Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T15:34:04.596012Z
Paper Citation Record · LEDGER
When to retrain a machine learning model
As of 12 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 2 inbound Pith citation observations for arXiv:2505.14903.
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 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-05-10T18:13:46.622289Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-11T21:51:33.232440Z
Reference resolution
18 of 18 outbound references displayed
- verified exact0
- verified fuzzy9
- unresolved7
- parse uncertain0
- malformed identifier2
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 8e208ac3-8bb9-4aca-8054-350297c53de3 · outbound
This paper cites staleness cost.
When to retrain a machine learning model staleness cost
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:34:08.168951Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0f1f25ea-5833-411f-b2e5-c36487550cf4 · outbound
This paper cites Scaling Laws for Neural Language Models.
When to retrain a machine learning model Scaling Laws for Neural Language Models
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:34:02.839770Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5646da45-9b53-4c6d-b04b-f6d8df04189e · outbound
This paper cites These approaches may work well when retraining costs are low, but they become unsuitable when retraining is expensive – it is not always optimal to retrain after every minor shift.
When to retrain a machine learning model These approaches may work well when retraining costs are low, but they become unsuitable when retraining is expensive – it is not always optimal to retrain after every minor shift
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:34:07.896436Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8f740a10-d22b-4b56-8612-c245b33ac4f5 · outbound
This paper cites an unresolved cited work.
When to retrain a machine learning model Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:34:07.417136Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation df9538f7-0a69-44b5-9697-e6b3db1df167 · outbound
This paper cites Some methods integrates epistemic uncertainty on Q-function to account for the distribution shift of unseen actions (Kumar et al., 2020; O’Donoghue et al., 2017; Luis et al., 2023).
When to retrain a machine learning model Some methods integrates epistemic uncertainty on Q-function to account for the distribution shift of unseen actions (Kumar et al., 2020; O’Donoghue et al., 2017; Luis et al., 2023)
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:34:07.116775Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 4b298177-fd8c-472e-8750-315af0c16959 · outbound
This paper cites w denotes the number of timestep of the offline phase, T denotes the number of timestep of the online phase.
When to retrain a machine learning model w denotes the number of timestep of the offline phase, T denotes the number of timestep of the online phase
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:34:06.320820Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c34e8474-b199-45e6-9f58-6ba5e7ecb857 · outbound
This paper cites We follow Mahadevan & Mathioudakis (2024) and use the Sklearn Multiflow library version (Montiel et al.,.
When to retrain a machine learning model We follow Mahadevan & Mathioudakis (2024) and use the Sklearn Multiflow library version (Montiel et al.,
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:34:06.046814Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 04fa6668-3400-4374-a92f-ef7302658b0e · outbound
This paper cites relative staleness cost.
When to retrain a machine learning model relative staleness cost
Reference 17
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-07T15:34:05.233297Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 45353d81-996b-4e90-b0f9-0112f3f4e813 · outbound
This paper cites an unresolved cited work.
When to retrain a machine learning model Unresolved cited work
Reference 19
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:34:05.763615Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation bbbc9c86-2b0a-47d1-a11a-3acdc522ae29 · outbound
This paper cites Therefore, with this specific parameterization, we can establish a connection between Q-learning and our learning method.
When to retrain a machine learning model Therefore, with this specific parameterization, we can establish a connection between Q-learning and our learning method
Reference 78
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:34:05.525077Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 226d6879-d640-40b1-9329-496ee60e7cfd · outbound
This paper cites The iWildCam 2020 Competition Dataset.
When to retrain a machine learning model The iWildCam 2020 Competition Dataset
Reference 2002
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:34:02.484228Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 76fb66a5-61dd-4db2-8352-623276ab0999 · outbound
This paper cites an unresolved cited work.
When to retrain a machine learning model Unresolved cited work
Reference 2008
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:34:06.606888Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 7b5b1656-6b63-4184-a74c-154b8c495e48 · outbound
This paper cites Normalized AUC of the combined performance/retraining cost metric ˆCα(θ), computed over a range of α values, for all datasets.
When to retrain a machine learning model Normalized AUC of the combined performance/retraining cost metric ˆCα(θ), computed over a range of α values, for all datasets
Reference 2012
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-07T15:34:04.904407Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 743d2426-b289-4069-b670-8452098165e3 · outbound
This paper cites The Freeze-Thaw method, introduced by Swersky et al.
When to retrain a machine learning model The Freeze-Thaw method, introduced by Swersky et al
Reference 2016
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:34:07.679726Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation a6c15ede-6d40-44bf-a831-4aca52a190d7 · outbound
This paper cites Predicting with confidence on unseen dis- tributions.
When to retrain a machine learning model Predicting with confidence on unseen dis- tributions
Reference 2017
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:34:08.658961Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e7e10b94-3c55-49ec-9ed1-75a2148969fe · outbound
This paper cites ,(x(i+1)∣D∣, y(i+1)∣D∣)∈R d ×{±1} be drawn i.i.d.
When to retrain a machine learning model ,(x(i+1)∣D∣, y(i+1)∣D∣)∈R d ×{±1} be drawn i.i.d
Reference 2018
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T15:34:06.891274Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 361a6aad-9c9c-49b2-8b32-825ee64c8413 · outbound
This paper cites Active Testing: Sample-Efficient Model Evaluation.
When to retrain a machine learning model Active Testing: Sample-Efficient Model Evaluation
Reference 2020
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T15:34:02.981417Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ea05fe16-c474-4497-8780-1c26bd28ae01 · outbound
This paper cites an unresolved cited work.
When to retrain a machine learning model Unresolved cited work
Reference 2021
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T15:34:08.428670Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Pith citing papers
Observation cf9a5c35-fc64-4fb1-bdea-a306934e3eed · inbound
Efficient Dataset Selection for Continual Adaptation of Generative Recommenders cites this paper.
Efficient Dataset Selection for Continual Adaptation of Generative Recommenders When to retrain a machine learning model
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T05:16:03.810543Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation bae637d4-ff43-4fc5-b9ad-b740c5f6cb9b · inbound
An empirical evaluation of the risks of AI model updates using clinical data: stability, arbitrariness, and fairness cites this paper.
An empirical evaluation of the risks of AI model updates using clinical data: stability, arbitrariness, and fairness When to retrain a machine learning model
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T21:51:33.256962Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.