Paper Citation Record · LEDGER

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights

As of 10 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2607.27482.

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

pith.paper-citation-record.v1
2607.27482 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T07:13:47.838796Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

22 of 22 outbound references displayed

verified exact5
verified fuzzy0
unresolved15
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 787d26cd-4d64-4449-89c8-590173aea06a · outbound

This paper cites Git Re-Basin: Merging Models modulo Permutation Symmetries.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Git Re-Basin: Merging Models modulo Permutation Symmetries

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:44.930147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e51c07c-41bd-4ea2-87b4-b740c2534296 · outbound

This paper cites For 2-way classification, micro F1 fell by 3.3 percentage points (0.886 to 0.853) and macro F1 by 6.1 points (0.881 to 0.820).

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights For 2-way classification, micro F1 fell by 3.3 percentage points (0.886 to 0.853) and macro F1 by 6.1 points (0.881 to 0.820)

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:47.681218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42aa7c1f-f358-4ac3-bf2a-af0c23c7fba9 · outbound

This paper cites B.1 Permutation Alignment This expands the alignment procedure of Section 3.4.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights B.1 Permutation Alignment This expands the alignment procedure of Section 3.4

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:47.838796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a0bc828-b5cc-48b5-be0a-5c0d12efec4d · outbound

This paper cites doi: 10.18653/v1/ P18-2110.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights doi: 10.18653/v1/ P18-2110

Reference 10

Resolution: malformed identifier; no resolver link, observed 2026-08-01T07:13:46.237699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c747d0ae-3356-44be-8ec5-315df87265d3 · outbound

This paper cites Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:46.476800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fec6515-8ec6-4eab-9999-11da8a28c31c · outbound

This paper cites doi: 10.18653/v1/W18-6210.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights doi: 10.18653/v1/W18-6210

Reference 14

Resolution: verified exact; doi, observed 2026-08-01T07:18:34.238132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bd342e28-646f-4bbb-a53c-ec01c4002c5f · outbound

This paper cites ISBN 979-10-95546-34-4.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights ISBN 979-10-95546-34-4

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:46.808770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c985f8da-6a6f-40bb-a0fa-d86957df6442 · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:47.093238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 713f4da9-e7d2-4762-b350-fd88df92902e · outbound

This paper cites doi: 10.18653/v1/2023.genbench-1.6.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights doi: 10.18653/v1/2023.genbench-1.6

Reference 19

Resolution: verified exact; doi, observed 2026-08-01T07:18:34.001926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a536cd7a-2011-4158-98e0-3a8690528c1b · outbound

This paper cites Exact Phase Transitions in Deep Learning.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Exact Phase Transitions in Deep Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:47.445005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 686780d6-6fd5-4689-acd3-6734cba2bd35 · outbound

This paper cites Mario Geiger, Stefano Spigler, Stéphane d’Ascoli, Levent Sagun, Marco Baity-Jesi, Giulio Biroli, and Matthieu Wyart.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Mario Geiger, Stefano Spigler, Stéphane d’Ascoli, Levent Sagun, Marco Baity-Jesi, Giulio Biroli, and Matthieu Wyart

Reference 1983

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:45.592868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe4be13-23c4-4c98-9759-a06a89fe458b · outbound

This paper cites The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:45.189799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52de09d7-2622-496a-9514-1eab8ed687f2 · outbound

This paper cites Komal Florio, Valerio Basile, Marco Polignano, Pierpaolo Basile, and Viviana Patti.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Komal Florio, Valerio Basile, Marco Polignano, Pierpaolo Basile, and Viviana Patti

Reference 2014

Resolution: verified exact; doi, observed 2026-08-01T07:18:35.241945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 329a0a04-96e0-474b-967e-cfb95e7dd1f7 · outbound

This paper cites Latent State Models of Training Dynamics.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Latent State Models of Training Dynamics

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:45.857689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93ae5803-7324-4858-bba9-7667126528c9 · outbound

This paper cites an unresolved cited work.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Unresolved cited work

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:45.079318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73880daa-1ad3-4dc2-97dc-1b9269de7553 · outbound

This paper cites The jamming transition as a paradigm to understand the loss landscape of deep neural networks.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights The jamming transition as a paradigm to understand the loss landscape of deep neural networks

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:45.720002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7d6aa90-cbaf-49d7-a4a4-bd12a8ca9258 · outbound

This paper cites doi: 10.18653/v1/D19-1018.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights doi: 10.18653/v1/D19-1018

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:46.927225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c5578cb-e798-4139-8100-1e6ef34df98a · outbound

This paper cites URLhttps://doi.org/10.3390/app10124180.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights URLhttps://doi.org/10.3390/app10124180

Reference 2020

Resolution: verified exact; doi, observed 2026-08-01T07:18:34.928390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a1e681da-f8dc-4497-8bcc-139ec190f841 · outbound

This paper cites doi: 10.18653/v1/2021.findings-emnlp.206.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights doi: 10.18653/v1/2021.findings-emnlp.206

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:47.024703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 873dcb82-c4b5-4ac5-9d91-cb2ffa41b94a · outbound

This paper cites Exact Phase Transitions in Deep Learning.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Exact Phase Transitions in Deep Learning

Reference 2022

Resolution: verified exact; local_arxiv, observed 2026-08-01T07:18:33.780245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1d5df555-8adc-40e5-bcdd-460e2eed66d5 · outbound

This paper cites Latent State Models of Training Dynamics.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights Latent State Models of Training Dynamics

Reference 2023

Resolution: metadata mismatch; local_arxiv, observed 2026-08-01T07:18:34.558183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 68c243ec-9ed8-4905-bd9e-6a459aa9171f · outbound

This paper cites doi: 10.1007/s40547-024-00143-4.

Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights doi: 10.1007/s40547-024-00143-4

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T07:13:46.587730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.