Paper Citation Record · LEDGER

SIA: Self Improving AI with Harness & Weight Updates

As of 19 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 3 inbound Pith citation observations for arXiv:2605.27276.

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

pith.paper-citation-record.v1
2605.27276 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T16:43:58.090334Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:22:26.644350Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-11T23:44:27.064764Z

Reference resolution

25 of 25 outbound references displayed

verified exact1
verified fuzzy0
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e3163f3e-0b63-4507-857d-dd895b69010b · outbound

This paper cites The surprising effectiveness of test-time training for few-shot learning.International Conference on Machine Learning, 2024.

SIA: Self Improving AI with Harness & Weight Updates The surprising effectiveness of test-time training for few-shot learning.International Conference on Machine Learning, 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6035b8a-52b9-49ca-a4a6-5357cb371208 · outbound

This paper cites Wolock, Abigail L.

SIA: Self Improving AI with Harness & Weight Updates Wolock, Abigail L

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4c0574-bc2c-42fb-8c7b-e88ead4f3b6b · outbound

This paper cites SkyRL-v0: Train real-world long-horizon agents via reinforcement learning.

SIA: Self Improving AI with Harness & Weight Updates SkyRL-v0: Train real-world long-horizon agents via reinforcement learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33cfb689-5562-4aa5-a614-d55345a73aaf · outbound

This paper cites Self-play fine-tuning converts weak language models to strong language models.

SIA: Self Improving AI with Harness & Weight Updates Self-play fine-tuning converts weak language models to strong language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c662ebe-fc4e-43ee-bece-f82e73207802 · outbound

This paper cites an unresolved cited work.

SIA: Self Improving AI with Harness & Weight Updates Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df38d11a-d87e-4050-96a8-f175aadc68f8 · outbound

This paper cites Zhu, Fengzhe Zhou, Zhuo Han, Songyang Zhang, Kai Chen, Zongwen Shen, and Jidong Ge.

SIA: Self Improving AI with Harness & Weight Updates Zhu, Fengzhe Zhou, Zhuo Han, Songyang Zhang, Kai Chen, Zongwen Shen, and Jidong Ge

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dce9f1b9-10a8-4e6a-af8d-d7453ad0bb8f · outbound

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

SIA: Self Improving AI with Harness & Weight Updates Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbc47684-c89b-4aed-9a36-67b86cb9b77b · outbound

This paper cites Automated design of agentic systems.International Conference on Learning Representations, 2024.

SIA: Self Improving AI with Harness & Weight Updates Automated design of agentic systems.International Conference on Learning Representations, 2024

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d18ee350-5c84-4e41-80f9-fdd309127c95 · outbound

This paper cites autoresearch: AI agents running research on single-GPU nanochat training automat- ically, 2026.

SIA: Self Improving AI with Harness & Weight Updates autoresearch: AI agents running research on single-GPU nanochat training automat- ically, 2026

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa68c658-10ed-485f-9be5-f1fb9534b782 · outbound

This paper cites Meta- harness: End-to-end optimization of model harnesses.International Conference on Machine Learning, 2026.

SIA: Self Improving AI with Harness & Weight Updates Meta- harness: End-to-end optimization of model harnesses.International Conference on Machine Learning, 2026

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c11ab33-5bdb-4868-8a48-9c5a0ca60d23 · outbound

This paper cites The AI scientist: Towards fully automated open-ended scientific discovery.arXiv.org, 2024.

SIA: Self Improving AI with Harness & Weight Updates The AI scientist: Towards fully automated open-ended scientific discovery.arXiv.org, 2024

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05a58452-1e6b-4df2-a673-ec147b067c9e · outbound

This paper cites Eureka: Human-level reward design via coding large language models.

SIA: Self Improving AI with Harness & Weight Updates Eureka: Human-level reward design via coding large language models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72e18a97-6b75-4876-8dc5-81cd2aa012df · outbound

This paper cites Self-refine: Iterative refinement with self- feedback.

SIA: Self Improving AI with Harness & Weight Updates Self-refine: Iterative refinement with self- feedback

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 604d5c56-fb3e-4794-9aac-7f85e60789a9 · outbound

This paper cites Shirobokov, B.

SIA: Self Improving AI with Harness & Weight Updates Shirobokov, B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 711cf113-fe8f-4289-9442-990a48ec10ad · outbound

This paper cites Romera-Paredes, M.

SIA: Self Improving AI with Harness & Weight Updates Romera-Paredes, M

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f67abfde-d96f-4ec2-a0e8-146d821a4788 · outbound

This paper cites HybridFlow: A flexible and efficient RLHF framework.

SIA: Self Improving AI with Harness & Weight Updates HybridFlow: A flexible and efficient RLHF framework

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f8a8d3a-fcfe-4398-a631-ebaf39248019 · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.

SIA: Self Improving AI with Harness & Weight Updates Reflexion: Language agents with verbal reinforcement learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 400f3933-d776-414c-bd6e-d34f77ecb09e · outbound

This paper cites Voyager: An open-ended embodied agent with large language models.Trans.

SIA: Self Improving AI with Harness & Weight Updates Voyager: An open-ended embodied agent with large language models.Trans

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9334939c-e672-434f-ac71-64042a95744e · outbound

This paper cites ReAct: Synergizing reasoning and acting in language models.

SIA: Self Improving AI with Harness & Weight Updates ReAct: Synergizing reasoning and acting in language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21d14137-f3f1-475f-bd0f-072a8d1e2510 · outbound

This paper cites Learning to discover at test time.arXiv.org, 2026.

SIA: Self Improving AI with Harness & Weight Updates Learning to discover at test time.arXiv.org, 2026

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45b8ac63-6fbe-4766-92ac-9e3a5fd3d444 · outbound

This paper cites an unresolved cited work.

SIA: Self Improving AI with Harness & Weight Updates Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510899ce-1a01-4ceb-a9c6-24a43eef8362 · outbound

This paper cites Darwin G¨ odel machine: Open- ended evolution of self-improving agents.SuperIntelligence - Robotics - Safety & Alignment, 2(3), 2025.

SIA: Self Improving AI with Harness & Weight Updates Darwin G¨ odel machine: Open- ended evolution of self-improving agents.SuperIntelligence - Robotics - Safety & Alignment, 2(3), 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 159a0358-f5af-415c-ba0d-ca46e4ac4e62 · outbound

This paper cites Hyperagents.

SIA: Self Improving AI with Harness & Weight Updates Hyperagents

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-06-29T16:53:41.447464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 57c983db-bee9-4760-8504-659fa2ad4e74 · outbound

This paper cites LlamaFac- tory: Unified efficient fine-tuning of 100+ language models.

SIA: Self Improving AI with Harness & Weight Updates LlamaFac- tory: Unified efficient fine-tuning of 100+ language models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9de642cf-ce32-4a5b-9647-22b426efbc57 · outbound

This paper cites TTRL: Test-time reinforcement learning.arXiv.org, 2025.

SIA: Self Improving AI with Harness & Weight Updates TTRL: Test-time reinforcement learning.arXiv.org, 2025

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-29T16:43:58.090334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4a23760a-9c94-49bc-9594-21f1c610ed85 · inbound

A Vocabulary for Multi-Agent Automated Research Systems cites this paper.

A Vocabulary for Multi-Agent Automated Research Systems SIA: Self Improving AI with Harness & Weight Updates

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T07:06:10.695871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c60cec7-4ac4-47af-ba70-31d49c856748 · inbound

Evo-Bench: Can Language Models Improve Agent Harness? cites this paper.

Evo-Bench: Can Language Models Improve Agent Harness? SIA: Self Improving AI with Harness & Weight Updates

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-11T23:44:27.097812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 192edf02-eef4-49db-98f1-2d6ce7af8406 · inbound

Evo-Bench: Can Language Models Improve Agent Harness? cites this paper.

Evo-Bench: Can Language Models Improve Agent Harness? SIA: Self Improving AI with Harness & Weight Updates

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T04:22:26.644350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.