Pith. sign in

Paper Citation Record · LEDGER

Power and Limitations of Aggregation in Compound AI Systems

As of 19 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2602.21556.

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

pith.paper-citation-record.v1
2602.21556 v2

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T21:09:53.841676Z

measured 59 of 59 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-09T20:20:26.414236Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T15:16:10.782925Z

Reference resolution

58 of 58 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved58
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d50f016e-a0bb-4793-a944-34a623450a7a · outbound

This paper cites Multiagent evaluation mechanisms.

Power and Limitations of Aggregation in Compound AI Systems Multiagent evaluation mechanisms

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:48.343087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:48.343087Z digest=sha256:f8358be55d04e0ed0a1d9a69a12648dea387843bacd8736b20e206241d829f03

Observation 97295ece-5a69-406d-b116-f8852b8b5724 · outbound

This paper cites How we built our multi-agent research system.

Power and Limitations of Aggregation in Compound AI Systems How we built our multi-agent research system

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:48.460186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:48.460186Z digest=sha256:4fd0d8462d1cb150231e3b971c6e6a24d019af2639cbc3c92b333f592b279372

Observation b775d29f-7162-4589-b7eb-43e426c3fb62 · outbound

This paper cites Ask Me Anything: A simple strategy for prompting language models.

Power and Limitations of Aggregation in Compound AI Systems Ask Me Anything: A simple strategy for prompting language models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:48.568672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:48.568672Z digest=sha256:912f95386809ad59426021da3853c9ed53bcb148179d7989dfa63d5584ef7794

Observation dbc429fe-930f-425d-b94b-9ad00c07ec25 · outbound

This paper cites Compound ai systems.

Power and Limitations of Aggregation in Compound AI Systems Compound ai systems

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:48.678645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:48.678645Z digest=sha256:77ab9c2b5cd952bdfecd41a8cd2c42a76fe9991b7e4574aad3521354ae32b3b4

Observation b8238315-ad47-4355-8780-d62216338614 · outbound

This paper cites Does the whole exceed its parts? the effect of ai explanations on complementary team performance.

Power and Limitations of Aggregation in Compound AI Systems Does the whole exceed its parts? the effect of ai explanations on complementary team performance

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:48.764204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:48.764204Z digest=sha256:76f583caa468def77edb8709aac97d742fb99adffac45c483e0197627bf86035

Observation 7568e28b-578f-45a1-a08d-78b5a874cb92 · outbound

This paper cites Regression equilibrium.

Power and Limitations of Aggregation in Compound AI Systems Regression equilibrium

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:48.863090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:48.863090Z digest=sha256:0f4918e7888a0cc609d1bc01b1b64db5a7a169b77406dabe61ef759ccbb6fbda

Observation ad57e8c2-4ad6-4184-835d-e933084730be · outbound

This paper cites Multitask principal--agent problems: Optimal contracts, fragility, and effort misallocation.

Power and Limitations of Aggregation in Compound AI Systems Multitask principal--agent problems: Optimal contracts, fragility, and effort misallocation

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:48.950710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:48.950710Z digest=sha256:f7de4f4f1825f4f2c1cfdb46f5900b66ac6a484d15745dbc9a1ed6ac687f4903

Observation 41e8f2b6-3b1b-439d-8363-223f75b647da · outbound

This paper cites Solutions Manual to Accompany Contract Theory, volume 1.

Power and Limitations of Aggregation in Compound AI Systems Solutions Manual to Accompany Contract Theory, volume 1

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.037263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.037263Z digest=sha256:d6c48c8302d47fd5ba2bd9ca6ae66e5151837ac2c5dfee6d86b2e54017e42c44

Observation c5bc77a0-b054-4461-bee4-be19ce2cd4f0 · outbound

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

Power and Limitations of Aggregation in Compound AI Systems FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.118067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.118067Z digest=sha256:61b7d7a9f9db1b0a6df841628a0305a04aeb0b66c22289e2df89d0e1c2caf8f6

Observation e2473506-036e-48c7-9c9c-e7be5bc58b8c · outbound

This paper cites Direct preference optimization with unobserved preference heterogeneity: The necessity of ternary preferences.

Power and Limitations of Aggregation in Compound AI Systems Direct preference optimization with unobserved preference heterogeneity: The necessity of ternary preferences

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.216355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.216355Z digest=sha256:df085f6fc6182a359e3773adea69661b64d9852069d2fc47c45659dfa8f52d86

Observation 3e5e7ecd-8d38-40e4-970e-4fa4cd7af835 · outbound

This paper cites Deep reinforcement learning from human preferences.

Power and Limitations of Aggregation in Compound AI Systems Deep reinforcement learning from human preferences

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.329907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.329907Z digest=sha256:cd9e2dcda30588ed414b1f68aa72932c798d149d73375a5386b75920ee0d898a

Observation e755d06d-e9d0-4092-8f19-90794929fa07 · outbound

This paper cites Emergent alignment via competition.

Power and Limitations of Aggregation in Compound AI Systems Emergent alignment via competition

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.402822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.402822Z digest=sha256:53a53c3b5e28ddaa0a8d9f1b2e1efc68d6416f0c8273240f52e27d95c3d47e75

Observation fc3f9a37-e4b3-4d1b-b7ea-df950e95512d · outbound

This paper cites Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback.

Power and Limitations of Aggregation in Compound AI Systems Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.481965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.481965Z digest=sha256:b009d46bfcd5ef1753a50dfe48d1e774d5d51968786d0802435faf2568c6cbd3

Observation cf3358a2-13d2-4260-a988-dfd0c2063134 · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

Power and Limitations of Aggregation in Compound AI Systems OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.563604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.563604Z digest=sha256:fa2a527e54a977c79c983d0852f44bee241a8d233046cd5cae0d40fa7bb4b6af

Observation 89d91a83-6b06-4717-b497-66f3d2b0a461 · outbound

This paper cites Mapping Social Choice Theory to RLHF.

Power and Limitations of Aggregation in Compound AI Systems Mapping Social Choice Theory to RLHF

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.653682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.653682Z digest=sha256:0828112b808f612e5dc80c76b5a0f119178eff1be6d5770c859a0a2a8d768f15

Observation 804cf1d0-eda4-462d-8655-a5e98a52f41c · outbound

This paper cites Incentive Design with Spillovers.

Power and Limitations of Aggregation in Compound AI Systems Incentive Design with Spillovers

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.741771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.741771Z digest=sha256:f3e5b5ae63b76e5075efe06da792672b704210d5048cc25f5e320721da28b9e8

Observation af239772-4bc4-4bcd-a614-8c3dda7e50d4 · outbound

This paper cites Ensemble methods in machine learning.

Power and Limitations of Aggregation in Compound AI Systems Ensemble methods in machine learning

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.821661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.821661Z digest=sha256:f89ff4d35da489bf44823fa9d91f4f8c68ccec97a2cb157c7c6bcb11f661cb2b

Observation 08c3fa7a-d1b1-47e8-90da-563d32f239df · outbound

This paper cites Impacts of aggregation on model diversity and consumer utility.

Power and Limitations of Aggregation in Compound AI Systems Impacts of aggregation on model diversity and consumer utility

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.897229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.897229Z digest=sha256:689140b10851ab557e006050379c4989ac839a20e337bef634485c316f60208d

Observation 500b38bd-ae8b-4b0f-9617-d585275b73b9 · outbound

This paper cites Human-algorithm collaboration: Achieving complementarity and avoiding unfairness.

Power and Limitations of Aggregation in Compound AI Systems Human-algorithm collaboration: Achieving complementarity and avoiding unfairness

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:49.973020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:49.973020Z digest=sha256:2361fcdddfcdc25f0ae00a9c3faa4566520c2413eaae2fd1374129d0ce27e3d6

Observation 6ec484f6-5faf-41ad-b2f6-a73d0da325d2 · outbound

This paper cites Improving factuality and reasoning in language models through multiagent debate.

Power and Limitations of Aggregation in Compound AI Systems Improving factuality and reasoning in language models through multiagent debate

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.051137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.051137Z digest=sha256:79cca0ea6ffa9dc3297f08c8e6ccf5cbedf845a3dda2c61bd8bd390bb577b5df

Observation abdc40ce-d23d-441e-bde2-c5c052ec4f2c · outbound

This paper cites A market for accuracy: Classification under competition.

Power and Limitations of Aggregation in Compound AI Systems A market for accuracy: Classification under competition

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.128531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.128531Z digest=sha256:d7de602a16bc48e4231954d334ca50a736c41b2a78c21048db46b21da005ab80

Observation edec1dfa-3996-46d4-aa50-c8b9c32fd205 · outbound

This paper cites Bayesian persuasion with multiple senders and rich signal spaces.

Power and Limitations of Aggregation in Compound AI Systems Bayesian persuasion with multiple senders and rich signal spaces

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.203845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.203845Z digest=sha256:aa3b47513d3db8352722d712b5aa44d70db4028bb408c9761c5403a64ba862bd

Observation 551547b7-8d69-4119-a622-2bb0160cf755 · outbound

This paper cites Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?.

Power and Limitations of Aggregation in Compound AI Systems Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.286275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.286275Z digest=sha256:b3811625be015c077a2f4626bb927a993fa5e2920414c521771bf79871fa12c3

Observation ec88ce40-6e5e-48bc-a141-e62b32b9a075 · outbound

This paper cites An analysis of the principal-agent problem.

Power and Limitations of Aggregation in Compound AI Systems An analysis of the principal-agent problem

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.370893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.370893Z digest=sha256:00c940b4c2cd941b401de8ae0445ca34885a670de08e0ac677c732d312eae6e7

Observation 19a10269-01ef-402c-b7f6-e9ca35116f4d · outbound

This paper cites Moral hazard and observability.

Power and Limitations of Aggregation in Compound AI Systems Moral hazard and observability

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.446900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.446900Z digest=sha256:a34ecdc1121d6c87d80d6bc05be1bdd11e72481a3331ed413ab25e82a7d85438

Observation e48d46e3-9882-47af-82fd-507b9f879d07 · outbound

This paper cites Moral hazard in teams.

Power and Limitations of Aggregation in Compound AI Systems Moral hazard in teams

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.518036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.518036Z digest=sha256:f91bb7e443d556cb644768b894c6384be714f4809838f96e6763f52fea106e6e

Observation 2612ef70-e79a-48da-acaf-7b85fe4ebe7a · outbound

This paper cites Multitask principal--agent analyses: Incentive contracts, asset ownership, and job design.

Power and Limitations of Aggregation in Compound AI Systems Multitask principal--agent analyses: Incentive contracts, asset ownership, and job design

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.595290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.595290Z digest=sha256:833c9237ca73a0cb1bdf76b70ea5cb3fe20a468ebfc865fc221913ae28345dce

Observation df4977b1-02c4-4a08-99ff-1fbfd9c39a30 · outbound

This paper cites Strategic Classification With Externalities.

Power and Limitations of Aggregation in Compound AI Systems Strategic Classification With Externalities

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.673927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.673927Z digest=sha256:dbba7fa02873e53f0bb9f87c9cfbbbd4d216e2c0c6d8dd2fb056f7f82f6273ff

Observation c57a163a-458e-4056-bf74-d67ec3e89580 · outbound

This paper cites Is best-of-n the best of them? coverage, scaling, and optimality in inference-time alignment.

Power and Limitations of Aggregation in Compound AI Systems Is best-of-n the best of them? coverage, scaling, and optimality in inference-time alignment

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.773477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.773477Z digest=sha256:7e1e035fda21e97c231a433051fcfcbdac57e9886ae033c7f36008d57f91a016

Observation 66a61a4a-7768-4f2d-aa5a-19875a9786ed · outbound

This paper cites The Consensus Game: Language Model Generation via Equilibrium Search.

Power and Limitations of Aggregation in Compound AI Systems The Consensus Game: Language Model Generation via Equilibrium Search

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.844723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.844723Z digest=sha256:87ee205bdf026d426ce6f01ac7c909931903dfdd125fc439ad6ee30f62fd1657

Observation 265bc117-f345-4d59-819a-e1db7d12e6b0 · outbound

This paper cites Improved bayes risk can yield reduced social welfare under competition.

Power and Limitations of Aggregation in Compound AI Systems Improved bayes risk can yield reduced social welfare under competition

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:50.931153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:50.931153Z digest=sha256:2bb6f0aa73ff11caf11170df1ebc4034aee04939de60455d6d86dbf74781215f

Observation 58ed631d-e57e-48a2-b9c2-086b6ceb355a · outbound

This paper cites Adversaries can misuse combinations of safe models.

Power and Limitations of Aggregation in Compound AI Systems Adversaries can misuse combinations of safe models

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.020648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.020648Z digest=sha256:49fccfcde065a341d0dee72a668a601dd2c3ca7c7db90010018bb860015eb0ac

Observation 8494f277-f18c-46fd-aeee-52f65d684c6b · outbound

This paper cites Uncovering gaps in how humans and llms interpret subjective language.

Power and Limitations of Aggregation in Compound AI Systems Uncovering gaps in how humans and llms interpret subjective language

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.096344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.096344Z digest=sha256:12fce9ea38532e65465a5960a80576331473e5cc37105599c2c219a6304bf931

Observation df655c6e-75a6-44d3-85f8-87b75e2b70b5 · outbound

This paper cites Debating with more persuasive llms leads to more truthful answers.

Power and Limitations of Aggregation in Compound AI Systems Debating with more persuasive llms leads to more truthful answers

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.185398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.185398Z digest=sha256:1bb37c9abfa555d0da885a05f47908dfef183fbf7287faae6ba06694a29260da

Observation f1ff9683-0cab-4d62-a025-c6ac019066a5 · outbound

This paper cites How do classifiers induce agents to invest effort strategically? ACM Transactions on Economics and Computation (TEAC), 8 0 (4): 0 1--23, 2020.

Power and Limitations of Aggregation in Compound AI Systems How do classifiers induce agents to invest effort strategically? ACM Transactions on Economics and Computation (TEAC), 8 0 (4): 0 1--23, 2020

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.264815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.264815Z digest=sha256:d4d503e54e69eda1c37c4d408e34c3c44fcb4cd1643c2c31012f9a2330ccbae0

Observation c47f5f43-eb4a-444f-928a-ee502163e86f · outbound

This paper cites The condorcet jury theorem, free speech, and correlated votes.

Power and Limitations of Aggregation in Compound AI Systems The condorcet jury theorem, free speech, and correlated votes

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.333883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.333883Z digest=sha256:287c1bcc7ca72c0cd40e031d89d2e413daa5dbe8f3cd163ce64ee477e86f440c

Observation f3b18ed7-b5ba-475f-acda-a038cad91340 · outbound

This paper cites The Theory of Incentives: The Principal-Agent Model.

Power and Limitations of Aggregation in Compound AI Systems The Theory of Incentives: The Principal-Agent Model

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.411382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.411382Z digest=sha256:093153f0ff0d56c2a6e87710514a0bba7e6300e8d670b642ddea76d9758985db

Observation 8bb7fc85-4d88-4839-af0d-d75954ab98fd · outbound

This paper cites Rank-order tournaments as optimum labor contracts.

Power and Limitations of Aggregation in Compound AI Systems Rank-order tournaments as optimum labor contracts

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.510271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.510271Z digest=sha256:3923ff1c95124f68d8f9a48213899bd5ac1e41bb58a0efb264b27471609b48b3

Observation 67cd8815-4750-4810-be36-bf444c00fe7a · outbound

This paper cites Alpacaeval: An automatic evaluator of instruction-following models, 2023.

Power and Limitations of Aggregation in Compound AI Systems Alpacaeval: An automatic evaluator of instruction-following models, 2023

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.586380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.586380Z digest=sha256:ff0226d92bea6cb28594635aa08e9af442b3fb60c8345e8582cf9f41c52abbbd

Observation 18d39a60-88ae-4196-98ce-ca6f73a46281 · outbound

This paper cites Strategic ranking.

Power and Limitations of Aggregation in Compound AI Systems Strategic ranking

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.663223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.663223Z digest=sha256:da9800bec0c73fd2068c01ab0f2012d8f0d616ef32852b3148c40a6dd985023f

Observation c01e027e-f63d-4b5a-883c-c563b0b0010b · outbound

This paper cites Recast: Strengthening llms' complex instruction following with constraint-verifiable data.

Power and Limitations of Aggregation in Compound AI Systems Recast: Strengthening llms' complex instruction following with constraint-verifiable data

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.822511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.822511Z digest=sha256:70694d2bfb2e60e4a63ed4dc4e26d10450bc1a6043f5fe401c1353ff0ef24e64

Observation b5b3e28d-af30-43d2-98ad-40393f0d1c84 · outbound

This paper cites Distributed algorithms.

Power and Limitations of Aggregation in Compound AI Systems Distributed algorithms

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:51.952921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:51.952921Z digest=sha256:ec10d9ff85756060611b9bf1c64e34de9639c35eecd7cf1f05c333facd49d27f

Observation ec057275-683f-4603-af67-69543d0ef6c1 · outbound

This paper cites AI Alignment and Social Choice: Fundamental Limitations and Policy Implications.

Power and Limitations of Aggregation in Compound AI Systems AI Alignment and Social Choice: Fundamental Limitations and Policy Implications

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:52.099062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:52.099062Z digest=sha256:847f93b3e827d29c8d8c8d5a4aa100b8900507e43362070dabdc9b7d2f8bbc60

Observation 6b87ff97-c7c3-4674-87ff-49ea38692f30 · outbound

This paper cites Training language models to follow instructions with human feedback.

Power and Limitations of Aggregation in Compound AI Systems Training language models to follow instructions with human feedback

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:52.239536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:52.239536Z digest=sha256:16b87273998c5b27fb71896d53eb2fdad66817fe48b79ecf3f64c3c778802fa6

Observation 4104c5c6-ef1b-4a7e-b8e1-4bf73a607627 · outbound

This paper cites Citeme: Can language models accurately cite scientific claims? Advances in Neural Information Processing Systems, 37: 0 7847--7877, 2024.

Power and Limitations of Aggregation in Compound AI Systems Citeme: Can language models accurately cite scientific claims? Advances in Neural Information Processing Systems, 37: 0 7847--7877, 2024

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:52.374019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:52.374019Z digest=sha256:cb5d1165bbf0e042e70952abfae4c9e4eb4eaf59e20d7ba8ebfb379795e8bf9f

Observation 1960e949-5356-45bf-b602-d17cfe94ae35 · outbound

This paper cites Competition and Diversity in Generative AI.

Power and Limitations of Aggregation in Compound AI Systems Competition and Diversity in Generative AI

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:52.559841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:52.559841Z digest=sha256:a68ea89030db42677fe3ecfbac9ece971804e868732f0a9d80cd5edd4fbf60e7

Observation 26a35d66-5010-4a60-84cf-e9b242532877 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Power and Limitations of Aggregation in Compound AI Systems Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:52.717157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:52.717157Z digest=sha256:916c192d24954e64bdfa13c7d6213bcb3a9fca4f52e04e63b03513c559c566e1

Observation 02e28d33-848f-49b7-85f4-a804264969da · outbound

This paper cites Direct Alignment with Heterogeneous Preferences.

Power and Limitations of Aggregation in Compound AI Systems Direct Alignment with Heterogeneous Preferences

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:52.874430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:52.874430Z digest=sha256:7f4b324493ada20ce8b803c7664afdf119c7330e583e03ec0197d69520779cfe

Observation df02ea31-9c72-4cc9-aa88-f4c37f7eec81 · outbound

This paper cites A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models.

Power and Limitations of Aggregation in Compound AI Systems A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.093539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.093539Z digest=sha256:56d34295e93b29086eea92e7e5b11b297d2cfbc22739fef10a8e99c2ed1e1270

Observation 225c2efc-0a5b-4da2-9b36-15e995167063 · outbound

This paper cites Multitask agency and contract choice: An empirical exploration.

Power and Limitations of Aggregation in Compound AI Systems Multitask agency and contract choice: An empirical exploration

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.223652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.223652Z digest=sha256:57517a08a2aae274daf055be20b03408c6ea7d293ee03887b657d0cb756f0ff9

Observation 56eb09af-4ce6-45d8-9c53-b8dd38d8087c · outbound

This paper cites Multi-agent reinforcement learning: Independent vs.

Power and Limitations of Aggregation in Compound AI Systems Multi-agent reinforcement learning: Independent vs

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.321269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.321269Z digest=sha256:ba27c0b52d1444e1f04f8f58269f6aebc6a75dcd95c3afebf99b071abc0a467c

Observation 7c5b7a25-fd14-4905-9cc4-c1f3b8fbcc4a · outbound

This paper cites SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models.

Power and Limitations of Aggregation in Compound AI Systems SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.391102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.391102Z digest=sha256:8c02015f4c5bb951c0031e515be144539df1ee1a2972ae61ed0bccf33305f7ad

Observation b2abef6c-e5dc-4d64-8599-89f7ee421f2c · outbound

This paper cites Self-consistency improves chain of thought reasoning in language models.

Power and Limitations of Aggregation in Compound AI Systems Self-consistency improves chain of thought reasoning in language models

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.469858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.469858Z digest=sha256:51b79a921c8c4d8eb9b795ac48a1b8df944dde391a236924c8555570ebcafcd1

Observation c2d0732e-488f-4631-9300-a6ec474658de · outbound

This paper cites Benchmarking complex instruction-following with multiple constraints composition.

Power and Limitations of Aggregation in Compound AI Systems Benchmarking complex instruction-following with multiple constraints composition

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.555203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.555203Z digest=sha256:9c97450d1d1a90f0dd91a8d3b956dd4fefda6b72859cff6e32b4a2d6620c3dae

Observation b0b28776-18b7-4624-a61e-1a53f048d2ec · outbound

This paper cites Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources.

Power and Limitations of Aggregation in Compound AI Systems Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.630491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.630491Z digest=sha256:a428b3c686959c765e6ccd4aa5e733448099f5af2d8fb5771eab389c2e0adbe0

Observation 8b442a11-c518-45c6-a73f-2e8ebfb48ed9 · outbound

This paper cites What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts.

Power and Limitations of Aggregation in Compound AI Systems What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.695023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.695023Z digest=sha256:5087d1e750116e64954ccd744da7f275819cf294ef53d49715889eff3d4e9b3d

Observation 7c43beee-49cc-49bd-bc0e-d96b2c7d46cb · outbound

This paper cites Cot-based synthesizer: Enhancing llm performance through answer synthesis, 2025.

Power and Limitations of Aggregation in Compound AI Systems Cot-based synthesizer: Enhancing llm performance through answer synthesis, 2025

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.777602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.777602Z digest=sha256:20cc48b5824109244922e6cade1d34eac009371704cb47deef778f3e69160171

Observation cb084f28-d2d3-43ca-9080-f141ee79517a · outbound

This paper cites Consequences of misaligned ai.

Power and Limitations of Aggregation in Compound AI Systems Consequences of misaligned ai

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-02T21:09:53.841676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T21:09:53.841676Z digest=sha256:60d48976507f0639c722100ec7a2eb60318b004986664234749490be9992bb61

Pith citing papers

Observation 75310491-50ba-4ac7-bc57-4ea0a4de647c · inbound

The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate cites this paper.

The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate Power and Limitations of Aggregation in Compound AI Systems

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-07-09T02:19:51.091671Z

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=2026-05-09T20:20:26.414236Z digest=sha256:07aa1918875e43ee3b3aee4f926e51bbd308682273ee6520ca3a13765385ef65