Paper Citation Record · LEDGER

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis

As of 19 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2505.18710.

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

pith.paper-citation-record.v1
2505.18710 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:30:56.248436Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:30:50.951365Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-16T00:30:51.481502Z

Reference resolution

39 of 39 outbound references displayed

verified exact1
verified fuzzy0
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation aa7a07b4-38b9-4a05-9f0e-7ba932e97873 · outbound

This paper cites online" 'onlinestring :=.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:52.656266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 827cc3ec-7073-4edf-848c-916604b681f8 · outbound

This paper cites write newline.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:52.744638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87afa78c-e2da-4f02-8807-e3cc02f209ef · outbound

This paper cites GPT-4 Technical Report.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis GPT-4 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:52.824716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 601b515b-1d0b-4725-ad7a-786a0b5938af · outbound

This paper cites Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:52.906135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88cf084c-d5db-4e09-8c81-fdfbb46acf90 · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:52.991748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2e10192-1437-4c0c-bc53-7e0f3a3f83d8 · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:53.066347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad9cd22b-fbbe-4ebb-9c00-2c8b7f58c2fc · outbound

This paper cites Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:53.191782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f49228e1-a807-43db-9428-ac8d35c7c656 · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:53.268669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18ce72a4-bd86-4e42-8d56-c5081cd4c15c · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:53.364959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76782d3d-30a3-4beb-8af6-18bac0c54bf3 · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:53.493153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f8e021-66f6-4ce1-ad52-d60167946a12 · outbound

This paper cites Rethinking with Retrieval: Faithful Large Language Model Inference.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Rethinking with Retrieval: Faithful Large Language Model Inference

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:53.569078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fd37d16-3671-4b6d-ac6b-9315399543ae · outbound

This paper cites Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:53.778386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4d33b04-423b-4b82-9ef7-5e07ef3b272f · outbound

This paper cites Unsupervised Dense Information Retrieval with Contrastive Learning.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unsupervised Dense Information Retrieval with Contrastive Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:53.863306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9d7a0dc-c480-4619-a58c-a5a6acce4039 · outbound

This paper cites Atlas: Few-shot Learning with Retrieval Augmented Language Models.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Atlas: Few-shot Learning with Retrieval Augmented Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:53.935877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6558374a-5019-4a13-8cc3-5da717212d2e · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:54.049064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 165378e4-0ccf-4964-a194-3fffa7d9d5d2 · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:54.180427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff323985-0754-448b-8c2d-e81093071341 · outbound

This paper cites Dense Passage Retrieval for Open-Domain Question Answering.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Dense Passage Retrieval for Open-Domain Question Answering

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:54.311608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1affa6fc-d9f7-4c14-92e9-8bc5a265ddf3 · outbound

This paper cites Bridging the Preference Gap between Retrievers and LLMs.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Bridging the Preference Gap between Retrievers and LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:54.419840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bcc27a7-6561-4d05-9ee4-67b563263318 · outbound

This paper cites SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:54.525693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e03c58cc-7794-4f8d-9ded-fdb2dad4336f · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:54.617743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce72a03e-1f67-46df-858f-b73c9e180a73 · outbound

This paper cites u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:54.732812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2327ce6-34a5-4800-bd70-56a1f7ae1353 · outbound

This paper cites Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:54.840814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12b92e94-51eb-4fd0-80d3-53314c049101 · outbound

This paper cites From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:54.951220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b8c7b36-ca21-4f30-817a-bb3f80a2c3d6 · outbound

This paper cites Contrastive Decoding: Open-ended Text Generation as Optimization.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Contrastive Decoding: Open-ended Text Generation as Optimization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.026727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c82370a8-376d-4f87-9573-92c31dbfc723 · outbound

This paper cites RA-DIT: Retrieval-Augmented Dual Instruction Tuning.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis RA-DIT: Retrieval-Augmented Dual Instruction Tuning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.094747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b6e3abe-38bd-4c22-a3a9-ce02adda65d7 · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.234743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6644aa7a-a242-43bd-aaa4-08d46ab6867e · outbound

This paper cites When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.288600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adb12687-863a-41ea-bbd9-217a2d1eb359 · outbound

This paper cites W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:30:56.488179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f1c7f738-b0b5-468d-8338-edba84b03221 · outbound

This paper cites SQuAD: 100,000+ Questions for Machine Comprehension of Text.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis SQuAD: 100,000+ Questions for Machine Comprehension of Text

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.450490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acc833d7-0d8b-4748-ab72-e0eb79b56a70 · outbound

This paper cites Trusting Your Evidence: Hallucinate Less with Context-aware Decoding.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Trusting Your Evidence: Hallucinate Less with Context-aware Decoding

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.518056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20ff52fd-7335-4fac-b45c-d3d2a277dfc6 · outbound

This paper cites REPLUG: Retrieval-Augmented Black-Box Language Models.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis REPLUG: Retrieval-Augmented Black-Box Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.611939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4c7dd07-665b-4c20-96cb-95d596040a73 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis LLaMA: Open and Efficient Foundation Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.659579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f38dd14a-f8b5-4e7f-8037-cc43e4becb77 · outbound

This paper cites Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.744806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 087cf98d-516d-47ff-aa06-ab6025e330e6 · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:56.776049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ffe53512-5524-44d4-b874-201c9dc22e7a · outbound

This paper cites REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:55.881903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8605a773-ab50-49ec-9faa-d3a67b960120 · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:56.006069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b2bf267-3578-454e-a3cf-55b80cbbc04b · outbound

This paper cites an unresolved cited work.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:56.082065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58b4c4e0-f525-4b39-a15a-1f80447ad69c · outbound

This paper cites Generate rather than Retrieve: Large Language Models are Strong Context Generators.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis Generate rather than Retrieve: Large Language Models are Strong Context Generators

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:56.152073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da3a6cc5-e9a5-451f-8805-ee1d4d2b3719 · outbound

This paper cites RAFT: Adapting Language Model to Domain Specific RAG.

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis RAFT: Adapting Language Model to Domain Specific RAG

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:56.248436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9ea1f465-654f-4a95-beeb-795bea38866d · inbound

LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence cites this paper.

LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-08-16T00:30:51.485559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.