Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-02T09:39:41.790057Z
Paper Citation Record · LEDGER
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs
As of 10 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 0 inbound Pith citation observations for arXiv:2606.31413.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
10 of 10 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved10
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation d5087d3f-7591-4879-9769-ffe524f4e762 · outbound
This paper cites an unresolved cited work.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs Unresolved cited work
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:41.559189Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0bea2c4c-c461-46fb-9587-78a9a61e1c8e · outbound
This paper cites We an- neal the temperature from τ= 1.5 to τ= 0.1 exponentially and keep the final temperature fixed for the last10%of training.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs We an- neal the temperature from τ= 1.5 to τ= 0.1 exponentially and keep the final temperature fixed for the last10%of training
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:41.710284Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f26d29e-83f5-4dc4-8883-3f8b27412b25 · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:40.820382Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b614ac22-c480-4174-b105-baad36f7b618 · outbound
This paper cites Mixture of LoRA Experts.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs Mixture of LoRA Experts
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:41.330490Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b3628f72-b64c-4699-b113-f208378bbc66 · outbound
This paper cites SiRA: Sparse Mixture of Low Rank Adaptation.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs SiRA: Sparse Mixture of Low Rank Adaptation
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:41.447055Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5cabdc61-f6e3-48f0-913d-d0babd099da8 · outbound
This paper cites This variant tests whether unit-scale routing is sufficient only at inference time, or whether the same behavior is also necessary during training.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs This variant tests whether unit-scale routing is sufficient only at inference time, or whether the same behavior is also necessary during training
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:41.790057Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c253108c-8124-472b-af36-e71244c31e8d · outbound
This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
Reference 2013
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:40.490339Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ce94de4-e7be-408b-a46f-2568ebb4a7f0 · outbound
This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Reference 2021
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:41.154618Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cb0fcaed-2f1e-4773-8cca-52035dc41c69 · outbound
This paper cites Towards Modular LLMs by Building and Reusing a Library of LoRAs.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs Towards Modular LLMs by Building and Reusing a Library of LoRAs
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:41.028505Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a615d3fe-cb9f-4163-869c-d34c0ee9dd9e · outbound
This paper cites Gemma 3 Technical Report.
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs Gemma 3 Technical Report
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:39:40.676178Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.