{"as_of":"2026-08-10T14:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:81ffa347541e8af822ecaf81e756286118be4a3ab8b0938ca7257cc26180de72","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T07:13:47.838796Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.27482/citation-record","integrity":"/paper/2607.27482/integrity","json":"/paper/2607.27482/citation-record.json","paper":"/paper/2607.27482"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.04836","last_updated":"2023-03-01T22:17:16Z","snapshot_observed_at":"2026-08-10T04:12:42.383543Z","submitted_at":"2022-09-11T10:44:27Z","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.04836","snapshot_observed_at":"2026-08-01T07:13:44.930147Z","title":"Ainsworth, Jonathan Hayase, and Siddhartha Srinivasa","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:44.930147Z"},"links":{"cited_paper":"/paper/2209.04836","citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:aa85a8e132cb5c33d4c8578a6ccec727961148c3eb7fcd49dc64e78d1a5c72db","observation_id":"787d26cd-4d64-4449-89c8-590173aea06a","resolution":{"observed_at":"2026-08-01T07:13:44.930147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:13:47.681218Z","title":"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)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:47.681218Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:f385b8bf1c59e7733a7c0584a97b02160c41a59ab4e79beced5d7d24db08a7bf","observation_id":"4e51c07c-41bd-4ea2-87b4-b740c2534296","resolution":{"observed_at":"2026-08-01T07:13:47.681218Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:13:47.838796Z","title":"B.1 Permutation Alignment This expands the alignment procedure of Section 3.4","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:47.838796Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:ec678d43335ed58601d6d8f911c452d064d2feea87efaf4a62de5510d66efdf8","observation_id":"42aa7c1f-f358-4ac3-bf2a-af0c23c7fba9","resolution":{"observed_at":"2026-08-01T07:13:47.838796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:13:46.237699Z","title":"doi: 10.18653/v1/ P18-2110","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:46.237699Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:364949a879c527f90f84ad67cc19274802b1afa2f972ba00fe25df3c06235dee","observation_id":"6a0bc828-b5cc-48b5-be0a-5c0d12efec4d","resolution":{"observed_at":"2026-08-01T07:13:46.237699Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.05320","last_updated":"2016-09-30T22:20:39Z","snapshot_observed_at":"2026-07-06T05:00:17.202185Z","submitted_at":"2016-06-16T19:13:52Z","title":"Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.05320","snapshot_observed_at":"2026-08-01T07:13:46.476800Z","title":"Jan Ole Krugmann and Jochen Hartmann","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:46.476800Z"},"links":{"cited_paper":"/paper/1606.05320","citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:089b65b39eaf03e37f6f1d4f9a03e07282c95a5db96ce777227f73798d28e677","observation_id":"c747d0ae-3356-44be-8ec5-315df87265d3","resolution":{"observed_at":"2026-08-01T07:13:46.476800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/w18-6210","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/W18-6210","venue":null,"work_id":"a6825363-a57c-48c2-8e86-89e7722c12ec","year":null},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:46.695553Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:7056e14ee306c5a76b1569ddd3221810a20824894c7ff6df65e7921a1a22d648","observation_id":"1fec6515-8ec6-4eab-9999-11da8a28c31c","resolution":{"observed_at":"2026-08-01T07:18:34.238132Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:13:46.808770Z","title":"ISBN 979-10-95546-34-4","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:46.808770Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:f24bc4d486192a8d145caebfcb877f19cc7b09bb542b0fa08f316b69483b19c3","observation_id":"bd342e28-646f-4bbb-a53c-ec01c4002c5f","resolution":{"observed_at":"2026-08-01T07:13:46.808770Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-08-01T07:13:47.093238Z","title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter.arXiv preprint arXiv:1910.01108,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:47.093238Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:dfe527f990f683f8f19878aa884a5f23adefbaf270c3c6ce120b2552097c28f0","observation_id":"c985f8da-6a6f-40bb-a0fa-d86957df6442","resolution":{"observed_at":"2026-08-01T07:13:47.093238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.genbench-1.6","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/2023.genbench-1.6","venue":null,"work_id":"2b7ed874-d4d9-4903-b7e1-2546e3c06106","year":2023},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:47.262591Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:511795d3d47bdbe515e0274109d1a6659ec8fa92ec1c7324a3079b0085e77694","observation_id":"713f4da9-e7d2-4762-b350-fd88df92902e","resolution":{"observed_at":"2026-08-01T07:18:34.001926Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12510","last_updated":"2022-05-25T06:00:34Z","snapshot_observed_at":"2026-08-03T16:27:20.637305Z","submitted_at":"2022-05-25T06:00:34Z","title":"Exact Phase Transitions in Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.12510","snapshot_observed_at":"2026-08-01T07:13:47.445005Z","title":"Liu Ziyin and Masahito Ueda","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:47.445005Z"},"links":{"cited_paper":"/paper/2205.12510","citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:5f95b6f6a84a32a1770a8202839714144506a46ac3d30a73f0e4b04e77364e46","observation_id":"a536cd7a-2011-4158-98e0-3a8690528c1b","resolution":{"observed_at":"2026-08-01T07:13:47.445005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:13:45.592868Z","title":"Mario Geiger, Stefano Spigler, Stéphane d’Ascoli, Levent Sagun, Marco Baity-Jesi, Giulio Biroli, and Matthieu Wyart","venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":1983,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:45.592868Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:0bc0f8d60dabb47701cea016ff2da4394c28c791920f748376e52b2abb4221ad","observation_id":"686780d6-6fd5-4689-acd3-6734cba2bd35","resolution":{"observed_at":"2026-08-01T07:13:45.592868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06296","last_updated":"2022-07-05T11:40:49Z","snapshot_observed_at":"2026-08-10T01:11:52.514832Z","submitted_at":"2021-10-12T19:28:48Z","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06296","snapshot_observed_at":"2026-08-01T07:13:45.189799Z","title":"Rahim Entezari, Hanie Sedghi, Olga Saukh, and Behnam Neyshabur","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:45.189799Z"},"links":{"cited_paper":"/paper/2110.06296","citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:f2b3dc7438a6fbc996cb12b9d5c80bf587fa44c2550efb73e24b6e96dc15a4c0","observation_id":"3fe4be13-23c4-4c98-9759-a06a89fe458b","resolution":{"observed_at":"2026-08-01T07:13:45.189799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.neuron.2014.01.042","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Komal Florio, Valerio Basile, Marco Polignano, Pierpaolo Basile, and Viviana Patti","venue":"Neuron","work_id":"6f09e536-7c27-4a28-9090-e6cd478dd27a","year":2014},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:45.369526Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:77ca2b7a45c09a67e834cd0b49531c44a2d7f99a8dd144cf703a972536004e44","observation_id":"52de09d7-2622-496a-9514-1eab8ed687f2","resolution":{"observed_at":"2026-08-01T07:18:35.241945Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.09543","last_updated":"2024-01-19T19:45:37Z","snapshot_observed_at":"2026-07-06T16:07:41.796478Z","submitted_at":"2023-08-18T13:20:08Z","title":"Latent State Models of Training Dynamics","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.09543","snapshot_observed_at":"2026-08-01T07:13:45.857689Z","title":"Latent state models of training dynamics","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:45.857689Z"},"links":{"cited_paper":"/paper/2308.09543","citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:e13bbed998cb3dde358b7fd4530691333ebc17637603d72197ffe04638a84a4a","observation_id":"329a0a04-96e0-474b-967e-cfb95e7dd1f7","resolution":{"observed_at":"2026-08-01T07:13:45.857689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:13:45.079318Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:45.079318Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:71608d78b8410d5d79eaa126483ab8d9c6143c0d534d46cb82c607ef68b75555","observation_id":"93ae5803-7324-4858-bba9-7667126528c9","resolution":{"observed_at":"2026-08-01T07:13:45.079318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.09349","last_updated":"2019-06-17T08:20:27Z","snapshot_observed_at":"2026-07-06T07:04:08.003446Z","submitted_at":"2018-09-25T07:15:27Z","title":"The jamming transition as a paradigm to understand the loss landscape of deep neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.09349","snapshot_observed_at":"2026-08-01T07:13:45.720002Z","title":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:45.720002Z"},"links":{"cited_paper":"/paper/1809.09349","citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:64e402ef8fcb397e1a2ed1bdce5c767703998ab0af564f9fac0a54609b6326c6","observation_id":"73880daa-1ad3-4dc2-97dc-1b9269de7553","resolution":{"observed_at":"2026-08-01T07:13:45.720002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:13:46.927225Z","title":"doi: 10.18653/v1/D19-1018","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:46.927225Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:f0a5a403a603df28844e915f250c8ddf8e0402c0c3f3a0e2c9db6bc1dad2e2b5","observation_id":"b7d6aa90-cbaf-49d7-a4a4-bd12a8ca9258","resolution":{"observed_at":"2026-08-01T07:13:46.927225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.3390/app10124180","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URLhttps://doi.org/10.3390/app10124180","venue":"Applied Sciences","work_id":"62673686-d704-40b4-86f4-79d5b5644be1","year":null},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:45.508426Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:bc1a85b0c0afcd5baef7c3bc982651e323b3a52733f019d1a61c8f0ec3fd0dcb","observation_id":"4c5578cb-e798-4139-8100-1e6ef34df98a","resolution":{"observed_at":"2026-08-01T07:18:34.928390Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:13:47.024703Z","title":"doi: 10.18653/v1/2021.findings-emnlp.206","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:47.024703Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:8bfaf9858a9f6e138fe3c47a82f4adc104a7555e90bb2efa15093fa487f08270","observation_id":"a1e681da-f8dc-4497-8bcc-139ec190f841","resolution":{"observed_at":"2026-08-01T07:13:47.024703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12510","last_updated":"2022-05-25T06:00:34Z","snapshot_observed_at":"2026-08-03T16:27:20.637305Z","submitted_at":"2022-05-25T06:00:34Z","title":"Exact Phase Transitions in Deep Learning","version":1},"cited_work":{"arxiv_id":"2205.12510","doi":"10.48550/arxiv.2205.12510","metadata_source":"pith","pith_arxiv_id":"2205.12510","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"Exact Phase Transitions in Deep Learning","venue":"cs.LG","work_id":"0d2c0aee-fe63-4c43-995e-23e3c5b5d493","year":2022},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:47.557748Z"},"links":{"cited_paper":"/paper/2205.12510","citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:27fe9227820b807100d911d699b9fd9ac7f9091465c7462e71cfa6312d07a13e","observation_id":"873dcb82-c4b5-4ac5-9d91-cb2ffa41b94a","resolution":{"observed_at":"2026-08-01T07:18:33.780245Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.09543","last_updated":"2024-01-19T19:45:37Z","snapshot_observed_at":"2026-07-06T16:07:41.796478Z","submitted_at":"2023-08-18T13:20:08Z","title":"Latent State Models of Training Dynamics","version":3},"cited_work":{"arxiv_id":"2308.09543","doi":"10.48550/arxiv.2308.09543","metadata_source":"pith","pith_arxiv_id":"2308.09543","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"Latent State Models of Training Dynamics","venue":"cs.LG","work_id":"00480c8b-dd92-46c5-be60-6d40b1aaff84","year":2023},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:46.092398Z"},"links":{"cited_paper":"/paper/2308.09543","citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:60ec1e69f524879dfefb6394b4006856984bc04122edd7793341ddd6aaa70c5b","observation_id":"1d5df555-8adc-40e5-bcdd-460e2eed66d5","resolution":{"observed_at":"2026-08-01T07:18:34.558183Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T07:13:46.587730Z","title":"doi: 10.1007/s40547-024-00143-4","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-01T07:13:46.587730Z"},"links":{"citing_paper":"/paper/2607.27482"},"observation_digest":"sha256:0b69a6f8b4e96d99454b68e78fcde66b9b90fb836603cc19fd02fd17dcf710d1","observation_id":"68c243ec-9ed8-4905-bd9e-6a459aa9171f","resolution":{"observed_at":"2026-08-01T07:13:46.587730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.27482","last_updated":"2026-07-29T21:51:29Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T03:52:44.439499Z","submitted_at":"2026-07-29T21:51:29Z","title":"Latent States in Neural Networks: Recovering the Temporal Structure of Drifting Data from Model Weights"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":15,"verified_exact":5,"verified_fuzzy":0},"total_outbound_references":22},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"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."}