Pith. sign in

Paper Citation Record · LEDGER

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

As of 18 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 3 inbound Pith citation observations for arXiv:2606.27288.

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

pith.paper-citation-record.v1
2606.27288 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T04:20:02.722108Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:41:10.574009Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-12T00:41:10.746614Z

Reference resolution

41 of 41 outbound references displayed

  • verified exact15
  • verified fuzzy0
  • unresolved26
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 29adf54a-3eaf-4138-9d50-dda2e5150d05 · outbound

This paper cites Tsitsiklis.Introduction to Linear Optimization.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Tsitsiklis.Introduction to Linear Optimization

Reference 1

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:90d7674fcd913b3ff29c9779c47b02c27a40100087ce18ba8c906353f7de236d

Observation 2dc3ce6b-f435-4b40-9f5f-f0a136238bab · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-07-04T14:19:53.605412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:adcb29fbcf6c7450b8e1d9c227b3b249f02845f34abd13157caa59e5749b0acd

Observation a0e6b167-2495-4d6e-b59d-072321e1e509 · outbound

This paper cites A Unified Approach to Routing and Cascading for LLMs.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models A Unified Approach to Routing and Cascading for LLMs

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.608705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:ed537eb1f709942da7067378384590ced63f24ebafab7b64538212810a6fb15b

Observation e0a5ee80-656a-4a0b-bb88-22f96aa57379 · outbound

This paper cites an unresolved cited work.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:3fe9addc0d5fb8ca00ba348eb0282a343519597279a1537774d2a234ba12d460

Observation b7c2c181-8a7f-45fa-8658-bc72922e1a27 · outbound

This paper cites Dixit and Robert S.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Dixit and Robert S

Reference 5

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:aade372025b32f07eb600d1744ee2f570ae84842b6ef443984eb6faeadfe46d3

Observation 5ea4d041-c992-4d89-a9f4-e5a670fef573 · outbound

This paper cites The devil is in the tails: actuarial mathematics and the subprime mortgage crisis.ASTIN Bulletin, 40(1):1–33, 2010.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models The devil is in the tails: actuarial mathematics and the subprime mortgage crisis.ASTIN Bulletin, 40(1):1–33, 2010

Reference 6

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:dd63ce07f9d3369aa97017cf38ce710852ce50420a99672f5a0db057ad04cbe4

Observation 4a9f4280-bdf1-420d-9993-cf5973b101a3 · outbound

This paper cites McNeil, and Daniel Straumann.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models McNeil, and Daniel Straumann

Reference 7

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:1958c1c99cef6c65c327a39001b06aa8dc45de2ec9beddcb5e15ee3ae09ec158

Observation fba27e13-c8e2-49c1-add2-d84227863693 · outbound

This paper cites Cost-of-Pass: An economic framework for evaluating language models.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Cost-of-Pass: An economic framework for evaluating language models

Reference 8

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.630618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:4be2217f584b19cd3a0e2209a618e40e6a47eb6e5dce98342757dffe038c081d

Observation 6b3e4cd1-9d6c-4519-afba-38479407a4e1 · outbound

This paper cites Representation of multivariate bernoulli distributions with a given set of specified moments.Journal of Multivariate Analysis, 168:290–303, 2018.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Representation of multivariate bernoulli distributions with a given set of specified moments.Journal of Multivariate Analysis, 168:290–303, 2018

Reference 9

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:6a003750e56defa87ac72b5a31cd1c1fcccad2d3fa131e1963ae1d0353dd599b

Observation d6d2f1b2-fd34-4ae9-a1cc-fe6000bea71d · outbound

This paper cites Selective classification for deep neural networks.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Selective classification for deep neural networks

Reference 10

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:1331418d9d0dc3d4c3af7ea96f8c416f3a86b34fecb05eee4e52062241ba374d

Observation af26074b-a7e9-40ab-b757-3cd2225a0ad8 · outbound

This paper cites an unresolved cited work.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:3e8bb21514deec484316a877206dcb71a560b3da84387769d3228ac6149c70b3

Observation 87e67d21-b3bf-4fc0-9a65-eeb7ff031ddf · outbound

This paper cites RouterBench: A Benchmark for Multi-LLM Routing System.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models RouterBench: A Benchmark for Multi-LLM Routing System

Reference 12

Resolution
verified exact
local_arxiv, observed 2026-07-04T14:19:53.617760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:54cc7985e1aa78087f6aafa541472ec6686474e58aea7b74fccc038dd7994d66

Observation e46e67cd-140b-4bef-8264-3858b6cb8fa1 · outbound

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

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

Reference 13

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.623152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:ee04df1aee103ab03f5fa64066b671e797290cac64f8750f623737e4a5eae73f

Observation 76cc74b8-4988-45d5-9f6a-ae6eda2d43ef · outbound

This paper cites When Does Confidence-Based Cascade Deferral Suffice?.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models When Does Confidence-Based Cascade Deferral Suffice?

Reference 14

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.614862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:0949e000eb4618a63f9ec7ad77787b3229f2f9da5483541f1b9eae8e4c8274e8

Observation 93dd0bbe-ba52-4994-86c4-7581c0363fd6 · outbound

This paper cites Correlated Errors in Large Language Models.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Correlated Errors in Large Language Models

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.636552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:74085118e81594afba4853ee04de38f3e45db693892393f7adf9c26b89f28081

Observation b194c67a-da44-4ec2-b303-bc6d1b61ea71 · outbound

This paper cites Algorithmic monoculture and social welfare.Proceedings of the National Academy of Sciences, 118(22):e2018340118, 2021.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Algorithmic monoculture and social welfare.Proceedings of the National Academy of Sciences, 118(22):e2018340118, 2021

Reference 16

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:f2d15293b4aa9554e6ee7de3af513b9e843b38aa6aef807eab759c4e9a132245

Observation b5500eae-2104-4ef6-b980-6eb5492a9f77 · outbound

This paper cites Competition when consumers have switching costs.The Review of Economic Studies, 62(4):515–539, 1995.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Competition when consumers have switching costs.The Review of Economic Studies, 62(4):515–539, 1995

Reference 17

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:b0559d28cf46409aacd2e704d6b14d519f9429ccc54331fc36807026eb52b114

Observation 14b14b7c-f165-468f-9c7c-1860a180d49f · outbound

This paper cites Neural network ensembles, cross validation, and active learning.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Neural network ensembles, cross validation, and active learning

Reference 18

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:2e662c1925a4d50cff7ad12668eae4a442f5d3e3bd4776a23b6301c52a9001e1

Observation 992fb59f-d57e-4117-aa01-a5ffb10229b4 · outbound

This paper cites Kuncheva.Combining Pattern Classifiers: Methods and Algorithms.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Kuncheva.Combining Pattern Classifiers: Methods and Algorithms

Reference 19

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:ed9d201cc0358e5ba68d760bb0885cc0ca10b4be0fd6eb977c8165d7d9d89ab0

Observation 856a3bd3-8fc1-4599-a38b-26179db0b208 · outbound

This paper cites Kuncheva and Christopher J.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Kuncheva and Christopher J

Reference 20

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:88401ad05241f51c47fd686a30ea7006b1dfd31cfa2725dd8d4848678ea802e7

Observation 920f41c9-796e-4293-bc94-69f7de978bd8 · outbound

This paper cites Kuncheva, Christopher J.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Kuncheva, Christopher J

Reference 21

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:31e86470714a043b8500bbaa8f5a75237347f13d0cc729bec9c5d979caaf7194

Observation 626256e9-dcd7-4660-aa07-1eaf46bc3228 · outbound

This paper cites an unresolved cited work.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:d0144b075625f6b604ef932ec5b9260082cc5d200310b47e5d50e904e54d9cf8

Observation 357129bc-5886-4d02-a8af-e471df4bed69 · outbound

This paper cites More Agents Is All You Need.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models More Agents Is All You Need

Reference 23

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.627458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:1bd87e3ca7c401721a8b779fc2906d15f828a117926c680ff2aba71c1ad7bd4d

Observation 5b5ad1f4-9ad7-4094-9b23-956c4ad5419d · outbound

This paper cites Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?

Reference 24

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.611757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:2e5189a0c0eb04dbee278d3a3abf915f766cf7c519a3054845cac7a050588d3e

Observation 865e11cb-6d15-4afd-89e4-f47b1f83dc9b · outbound

This paper cites AutoMix: Automatically Mixing Language Models.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models AutoMix: Automatically Mixing Language Models

Reference 25

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.633575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:973417419e73a6e1dfc932efcfc9baf7953abb114ceae07589a664c665fe9d14

Observation 8f018305-73eb-4b85-a6ba-34989c492da8 · outbound

This paper cites Portfolio selection.The Journal of Finance, 7(1):77–91, 1952.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Portfolio selection.The Journal of Finance, 7(1):77–91, 1952

Reference 26

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:7ff45a31114dbfb2ef3fa3e95855a3b1f26d67137787f079ad36ff5be5b924e7

Observation 0b533e17-de81-4770-90ca-fd45c94ae6ea · outbound

This paper cites Marshall and Ingram Olkin.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Marshall and Ingram Olkin

Reference 27

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:3dc352b8d4884936aced6291a1f73091f31c86a201a7e039927c5c03de14bf5a

Observation e390aa53-487c-472c-9fd6-3fac86aadf17 · outbound

This paper cites The value of waiting to invest.The Quarterly Journal of Economics, 101(4):707–727, 1986.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models The value of waiting to invest.The Quarterly Journal of Economics, 101(4):707–727, 1986

Reference 28

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:2dcb16a60217b18d0605e29c2f965d7dba56f3018570f0fe1b6c6031726e080d

Observation 2ab27fe4-d1f5-408c-b09e-89c9af180ba5 · outbound

This paper cites an unresolved cited work.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Unresolved cited work

Reference 29

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:6fdbebc608741bf91aed7ef0e62d607ff5b3ccd3a35d52ee0c646dc9f94d903f

Observation 63c4cfb9-ee5e-463c-8452-a3f134ca8e20 · outbound

This paper cites Maximum likelihood estimation of the polychoric correlation coefficient.Psychome- trika, 44(4):443–460, 1979.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Maximum likelihood estimation of the polychoric correlation coefficient.Psychome- trika, 44(4):443–460, 1979

Reference 30

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:9661f5bac64149a8d59a91842b200c0fc84424e98dd7b9b14cf5278d5a2342a0

Observation fa7d0f24-9617-44dc-9cbb-3369fe87ec2c · outbound

This paper cites RouteLLM: Learning to Route LLMs with Preference Data.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models RouteLLM: Learning to Route LLMs with Preference Data

Reference 31

Resolution
verified exact
local_arxiv, observed 2026-07-04T14:19:53.620197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:6f63dbae7fd4f5c7dc1d9132c01be20e146d4957c2a44de982e3d13a658b56d4

Observation 82fe22aa-69da-49e0-a3b4-37a0d187e978 · outbound

This paper cites Mathematical contributions to the theory of evolution.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Mathematical contributions to the theory of evolution

Reference 32

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:b4bdb3511d4f7cf552c57c98de349cefbf27eaca3b24b4f2cd937ff044c00dba

Observation f798fb30-40b5-4310-aac8-0241ee463e85 · outbound

This paper cites Bivariate extreme statistics, i.Annals of the Institute of Statistical Mathematics, 11(2):195–210, 1959.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Bivariate extreme statistics, i.Annals of the Institute of Statistical Mathematics, 11(2):195–210, 1959

Reference 33

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:a8bcadad08872f7c472ac7d13de399c57b236eb5834280e1e5baa9b0989cec73

Observation e641ab3b-d1ff-4cf3-8d11-0cd60afcb3e3 · outbound

This paper cites How many stocks make a diversified portfolio?Journal of Financial and Quantitative Analysis, 22(3):353–363, 1987.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models How many stocks make a diversified portfolio?Journal of Financial and Quantitative Analysis, 22(3):353–363, 1987

Reference 34

Resolution
verified exact
doi, observed 2026-06-26T05:29:00.401113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:47a64dc17db3e65e07c8c5db8e46ffc31dfc513bcac201f4f308089a3935defd

Observation 8d2f9bd3-7770-4368-90c5-72294826820b · outbound

This paper cites arXiv preprint arXiv:2602.08003 , year =.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models arXiv preprint arXiv:2602.08003 , year =

Reference 35

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.639847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:34589fad13d3f03865a8b394a92915e327050edf5c2c5a076512a5f4e4f51c18

Observation 97ce85bb-34e9-4212-8de9-c4ef6fd1cc07 · outbound

This paper cites Generalization error of ensemble estimators.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Generalization error of ensemble estimators

Reference 36

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:58e79de15c41ee270a7a281f9449be3764a73e721a79ab9df00debe53d75c693

Observation 962a02f0-6fe8-4431-9b1b-7eb7db5bacfb · outbound

This paper cites Mixture-of-Agents Enhances Large Language Model Capabilities.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Mixture-of-Agents Enhances Large Language Model Capabilities

Reference 37

Resolution
verified exact
local_arxiv, observed 2026-07-04T14:19:53.602587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:62e236befd31b6f310d1a57e8d1caed80f87db8b0c72908f292217c273ea3e2e

Observation 66a6a302-1149-45d3-9eb5-a31e24118f6b · outbound

This paper cites A Unified Theory of Diversity in Ensemble Learning.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models A Unified Theory of Diversity in Ensemble Learning

Reference 38

Resolution
verified exact
arxiv_id, observed 2026-07-04T14:19:53.642727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:6185ceaf83697d2464a121f7ec75e7250a782425cb5ece1ad465564be828b657

Observation 5f08d2c2-699d-46fe-8bde-472e06548d04 · outbound

This paper cites an unresolved cited work.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:86155c86bdd4c74a5bcec06e18acd0dff9ca8bd2e2d77ed3194cc8dadbb632c6

Observation 7e00cdc3-ce17-41e2-90a8-8f6c4affdca7 · outbound

This paper cites thinking.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models thinking

Reference 40

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:ec1cfb2c28e86494f20af55fadd1c45beafe6c46fd27bb68d1c351f4fe185cb1

Observation b1dde4e9-a8c0-4d18-8c72-fe784d82909f · outbound

This paper cites an unresolved cited work.

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Unresolved cited work

Reference 41

Resolution
unresolved
no resolver link, observed 2026-06-26T04:20:02.722108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T04:20:02.722108Z digest=sha256:b9973576a7f9069bc71d5640fb8c82241dd3652482524a7b01e429381c7f0eab

Pith citing papers

Observation ea57aa22-70df-40c7-90f3-f3e5ff7bf5e1 · inbound

How Much of the Routing Gap Is Real? Decomposing the Router-to-Oracle Gap into Reproducible Specialist Advantage and Single-Draw Label Noise cites this paper.

How Much of the Routing Gap Is Real? Decomposing the Router-to-Oracle Gap into Reproducible Specialist Advantage and Single-Draw Label Noise When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

Reference 40

Resolution
unresolved
no resolver link, observed 2026-07-12T02:29:58.886380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-12T02:29:58.886380Z digest=sha256:23f1d7b559876be9f22357c10d4c507f6c0d0ba3c7b99a3b8890102090011c6b

Observation 894c4f17-0c41-42e5-842e-2c4aed807acf · inbound

Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles cites this paper.

Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-01T09:29:48.309226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T09:29:48.309226Z digest=sha256:1aae0a8e0dc27c75e1e1b670c4ba311fb608d3c4514fac5d0968d462f5fac669

Observation b3470af0-420f-431f-890c-f6967526c631 · inbound

Evaluator Ensembles Under Reward Hacking: Covariance Geometry and Finite-Search Guarantees cites this paper.

Evaluator Ensembles Under Reward Hacking: Covariance Geometry and Finite-Search Guarantees When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

Reference 28

Resolution
metadata mismatch
local_arxiv, observed 2026-08-12T00:41:10.753254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=arxiv_source observed=2026-08-12T00:41:10.574009Z digest=sha256:36942d3e2f667d23bcb0443840d0ced69d607df6f6dc2c160be0ae4fec2e889c