Paper Citation Record · LEDGER

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning

As of 6 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2605.10488.

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

pith.paper-citation-record.v1
2605.10488 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-12T04:19:01.836535Z

measured 37 of 37 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

37 of 37 outbound references displayed

verified exact27
verified fuzzy6
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 48c5e544-52a6-4848-a0ae-64afa801d7f1 · outbound

This paper cites Neuro- symbolic entity alignment via variational inference.arXiv preprint arXiv:2410.04153.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Neuro- symbolic entity alignment via variational inference.arXiv preprint arXiv:2410.04153

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.519182Z

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 5631b6dd-92a0-4b22-b394-1e783cdf536f · outbound

This paper cites Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.540099Z

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 3cdd3d0c-ac01-4c78-915f-45141e91c19b · outbound

This paper cites Distill-synthkg: Distilling knowledge graph synthesis workflow for improved coverage and efficiency.arXiv preprint arXiv:2410.16597.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Distill-synthkg: Distilling knowledge graph synthesis workflow for improved coverage and efficiency.arXiv preprint arXiv:2410.16597

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.585927Z

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 6c233309-ab0b-443f-9d4c-7494e4e2ea01 · outbound

This paper cites Paulheim, Knowledge graph refinement: A survey of approaches and evaluation methods, Semantic Web 8 (3) (2017) 489–508.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Paulheim, Knowledge graph refinement: A survey of approaches and evaluation methods, Semantic Web 8 (3) (2017) 489–508

Reference 4

Resolution: metadata mismatch; doi, observed 2026-05-12T04:21:21.303909Z

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 8b4ac1e1-bea6-43e2-a6a0-9f3a9fc391bb · outbound

This paper cites From Local to Global: A Graph RAG Approach to Query-Focused Summarization.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning From Local to Global: A Graph RAG Approach to Query-Focused Summarization

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.480552Z

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 ec25b426-07de-4822-b458-880d292665c1 · outbound

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

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.472029Z

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 3f342ea3-4318-456c-90bc-d95602349674 · outbound

This paper cites LightRAG: Simple and Fast Retrieval-Augmented Generation.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning LightRAG: Simple and Fast Retrieval-Augmented Generation

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:59:04.437407Z

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 3f17e555-49ea-4829-b917-da58214c3f44 · outbound

This paper cites From RAG to Memory: Non-Parametric Continual Learning for Large Language Models.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning From RAG to Memory: Non-Parametric Continual Learning for Large Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:36:19.859440Z

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 a7b5669d-13a9-4740-9d0c-d45d7ce0ba2f · outbound

This paper cites Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-12T21:59:02.400889Z

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 3bbce0a4-7f4a-431c-b155-1c8c65171ea0 · outbound

This paper cites Retrieval-augmented generation with hierarchical knowledge.arXiv preprint arXiv:2503.10150.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Retrieval-augmented generation with hierarchical knowledge.arXiv preprint arXiv:2503.10150

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.453207Z

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 0ba73384-b61d-4e3a-9b40-17255fd5a62f · outbound

This paper cites OpenAI o1 System Card.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning OpenAI o1 System Card

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.406074Z

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 51c49942-a680-4cf0-8aad-d049bbe02e1e · outbound

This paper cites s3: You don’t need that much data to train a search agent via rl.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning s3: You don’t need that much data to train a search agent via rl

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:41:40.143193Z

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 922d26e3-d591-4e33-8e19-041dfc1d5cbb · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.580444Z

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 47ce6274-086d-4dd1-8dbc-0fe4aa7cc187 · outbound

This paper cites DeepSeek-V3 Technical Report.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning DeepSeek-V3 Technical Report

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.533910Z

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 57ab5716-4ed3-4a69-b202-bf5905c40190 · outbound

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

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Understanding R1-Zero-Like Training: A Critical Perspective

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.439454Z

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 09f130b6-8182-4d7f-a0f8-583bb253d92a · outbound

This paper cites Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-04T02:06:52.238547Z

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 43133230-671d-4818-afaf-78bce3287679 · outbound

This paper cites A Replication Study of Dense Passage Retriever.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning A Replication Study of Dense Passage Retriever

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.412406Z

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 93979751-ce2e-4b5f-96eb-00a8d1d376c5 · outbound

This paper cites Evaluating Very Long-Term Conversational Memory of LLM Agents.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Evaluating Very Long-Term Conversational Memory of LLM Agents

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:05:17.171076Z

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 f4177b31-5447-4dc5-a0e1-c84e4ed46f78 · outbound

This paper cites Zep: A Temporal Knowledge Graph Architecture for Agent Memory.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Zep: A Temporal Knowledge Graph Architecture for Agent Memory

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.559902Z

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 d69d2517-5c34-468c-9e65-114e88a9e687 · outbound

This paper cites Proximal Policy Optimization Algorithms.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.596552Z

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 93634d9a-6929-42e9-ada6-ece57d5a629e · outbound

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

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T06:26:23.613344Z

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 784aedad-9fc7-4402-91ae-c52153fc49fc · outbound

This paper cites AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.528480Z

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 e75c105c-db02-4b37-b433-c744e619cbdb · outbound

This paper cites Mem-{\alpha}: Learning Memory Construction via Reinforcement Learning.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Mem-{\alpha}: Learning Memory Construction via Reinforcement Learning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:19:44.839865Z

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 66d14bd2-776c-4f9c-bf5e-11000f273f42 · outbound

This paper cites Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-06-02T02:03:37.535466Z

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 a91df4ae-4735-48a0-a27d-6d0410558fc8 · outbound

This paper cites A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.574460Z

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 414b6233-aa59-4141-85dd-159a8ff8c713 · outbound

This paper cites Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-13T04:55:54.660411Z

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 e4564e20-fe4d-4d58-9031-04ca00a0a370 · outbound

This paper cites Qwen3 Technical Report.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Qwen3 Technical Report

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:26:23.458818Z

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 417dc941-4814-43b2-be02-25331c320118 · outbound

This paper cites Graph-based agent memory: Taxonomy, techniques, and applications.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Graph-based agent memory: Taxonomy, techniques, and applications

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.503352Z

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 27e17f19-82cb-4f5d-8aca-08bb1b549a62 · outbound

This paper cites Hotpotqa: A dataset for diverse, explainable multi-hop question answering.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Hotpotqa: A dataset for diverse, explainable multi-hop question answering

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:41:40.154677Z

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 351e7c83-7d6d-4e6b-8915-f342794b22a2 · outbound

This paper cites KG-BERT: BERT for Knowledge Graph Completion.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning KG-BERT: BERT for Knowledge Graph Completion

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.591946Z

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 da8f488d-53ab-48ab-9daa-15bacaab6f28 · outbound

This paper cites Leanrag: Knowledge-graph-based generation with semantic aggregation and hierarchical retrieval.arXiv preprint arXiv:2508.10391.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Leanrag: Knowledge-graph-based generation with semantic aggregation and hierarchical retrieval.arXiv preprint arXiv:2508.10391

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.645868Z

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 aad3e547-563a-4727-b293-ac509e3f4fb6 · outbound

This paper cites TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.553908Z

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 8d25e7b5-2462-4e24-bea3-f5355f3cadb6 · outbound

This paper cites an unresolved cited work.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-05-12T15:41:40.145456Z

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 af1382cd-c1ec-4479-8087-39eed11eef77 · outbound

This paper cites missing evidence.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning missing evidence

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:41:40.152133Z

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 ba596462-d236-4cbc-afed-2821b3963189 · outbound

This paper cites Camdenton is a city in Camden County, Missouri, United States.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Camdenton is a city in Camden County, Missouri, United States

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:41:40.147824Z

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 f2ed37b6-dc4a-453a-a763-514973b40b0b · outbound

This paper cites He directed 159 films between 1926 and.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning He directed 159 films between 1926 and

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:41:40.149948Z

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 0e9490d8-10e3-4982-8ce2-34577351df7c · outbound

This paper cites Fighting with Buffalo Bill.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Fighting with Buffalo Bill

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-12T15:41:40.157928Z

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.