Paper Citation Record · LEDGER

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning

As of 8 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2607.22769.

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

pith.paper-citation-record.v1
2607.22769 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T06:19:33.724551Z

measured 12 of 12 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

12 of 12 outbound references displayed

verified exact0
verified fuzzy0
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3652de58-bbaa-4d06-8d5d-c3d3c0f48d4c · outbound

This paper cites Nemotron-climb: Clustering-based iterative data mixture optimization.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Nemotron-climb: Clustering-based iterative data mixture optimization

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:32.099580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac5b3502-6737-4d99-b71a-6e35bc680979 · outbound

This paper cites Training Compute-Optimal Large Language Models.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Training Compute-Optimal Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:32.223883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70f937f4-19c3-4b23-9a72-22cd41637be1 · outbound

This paper cites Scaling Laws for Neural Language Models.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Scaling Laws for Neural Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:32.464859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eef586f3-1521-4934-b262-7cb4f560ebc5 · outbound

This paper cites Rho-1: Not All Tokens Are What You Need.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Rho-1: Not All Tokens Are What You Need

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:32.644746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7098e97-af5e-4fc8-a46f-93f300adc2d8 · outbound

This paper cites Scalebio: Scalable bilevel optimization for llm data reweighting.Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Scalebio: Scalable bilevel optimization for llm data reweighting.Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:32.754745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c45f3513-2912-4ade-820f-f20ce1a27d97 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:32.909831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 875e4b27-41d0-41de-a15c-9e8403d60a23 · outbound

This paper cites Qurating: Select- ing high-quality data for training language models.International Conference on Machine Learning, 2024.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Qurating: Select- ing high-quality data for training language models.International Conference on Machine Learning, 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:33.024740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c8288b-7575-47fa-8bed-2d1642d7603f · outbound

This paper cites LESS: Selecting Influential Data for Targeted Instruction Tuning.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning LESS: Selecting Influential Data for Targeted Instruction Tuning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:33.174874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24290403-1671-403d-af9b-c749768a8733 · outbound

This paper cites Data selection for language models via importance resampled mcmc.Advances in Neural Information Processing Systems, 36, 2023.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Data selection for language models via importance resampled mcmc.Advances in Neural Information Processing Systems, 36, 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:33.305650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5915e398-61dc-40ce-88ee-7d05e39ceffd · outbound

This paper cites Doremi: Optimizing data mixtures speeds up language model pretraining.Advances in Neural Information Processing Systems, 36, 2023.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Doremi: Optimizing data mixtures speeds up language model pretraining.Advances in Neural Information Processing Systems, 36, 2023

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:33.392135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cffd2bca-5698-486b-95d8-a2832d153890 · outbound

This paper cites Dataflex: A unified framework for data-centric dynamic training of large language models.arXiv preprint arXiv:2603.26164, 2026.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning Dataflex: A unified framework for data-centric dynamic training of large language models.arXiv preprint arXiv:2603.26164, 2026

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:33.624844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3478ff6d-deba-4dae-bcd6-0b7517a56165 · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T06:19:33.724551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.