Paper Citation Record · LEDGER

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models

As of 22 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 2 inbound Pith citation observations for arXiv:2412.01868.

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

pith.paper-citation-record.v1
2412.01868 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T04:41:03.481745Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:25:21.884249Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T18:09:39.951741Z

Reference resolution

23 of 23 outbound references displayed

verified exact0
verified fuzzy6
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4262be82-2ec3-45e9-916d-f0f05805a479 · outbound

This paper cites Could you convert {query} from {in-lang} to {out-lang}?.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Could you convert {query} from {in-lang} to {out-lang}?

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T04:41:03.924461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f8dc9766-212f-4f33-8da4-16196d5be8a3 · outbound

This paper cites LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.370441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5234f6a6-820e-49fd-b329-2238743a86a1 · outbound

This paper cites GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.387506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81bae001-b4f2-4ba9-9ef3-4e9fdb76e959 · outbound

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

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.393471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b219d3b-90b1-4613-b0ab-da9dcec7883c · outbound

This paper cites Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.398479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 709084f9-0522-41d6-98d0-568d8ce2c81b · outbound

This paper cites An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.403747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05305f93-d72e-4e92-9277-7410a9e5708f · outbound

This paper cites MTEB: Massive Text Embedding Benchmark.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models MTEB: Massive Text Embedding Benchmark

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.409362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b957c14-4d07-4c01-ab3a-f4825f69ba19 · outbound

This paper cites doi: 10.1109/HCS61935.2024.10664717.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models doi: 10.1109/HCS61935.2024.10664717

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.419599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0babe29-107f-4580-9555-083de5ce211b · outbound

This paper cites SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.424827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb937bf2-0aa4-4eec-bf8a-de73f826c132 · outbound

This paper cites Llm routing with benchmark datasets.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Llm routing with benchmark datasets

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T04:41:03.956794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation aa1452b3-2d6a-4bda-bf16-2d1b70ce40aa · outbound

This paper cites Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.447137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2670574a-580f-4f37-a18c-50b183ceca1b · outbound

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

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Gemma 2: Improving Open Language Models at a Practical Size

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.452510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85afcd9f-2959-4cc8-a881-1c9e889a8e51 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.458064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b70cc4-4587-49fd-bb96-f073f3a6981d · outbound

This paper cites Mmlu-pro: A more robust and challenging multi- task language understanding benchmark (published at neurips 2024 track datasets and benchmarks),.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Mmlu-pro: A more robust and challenging multi- task language understanding benchmark (published at neurips 2024 track datasets and benchmarks),

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T04:41:03.941096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 18c5fb7c-7412-4214-b87e-6c31d57855d1 · outbound

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

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.470413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b29de4da-9263-4573-8a18-965abe0f4464 · outbound

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

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.476113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ebc7e03-e36f-4562-b070-3a5dcc2cf6df · outbound

This paper cites Sheikholeslami, F., Jain, S., and Giannakis, G.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Sheikholeslami, F., Jain, S., and Giannakis, G

Reference 2009

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T04:41:03.989787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7e937633-e5ae-42cd-b950-f86dacc478ee · outbound

This paper cites Scaling Laws for Neural Language Models.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Scaling Laws for Neural Language Models

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.376177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 539d24a9-c273-4cf1-9b5a-36bccbdec6b0 · outbound

This paper cites an unresolved cited work.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Unresolved cited work

Reference 2019

Resolution: unresolved; raw_fallback, observed 2026-08-12T04:41:03.972963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6646521b-2d82-476a-8c44-33ef67b292aa · outbound

This paper cites and Byrne, B.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models and Byrne, B

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T04:41:04.024125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 46d0041a-232a-4efc-abec-616d49a8c71f · outbound

This paper cites Sambanova sn40l rdu: Breaking the barrier of trillion+ parameter scale gen ai computing.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Sambanova sn40l rdu: Breaking the barrier of trillion+ parameter scale gen ai computing

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T04:41:04.007377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 653edab9-299f-46f9-a957-117863ddf284 · outbound

This paper cites Mistral 7B.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Mistral 7B

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.363331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1fce6c2-7637-4461-960c-080615f18245 · outbound

This paper cites Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference.

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-12T04:41:03.356822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d43ddf81-6576-4f2c-9476-c4092f80cff8 · inbound

Arch-Router: Aligning LLM Routing with Human Preferences cites this paper.

Arch-Router: Aligning LLM Routing with Human Preferences Composition of Experts: A Modular Compound AI System Leveraging Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T19:25:21.884249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5019aa6d-80f7-4a5e-ba79-b6bd8694ef35 · inbound

CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering cites this paper.

CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering Composition of Experts: A Modular Compound AI System Leveraging Large Language Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:09:39.960736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.