Paper Citation Record · LEDGER

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection

As of 10 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 2 inbound Pith citation observations for arXiv:2505.22192.

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

pith.paper-citation-record.v1
2505.22192 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:16:21.483149Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T09:19:53.618384Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

22 of 22 outbound references displayed

verified exact4
verified fuzzy6
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e3683dd6-2dbf-4da2-b776-9deafc21c250 · outbound

This paper cites Improving Factuality and Reasoning in Language Models through Multiagent Debate.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Improving Factuality and Reasoning in Language Models through Multiagent Debate

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:19.597111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d699502b-ccf1-45cf-852a-f25c2ccb4242 · outbound

This paper cites AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:19.685225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9c735de-dd20-4ef2-bf26-0675e8a2035d · outbound

This paper cites More Agents Is All You Need.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection More Agents Is All You Need

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:19.791117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c972a376-bbff-4106-aa57-6940afd04fb5 · outbound

This paper cites Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:19.873822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bb7575d-c537-4f00-bd2c-57a34a1dbc92 · outbound

This paper cites The Rise and Potential of Large Language Model Based Agents: A Survey.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection The Rise and Potential of Large Language Model Based Agents: A Survey

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:19.983174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73ca2157-22ff-408f-98c0-a47875f55b6a · outbound

This paper cites A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:20.062821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54cef82e-45d1-4839-b18c-d2db5635b513 · outbound

This paper cites A Survey on Contribution Evaluation in Vertical Federated Learning.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection A Survey on Contribution Evaluation in Vertical Federated Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:20.137727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab31d35-1413-431c-bb16-d2dbaabb8558 · outbound

This paper cites Survey on contribution evaluation for federated learning,.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Survey on contribution evaluation for federated learning,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:16:24.087073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 192b2e43-d92c-47a0-8916-8ba04fab3b8a · outbound

This paper cites Incentive Allocation in Vertical Federated Learning Based on Bankruptcy Problem.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Incentive Allocation in Vertical Federated Learning Based on Bankruptcy Problem

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:16:22.534500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 605dd47a-b50e-4eb6-a8cb-59d97033df3d · outbound

This paper cites A Bargaining-based Approach for Feature Trading in Vertical Federated Learning.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection A Bargaining-based Approach for Feature Trading in Vertical Federated Learning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:16:22.372938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c1df1953-a198-420d-82f9-e3a89d761480 · outbound

This paper cites Efficient participant contribution evaluation for horizontal and vertical federated learning,.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Efficient participant contribution evaluation for horizontal and vertical federated learning,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:16:23.909005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c1bb7f01-41bb-4666-b36c-6670304e487e · outbound

This paper cites Hierarchical Federated Learning Incentivization for Gas Usage Estimation.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Hierarchical Federated Learning Incentivization for Gas Usage Estimation

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:16:22.197126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1962d965-c2a9-44db-8c25-6967305bcde5 · outbound

This paper cites TradingGPT: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection TradingGPT: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:20.583371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6226bf2a-f805-4095-a318-d172b6807443 · outbound

This paper cites MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:20.679329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b87b2b3-99fc-4348-ad15-872e2c36b98b · outbound

This paper cites ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:20.779271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21369eb-375c-4824-9b6d-e512457b57c3 · outbound

This paper cites Examining inter- consistency of large language models collaboration: An in-depth analysis via debate,.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Examining inter- consistency of large language models collaboration: An in-depth analysis via debate,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:16:23.689646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 06eddc09-a7ed-42ed-861d-94d77ab17c9d · outbound

This paper cites CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:20.953096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8c1bb0f-bba1-4f29-ac5c-7f12846f4f7e · outbound

This paper cites Prompt Valuation Based on Shapley Values.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Prompt Valuation Based on Shapley Values

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:16:21.796758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 023a3a62-934a-43f4-b0fb-55b5ac731bf5 · outbound

This paper cites Llm-blender: Ensembling large language models with pairwise ranking and generative fusion,.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Llm-blender: Ensembling large language models with pairwise ranking and generative fusion,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:16:23.458976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 89561aa7-546f-4374-93aa-6ed99bb7101e · outbound

This paper cites Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:21.292940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d2d51d9-9b1c-497c-98ca-47a51b8d48af · outbound

This paper cites <copy other agents’ responses>.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection <copy other agents’ responses>

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:16:22.974811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7148a935-b145-438d-8307-0b04b396cfee · outbound

This paper cites <copy other agents’ responses>.

Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection <copy other agents’ responses>

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:16:23.202979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation f0a8434f-cc44-4124-aca6-ae454513f7d6 · inbound

Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory cites this paper.

Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T09:19:53.618384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 011cecdb-e124-4473-bcd1-1e5a50d0e33d · inbound

Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges cites this paper.

Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T00:32:23.761399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.