Pith. sign in

Paper Citation Record · LEDGER

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems

As of 9 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2607.21627.

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

pith.paper-citation-record.v1
2607.21627 v1

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T08:17:29.480487Z

measured 66 of 66 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

66 of 66 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved66
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f3f5ab54-886a-4dd7-9087-d351521a358f · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:21.983018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:21.983018Z digest=sha256:15c26bfb2d3950e5667b0e57a54b12a1dbdeccb8d89403c1f478e155e7ff111e

Observation 12f45190-ee13-4e68-be97-7871fb07c34c · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:22.174157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:22.174157Z digest=sha256:55674e8a107c0d4f531438eef445ef2ea14c57c72cd5898a099d4fc9f5f3d4ab

Observation 567d3d60-41d9-42e3-bfd9-ca7c4d6303fc · outbound

This paper cites 2022 , doi=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems 2022 , doi=

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:22.316803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:22.316803Z digest=sha256:038c23a8ec74d5f63fef8b26f9f1f8b4234a6af7b59977219785adefe3028ad3

Observation 6ab84b70-1828-4c90-8a8c-16c1e5a57b9a · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems A General Language Assistant as a Laboratory for Alignment

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:22.406938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:22.406938Z digest=sha256:fa14a639fc40e991e0cdd1a6f5a50a5f474d31447fdfdca5a2568f0f1bbcab81

Observation 11d4c5ec-c1ce-4b12-afc9-d8ae18453d3b · outbound

This paper cites Nature human behaviour , volume=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Nature human behaviour , volume=

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:22.504116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:22.504116Z digest=sha256:a6e779dd8d4faf1a2b83a792be938c6478a49a29bb458362e1f114c3718d8c06

Observation e07c777a-8093-457f-944b-4d08a356e593 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Constitutional AI: Harmlessness from AI Feedback

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:22.641299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:22.641299Z digest=sha256:97f2d20267c4ed61f06f34d7544d06e7a391c91da5e9423a98cb38778304d8af

Observation 2006f101-8fd0-46dc-831d-84a4f25ff9d9 · outbound

This paper cites Breaking Neural Network Scaling Laws with Modularity.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Breaking Neural Network Scaling Laws with Modularity

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:22.735877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:22.735877Z digest=sha256:a062a28dd8fd3c0749563ae330933056a5c277f7f3acb317022f73df3232f7f5

Observation 9f53f4a4-45e6-40ad-ba7f-f22b17adc4c6 · outbound

This paper cites Why Do Multi-Agent LLM Systems Fail?.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Why Do Multi-Agent LLM Systems Fail?

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:22.854953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:22.854953Z digest=sha256:42ffa0dda583d678f15638b8158bce94d2dbf5a45161dea860f7529e7df4ab1d

Observation af9f4ee6-9fa2-4361-bd97-addd14a73f41 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Advances in Neural Information Processing Systems , volume=

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:23.013749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:23.013749Z digest=sha256:4423f6430f71569f124c3a4cbf0ebb59b7b68a0fa6a38d65603ff40ea9747e3b

Observation 7961f166-f795-4164-bbb5-cdf47fdf2a91 · outbound

This paper cites Prompt Injection: Parameterization of Fixed Inputs.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Prompt Injection: Parameterization of Fixed Inputs

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:23.173995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:23.173995Z digest=sha256:d2e4a1cf628767d6bd6b37b2e56ee2544b31b7a343d517ac68b096a801fd0b93

Observation 10c05fd2-fe2a-4dd3-8cfd-e88e82ad1114 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:23.320798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:23.320798Z digest=sha256:6cba27eafd0f4b80cb2eba594d917552bc08c2b63cb483293d89d3f19314b1d7

Observation 911ca4a3-cb89-4580-8867-8957ae3a86e4 · outbound

This paper cites Journal of Machine Learning Research , volume=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Journal of Machine Learning Research , volume=

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:23.425661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:23.425661Z digest=sha256:f8f83179146e2a21dfaf254ca4c3ed45621c5686c7514ff79f941f75b1916f91

Observation a409c0e3-a4a8-4260-a53c-247d46e2b6d6 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems KTO: Model Alignment as Prospect Theoretic Optimization

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:23.545576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:23.545576Z digest=sha256:7705ad527ef1e65b587e273f1f48a553cd9087622dd560753d6e2c6ae7ae99ee

Observation 904a9d38-fd58-432c-aada-f7ca9e3acde9 · outbound

This paper cites Journal of Machine Learning Research , volume=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Journal of Machine Learning Research , volume=

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:23.706994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:23.706994Z digest=sha256:51e2f1da74429b8794bb830c22b2ab4acebfc3a0c3966846c9eef9e069b1ba68

Observation 0222516c-af7a-4b0d-8bd5-774e6e92a09e · outbound

This paper cites International Conference on Machine Learning , pages=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems International Conference on Machine Learning , pages=

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:23.858087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:23.858087Z digest=sha256:414d1dea6639ec3508d63713827eedd933e1f1ce98c4a007bd28c83082000b8a

Observation a594a842-8016-43a9-a288-bb1bf5a011bd · outbound

This paper cites Nature Machine Intelligence , volume=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Nature Machine Intelligence , volume=

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:23.980166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:23.980166Z digest=sha256:cb1db98d5ac45ac7e9177a55e14b975cc67d9cd3bafa8f205100f9945fe54453

Observation 9b297eff-bf99-4677-8c34-a66200cda96b · outbound

This paper cites The Journal of Machine Learning Research , volume=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems The Journal of Machine Learning Research , volume=

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.059841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.059841Z digest=sha256:9d9413d510fab9600a23637640495e15aec810d717c05841d8182d117b88bee8

Observation 4e5556ad-8d33-46f2-b540-34263f81cfba · outbound

This paper cites Proceedings of the 28th International Conference on Computational Linguistics , pages=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Proceedings of the 28th International Conference on Computational Linguistics , pages=

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.108504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.108504Z digest=sha256:89f9c90e0e8591902eb972ddb688b1653268ad4d68f0f81a3f1d4391b6fe7e67

Observation 4c8807ad-43d8-4034-8985-1d5f8b019be7 · outbound

This paper cites Risks from Learned Optimization in Advanced Machine Learning Systems.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Risks from Learned Optimization in Advanced Machine Learning Systems

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.184564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.184564Z digest=sha256:9a056f1ff56ad34537de5a6e700866f195558a29e038ac2d33089f899b7476fe

Observation f4be7f70-6d09-4e66-ad9d-44ab01d75a47 · outbound

This paper cites Nonlinear Independent Component Analysis: Existence and Uniqueness Results , journal =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Nonlinear Independent Component Analysis: Existence and Uniqueness Results , journal =

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.268235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.268235Z digest=sha256:3efd5945313edfe55c67c2b6197af2444879867bf7c83242d19e44dc63dd85ef

Observation aca62e53-c6fd-4182-9a7a-f2e5f0b28e1a · outbound

This paper cites Nonlinear.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Nonlinear

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.332554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.332554Z digest=sha256:9b1534b48dc71260402f1ec7d823b1bee09c6edaa73f540c601af6eb8fbb4583

Observation 78119a05-fa8a-449e-9337-8d20679eb715 · outbound

This paper cites , title =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems , title =

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.477289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.477289Z digest=sha256:20383fa121ad987d2f85315927dff2be9bee4197bb6f6b7a94311a23cc7178ba

Observation 4612e4af-06f6-48ec-952e-015a9f131066 · outbound

This paper cites , title =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems , title =

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.600070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.600070Z digest=sha256:0862ad8e8d358205bdc7d720970b54b5f5e0e807357317bb568265d44cb10a13

Observation 593cd069-4a7f-430b-a25b-22cf31752395 · outbound

This paper cites and Moazam, Hanna and Miller, Heather and Zaharia, Matei and Potts, Christopher , title =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems and Moazam, Hanna and Miller, Heather and Zaharia, Matei and Potts, Christopher , title =

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.733973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.733973Z digest=sha256:ddf117808ab6a8fd9bfff2f71c73d708faecc22b743b01db6e2bc12b002a0d84

Observation a674c9ba-f3b3-4a03-9a9b-395d5a0f3f47 · outbound

This paper cites NeurIPS , year =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems NeurIPS , year =

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.815423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.815423Z digest=sha256:82cf4de3d1224191ff8c9627eb904f7e0f4e7f0b216c9deeff57a7332a1ae934

Observation 0ab31f39-1536-4567-863b-3fefddcc2204 · outbound

This paper cites ICML , year =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems ICML , year =

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.884724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.884724Z digest=sha256:b18b6077f1099103e27bbf4bd36bf4cf1dbfd51cf2a0b9dbae67f59d635fa048

Observation d6cfae8c-246b-4bdc-82d3-354fa5af7b0f · outbound

This paper cites Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations , booktitle =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations , booktitle =

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:24.970705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:24.970705Z digest=sha256:0db60b46743fd936e9bd74af364749444fa337a8f1337b38205214811f2c718f

Observation 0bfb7c7c-f028-4403-9515-f975e336a033 · outbound

This paper cites Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:25.026511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:25.026511Z digest=sha256:bc13481ce75b37307e7c77c7e95d42d5840d50e7787cd7c0ba87f473d7d6d5d1

Observation 8a29c3a4-88a1-4e16-b87e-4066fd0934a2 · outbound

This paper cites Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics , pages=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics , pages=

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:25.102639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:25.102639Z digest=sha256:5e3a0f5386b9a23a2551d2767d0eb85e9357b4409c56d4cb1d666db5330fc806

Observation eacdceca-3276-4826-b01a-dab9bf7f497f · outbound

This paper cites NeurIPS , year =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems NeurIPS , year =

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:25.250017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:25.250017Z digest=sha256:4e3408044b6dabaf7f3b5ff6ca57d9727cc1674d1ea5ddf0fc7422ba5f52f724

Observation 12e5e5a3-5937-4187-9bc2-3f3eb0478216 · outbound

This paper cites an unresolved cited work.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Unresolved cited work

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:25.394568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:25.394568Z digest=sha256:cab13e22e0861b478e0f8b9fdb04f55f63a3fd1fd485f399b33927cb95104469

Observation 5a8544b8-5db9-402d-b5b4-2fc6c94a8814 · outbound

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

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Training language models to follow instructions with human feedback

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:25.534023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:25.534023Z digest=sha256:5987d1e1a033152f116b4573bb3a3956553dade00a01d15e0155b9b1090cf738

Observation 32f7e0b6-64ed-438b-af0e-fe9c6e80c8c2 · outbound

This paper cites Feedback Loops With Language Models Drive In-Context Reward Hacking.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Feedback Loops With Language Models Drive In-Context Reward Hacking

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:25.689409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:25.689409Z digest=sha256:63af047af45e98531ec42264c072cf0258a50437936f1ec22f6fda557f5b6890

Observation 3bbeb144-4d09-461e-a7c4-b89235127996 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:25.772652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:25.772652Z digest=sha256:9351e77ea94f9ea2650b1bfb00730c3ba529302867885c93ed1e4c347c20b1af

Observation f00da79c-740f-4932-bd56-a299bec5b7c1 · outbound

This paper cites RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:25.888729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:25.888729Z digest=sha256:48958db273cf94d6db2ab41e0b79e2a83ce2b7f053b58c478bc341f595afbedc

Observation 8031bdb6-b3b2-4331-95d1-6439e3066742 · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Towards Understanding Sycophancy in Language Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:26.028655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:26.028655Z digest=sha256:4d72f065c4c1e2fda9281fb52cc80e11c24d24afa8fa85f5391cb68331420123

Observation 87cb05f9-ca86-4033-959d-4ae5c9f4289b · outbound

This paper cites arXiv preprint arXiv:2411.15927 , year =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems arXiv preprint arXiv:2411.15927 , year =

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:26.172865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:26.172865Z digest=sha256:e2f1a5ee0213ce0084d01fb1c3b0570166bc0d576d5bb150dd9fd1be58d8f72a

Observation 2a959382-0dc7-4205-ac63-77d9dd5d70f9 · outbound

This paper cites an unresolved cited work.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Unresolved cited work

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:26.257623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:26.257623Z digest=sha256:0c804fd1a737cced6d2bf49f5ba9f3318588be3686cab3afd3ac81c833f165eb

Observation b9d82d3a-535f-425f-8fd3-486c7f062d7e · outbound

This paper cites Learning by Distilling Context.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Learning by Distilling Context

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:26.367813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:26.367813Z digest=sha256:29ba52704c82e6a115517ed819cca57262eca239661e5b266bbb94d646d3cf3b

Observation bd525008-1d5c-4ba2-931d-22f5a0cbd43f · outbound

This paper cites Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics , pages=

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:26.514088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:26.514088Z digest=sha256:f21962c774e3e752d07183a505b465913a116296e5ed4571fa322d0b7d90c908

Observation 2bedaa98-a1fc-4bc3-92db-8fc604598a57 · outbound

This paper cites ICML , year =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems ICML , year =

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:26.650527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:26.650527Z digest=sha256:033306b7b1a74a2d880270e8a822c3819a63fa639ad59e5570517d30c9195b7a

Observation bea640d5-68c8-43f4-bd9e-503bfaa6670a · outbound

This paper cites International Conference on Learning Representations (ICLR) , year =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems International Conference on Learning Representations (ICLR) , year =

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:26.791779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:26.791779Z digest=sha256:ba6b496e8402d040798c9e4397e5358339816d76563beb4a4748d4a53eeb14ae

Observation 384c9067-8543-4dd2-8cad-6f4b1f6e5dac · outbound

This paper cites arXiv preprint arXiv:2502.17721 , year =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems arXiv preprint arXiv:2502.17721 , year =

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:26.920374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:26.920374Z digest=sha256:421775590ac1139c52b246c3dcfa76db25f3b0561d56f6fa620fe8124ee75628

Observation 20ebdedf-b59d-4c78-970e-c026bf313490 · outbound

This paper cites International Conference on Learning Representations (ICLR) , year =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems International Conference on Learning Representations (ICLR) , year =

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.079584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.079584Z digest=sha256:f473eeff9caee8cd2bc273082948abf50622655d52a6fa4d97fd171a69e49d8c

Observation bbb1954d-fc24-4b2a-a502-6eb5f3b016a7 · outbound

This paper cites Advances in neural information processing systems , volume=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Advances in neural information processing systems , volume=

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.190780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.190780Z digest=sha256:a5c1785c8e92905f9b81073cf2dc8c424d8e5792b96bfdd78f3f6fafe77560c3

Observation 89754e6e-158b-4e0e-a21d-faff0ccec044 · outbound

This paper cites TextGrad: Automatic "Differentiation" via Text.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems TextGrad: Automatic "Differentiation" via Text

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.300236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.300236Z digest=sha256:ed5ca0e1572659c3f703425bd5e0abcc6610abd0300c274881e7b9375632f0f4

Observation 23b78b21-3a48-4b19-a38c-c231fe388614 · outbound

This paper cites AFlow: Automating Agentic Workflow Generation.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems AFlow: Automating Agentic Workflow Generation

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.345384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.345384Z digest=sha256:952e122041b8f07d50891eeba77a4f406a87391c123ee4a7950efde370122dd3

Observation c1d2f4ec-36d1-4b2f-abb5-dfc97d7343b6 · outbound

This paper cites Journal of Machine Learning Research , volume =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Journal of Machine Learning Research , volume =

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.416413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.416413Z digest=sha256:155ba72ffa83e29abb65be2e584eb4fe18015976672f91816a92da5a46cd322d

Observation 38405a09-982f-499a-b770-87a365165e47 · outbound

This paper cites and Schirm, Allen L.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems and Schirm, Allen L

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.459251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.459251Z digest=sha256:6fed43ba1185851389c3c23b008c3f94372927cd5392104415a870f0529fc664

Observation c8ac5096-5a3f-43f7-84df-a090b68dfe59 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Fine-Tuning Language Models from Human Preferences

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.567937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.567937Z digest=sha256:75cf1cdc3bcf4762bb333b2dd0580a54d4459050579cedd386c1a26b059a3c5a

Observation fd9fea95-776f-45cc-8cf1-9d65d1d0f965 · outbound

This paper cites ST-MoE: Designing Stable and Transferable Sparse Expert Models.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems ST-MoE: Designing Stable and Transferable Sparse Expert Models

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.639120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.639120Z digest=sha256:cead0e7fc3a6db18a54cde97c7e924583c65e3658bfadcfa9ee56734759f9f4c

Observation 30face9b-bb12-45b0-936a-97e119cf0cd9 · outbound

This paper cites and Salakhutdinov, Ruslan and Manning, Christopher D.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems and Salakhutdinov, Ruslan and Manning, Christopher D

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.777334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.777334Z digest=sha256:eda7634b367fcd8cb9fc3af38e3bb4f060366295660572af5d38ecb84c8294d0

Observation 32b9db52-0670-406b-a0d4-f547024a27c6 · outbound

This paper cites NAACL , year =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems NAACL , year =

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:27.897965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:27.897965Z digest=sha256:9fe6371a6b6988854828dcb63c16642b7ed2363fb2695235ad748ade6355b69b

Observation 940bbb06-1961-4118-8f3d-cea10c9b5c1b · outbound

This paper cites Program Synthesis with Large Language Models.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Program Synthesis with Large Language Models

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:28.020593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:28.020593Z digest=sha256:15fa0b06954db571d9acd305eb2fbda6f522d2dad148755f7bbecffa3cf6b4d2

Observation 3c17ac66-529a-446f-9b63-b65ecb06dc92 · outbound

This paper cites Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:28.145819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:28.145819Z digest=sha256:8e4679a3e6a4951aa290bfaff641f6bfd36247dbd71dcda8667d94e201bb73a5

Observation 0cf3cfe5-4796-4e14-bebc-861a0635a0a9 · outbound

This paper cites Qwen2.5 Technical Report.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Qwen2.5 Technical Report

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:28.266183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:28.266183Z digest=sha256:3ea6b7344cd7ca170d6bfa2efbb823a934eecc67c5dc7f1c4484c3cb530f3e31

Observation 0140b66d-0c8a-41fb-b5b8-4e2c260bc753 · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Transactions of the Association for Computational Linguistics , volume=

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:28.385719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:28.385719Z digest=sha256:bbcfbe27da4e0e6e2cb17a21dd69af0c8236fb3fe8d0977fa725bf81a82df057

Observation 617e1fd3-0a08-4843-93e3-22685e19fbce · outbound

This paper cites an unresolved cited work.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Unresolved cited work

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:28.549905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:28.549905Z digest=sha256:b9f7cdac427415e0d9a199f3f9cb7e25da41086111f88ab2e36692e31471e8a8

Observation 02568a6c-da16-4fe6-aecb-f0f34086cf14 · outbound

This paper cites Advances in Neural Information Processing Systems , year=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Advances in Neural Information Processing Systems , year=

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:28.663771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:28.663771Z digest=sha256:623a948dd7ead5dc33f9253d1b7237067e6377459c9842f754c171b2ebd4415e

Observation 9c02041d-5ef1-45a7-98fa-5553e3305263 · outbound

This paper cites Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:28.807091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:28.807091Z digest=sha256:8ddbab09b16cbfa43854506a469d0836557bffd6cff8ae23639c21a17dd4f8ea

Observation f4db7cc4-ec52-498c-b06a-b160554aaa82 · outbound

This paper cites Linearly-solvable.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Linearly-solvable

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:28.941011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:28.941011Z digest=sha256:bca5a1d32bae74938f32617e110a7765dae8f73509e240509503680694ae7975

Observation 3d803a2f-aab2-4fdb-8216-3d054cd4c4dd · outbound

This paper cites AAAI Conference on Artificial Intelligence , year=.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems AAAI Conference on Artificial Intelligence , year=

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:29.075633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:29.075633Z digest=sha256:13129fadeb3c43c757e726a3b95b446435cc4a703bd484c35d2ccd8461736136

Observation 72dfc77d-d891-4871-a79e-f947d79a5d57 · outbound

This paper cites and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , title =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Wang, Lu and Chen, Weizhu , title =

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:29.186889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:29.186889Z digest=sha256:a6754b52f8533fc80145141c2a567555da4c76fb0cb6ea682063b600111d05e8

Observation 8337b682-79c0-4818-a222-159df8597bd5 · outbound

This paper cites Let's Verify Step by Step.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Let's Verify Step by Step

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:29.251917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:29.251917Z digest=sha256:717eb3996faf40c0b1b005d7c52003dafc0a88ef5021b8294381cf85eeaef29c

Observation 4edc27e3-7411-42a8-b500-9f3a86dd2465 · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems Solving math word problems with process- and outcome-based feedback

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:29.334723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:29.334723Z digest=sha256:af2ebb573271727d39bdc62f093d8f470df747a320127e1a32fb6b92c8c17e3f

Observation aa76418b-5651-495a-a028-6838e366c30a · outbound

This paper cites , title =.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems , title =

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-02T08:17:29.480487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T08:17:29.480487Z digest=sha256:2f920077179050287bebefcaaa8ba5919b7a01b8cb65a9016ba7ca70c46d135c

Pith citing papers

No inbound Pith citation observations are available.