modeling.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework RewardBench: Evaluating Reward Models for Language Modeling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.346495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca7e99f-4071-4063-93ac-0f7b35225c0b · outbound

This paper cites an unresolved cited work.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.349624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation facf74dc-aaa8-4041-b80c-a697b3c0462b · outbound

This paper cites From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.352224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08de6af2-252b-4bd2-ac16-6ea088802325 · outbound

This paper cites SimPO: Simple Preference Optimization with a Reference-Free Reward.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework SimPO: Simple Preference Optimization with a Reference-Free Reward

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.355296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c649d71e-e58c-4e90-b088-c6d3f7a22e2b · outbound

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

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Training language models to follow instructions with human feedback

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.358311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a24bcf97-6762-47b6-9984-29a50dde373c · outbound

This paper cites Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-05T15:25:35.605803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 31890875-23db-473b-beb4-23c8de303c37 · outbound

This paper cites an unresolved cited work.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.365480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdde10b8-fd83-4c49-98d8-ae73486fe0bb · outbound

This paper cites an unresolved cited work.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:25:35.814122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3638db20-ec18-4d80-a848-247641455975 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Gemma 2: Improving Open Language Models at a Practical Size

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.370884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5198434-c956-4da9-8c34-1a60a954360e · outbound

This paper cites Learning to summarize from human feedback.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Learning to summarize from human feedback

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.373964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9fbefe5-a8b6-4452-8c8c-9ad588de887d · outbound

This paper cites an unresolved cited work.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.376904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 868bf964-29a8-4a94-a26d-be1fbe282ffd · outbound

This paper cites an unresolved cited work.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.379579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c418fa0-b6b9-4179-9f75-6a6bbf36ed71 · outbound

This paper cites Hybrid Alignment Training for Large Language Models.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Hybrid Alignment Training for Large Language Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-05T15:25:35.491015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c798dd28-4929-4b73-a9d5-7102f66a80cb · outbound

This paper cites an unresolved cited work.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:25:35.800105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2a379593-88ca-4d08-bb53-4ebb4da394de · outbound

This paper cites HelpSteer2-Preference: Complementing Ratings with Preferences.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework HelpSteer2-Preference: Complementing Ratings with Preferences

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.388592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88c00a00-7b70-494f-a432-ab08a843f7e9 · outbound

This paper cites Foundations of Large Language Models.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Foundations of Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.391626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 217601ac-2e29-402c-825d-d763b61db5cf · outbound

This paper cites Qwen3 Technical Report.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Qwen3 Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.394797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca0fdb99-e30d-4830-9981-4e1aa7a27de4 · outbound

This paper cites Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.397981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d83beb0-7cbb-4590-bc32-b499daaba649 · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.400879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2132af52-a5f3-4e90-83a0-270762cda0fd · outbound

This paper cites LIMA: Less Is More for Alignment.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework LIMA: Less Is More for Alignment

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.404093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62608cbf-0e4b-4842-8a57-1625d88e15cf · outbound

This paper cites an unresolved cited work.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:25:35.791472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7abfbee9-2464-4368-af77-4ad008632c00 · outbound

This paper cites online" 'onlinestring :=.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework online" 'onlinestring :=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.409794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bb5983b-c7dc-4038-8bcf-54fe2b4133fa · outbound

This paper cites write newline.

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework write newline

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T15:25:35.413399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.