{"as_of":"2026-08-23T02:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8cb732b4888a268993a8fb28d82146eabe4c90403ce67bd04faadd50b5d85215","coverage":[{"denominator":21,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":21,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T14:57:46.266050Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2508.21106/citation-record","integrity":"/paper/2508.21106/integrity","json":"/paper/2508.21106/citation-record.json","paper":"/paper/2508.21106"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.985634Z","title":"A differential equation for modeling nesterov’s accelerated gradient method: Theory and insights","venue":null,"work_id":"2de9ed7c-de0a-4ac1-939f-4a0577268e63","year":2016},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.161235Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:d447dd43df68393cd661994bc268206a36023bee6efa647ff4fbe0f6294db1a3","observation_id":"c0cb8724-a1a0-4152-b4bd-437fe7a20bff","resolution":{"observed_at":"2026-08-05T14:57:46.991250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.963480Z","title":"A lyapunov analysis for accelerated gradient methods: From determinis- tic to stochastic case","venue":null,"work_id":"78303607-a742-4adc-8c47-18adb9852893","year":2020},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.167574Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:101d7dac1774034ea7f7a57c313913356b1ae8447f886f3dfe38aad359c0b407","observation_id":"8cce668e-40ce-4891-9ead-c2b60f3246ab","resolution":{"observed_at":"2026-08-05T14:57:46.969809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.14937","last_updated":"2023-09-30T21:07:16Z","snapshot_observed_at":"2026-08-16T16:28:06.006180Z","submitted_at":"2022-09-29T16:54:53Z","title":"NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.14937","snapshot_observed_at":"2026-08-05T14:57:46.173330Z","title":"NAG-GS: Semi-implicit, accelerated and robust stochastic optimizer","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.173330Z"},"links":{"cited_paper":"/paper/2209.14937","citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:5abbfc36d2846d0f690c2ea9d8a5136a705012f0433e68bb983165a4a3955e23","observation_id":"e15d7023-7857-49bb-9672-d2c6c8c4d130","resolution":{"observed_at":"2026-08-05T14:57:46.173330Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.790599Z","title":"A method of solving a convex programming problem with convergence rate O(1/k2)","venue":null,"work_id":"71453d30-bc44-4baa-bce1-a1aa6157deb6","year":1983},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.180465Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:3ce5e4259445b946c496761a08f194fcfa94180cf65a769cf122b511d136912b","observation_id":"9f4034d1-9e88-42d0-8c2b-133d0439c8ed","resolution":{"observed_at":"2026-08-05T14:57:46.943868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-05T14:57:46.185934Z","title":"Adaptive subgradient methods for online learning and stochastic optimization","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.185934Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:23ee4706eeedc69850ac94601c50e5bb616c9d1588df6986902000d2e0896280","observation_id":"1f604b57-c3d5-4e9b-90a1-e228f8201b34","resolution":{"observed_at":"2026-08-05T14:57:46.185934Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.758518Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":"ac292344-af98-4da5-a3a0-ab6b91eed253","year":2015},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.192172Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:e6c50e63de2f09ba07353cc7f2a65de76cdac1d7009ff78f7991dec14414de3a","observation_id":"a56d38a7-ff15-4714-af8e-cb9b6337dc05","resolution":{"observed_at":"2026-08-05T14:57:46.764386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.731846Z","title":"Hinton, Nitish Srivastava, and Kevin Swersky","venue":null,"work_id":"5c2b5d8e-1eb6-4493-8aaf-f331f7dcb521","year":2012},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.197835Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:57eb0a51f2e9e5435171950053c6c5182a3d9903f70dd4fb32673a5d27b46c57","observation_id":"12472c65-1927-4bad-b67e-fd882206cf75","resolution":{"observed_at":"2026-08-05T14:57:46.739792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1405.0223","last_updated":"2016-12-30T08:11:13Z","snapshot_observed_at":"2026-08-18T18:57:39.020840Z","submitted_at":"2014-05-01T17:18:17Z","title":"Fast symmetric factorization of hierarchical matrices with applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1405.0223","snapshot_observed_at":"2026-08-05T14:57:46.202967Z","title":"Fast symmetric factorization of hierarchical matrices with applications","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.202967Z"},"links":{"cited_paper":"/paper/1405.0223","citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:8f8b36b6a1fd1dcdc779024a945688600b2a1e72d6851104b0367bf1457eed3d","observation_id":"01fe4d20-3e98-423a-8786-81acc332cc3a","resolution":{"observed_at":"2026-08-05T14:57:46.202967Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.711231Z","title":"Buhmann, and Nicolai Meinshausen","venue":null,"work_id":"940f2d16-1578-4c14-baed-49a7999c275c","year":2016},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.208440Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:28010008d5dcc4f016cfd81c44eecfc62c2d5122e6db2ea1a57ea218217aa93c","observation_id":"0aa6c51b-0928-4bab-9588-b5810dd92272","resolution":{"observed_at":"2026-08-05T14:57:46.716678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.691290Z","title":"Ravikumar","venue":null,"work_id":"45718b8d-7c2c-47e5-9291-1885a5da26dd","year":2018},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.213433Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:5c78628ef6e4f3153e1f1bf753068e9775497b04aed8aaf61573d9c261be410a","observation_id":"0bc8450f-d7c5-4c63-ae42-0586c1a37f3e","resolution":{"observed_at":"2026-08-05T14:57:46.697408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-05T14:57:46.218132Z","title":"Shampoo: Preconditioned stochastic tensor optimization, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.218132Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:00f47f9796efdf26316974e62b638b4dbd75769249dea2d9596ae6c83d454598","observation_id":"a07c0f1d-7372-418c-a196-bc556810cccd","resolution":{"observed_at":"2026-08-05T14:57:46.218132Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.651896Z","title":"SOAP: One-shot pruning of generative pre-trained transformer checkpoints with a second-order method, 2024","venue":null,"work_id":"a8849ce1-54ea-425f-9181-2563e610db0a","year":2024},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.223059Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:5f37db5789730d56c95efeb8681625d7673f8e36ebf4fa2efec766371ba433a3","observation_id":"eb859d9d-e365-4b0e-89ef-708bc84307a0","resolution":{"observed_at":"2026-08-05T14:57:46.658323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.625259Z","title":"Efficient full-matrix adaptive regularization, 2020","venue":null,"work_id":"edde1f4a-2900-4bb4-9441-7a80b7618139","year":2020},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.227884Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:08ac7bc581937e0149eaf0c136c4be5f331e33fb7da5979c5236631984ae6e2e","observation_id":"3025c056-192e-4382-98f7-0891e9606cc1","resolution":{"observed_at":"2026-08-05T14:57:46.634423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.604929Z","title":"Remove that square root: A new efficient scale-invariant version of adagrad","venue":null,"work_id":"04ec7520-9b28-462f-8e8b-a5a49d72f24f","year":2024},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.232425Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:e44fd163011a7ec4bc53c78487d84ac84b74481799e20fe6e19d93c5f9089e98","observation_id":"a62dd9a9-8575-4258-ae4f-a4ee28a7daf8","resolution":{"observed_at":"2026-08-05T14:57:46.611913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.5701","last_updated":"2012-12-22T15:46:49Z","snapshot_observed_at":"2026-08-19T05:19:50.480481Z","submitted_at":"2012-12-22T15:46:49Z","title":"ADADELTA: An Adaptive Learning Rate Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.5701","snapshot_observed_at":"2026-08-05T14:57:46.237358Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.237358Z"},"links":{"cited_paper":"/paper/1212.5701","citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:b05a451c6637124346f6b098ba186d589a0bacd3ec9a798a952182d3266f7f94","observation_id":"36ca58d6-a7d4-471d-b8d9-2919ab651a07","resolution":{"observed_at":"2026-08-05T14:57:46.237358Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.584388Z","title":"Incorporating nesterov momentum into adam","venue":null,"work_id":"b5947086-2f4e-4069-85b2-f71b82c3a40e","year":2016},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.242370Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:675964e69a319cd128a57b9d6d551b92930d1a7450a1d6aa2c6df67213d7a54e","observation_id":"c7b2bf66-7b46-4633-8ead-40e160ba2c09","resolution":{"observed_at":"2026-08-05T14:57:46.590831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.564128Z","title":"Fast low-rank modifications of the thin singular value decomposition","venue":null,"work_id":"d37f601a-1e9b-4b9b-a16c-7428b5aec056","year":2006},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.246867Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:30bf0085d3ddffe417c2ef8619297e6082eb0be70879bdb83d2289377c51caad","observation_id":"7352e02f-67d1-41a5-894f-808dec55c27f","resolution":{"observed_at":"2026-08-05T14:57:46.570242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.545345Z","title":"A projector-splitting integrator for dynamical low-rank approximation, 2013","venue":null,"work_id":"fd02954c-e4fd-4693-8877-919116e4b2cb","year":2013},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.251467Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:dd8ccc13376f5dfbe1a92d38ba3d4fb01c1d8d7b074bd8f7a9f71e05491390a6","observation_id":"b37ed6e1-23f7-4cb2-900c-420b9a0f688d","resolution":{"observed_at":"2026-08-05T14:57:46.551178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"stable/2344614","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.412356Z","title":null,"venue":null,"work_id":"b879acd3-1922-44c1-9abd-19982d0d1572","year":1972},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.256252Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:73409cbe6e4898faad090a939223975e428245eb1b8a925719fa2f8891dcfa63","observation_id":"f3b54426-bfbb-4add-a11f-344871e35d59","resolution":{"observed_at":"2026-08-05T14:57:46.421800Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-05T14:57:46.261072Z","title":"UCI machine learning repository, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.261072Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:abdea954def51b42902f1dca6427a80e8c24f0ad1e3d3942dd48bd9c9d86af81","observation_id":"2a5993ae-62b6-4620-b3c5-93b0416ca442","resolution":{"observed_at":"2026-08-05T14:57:46.261072Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:57:46.503215Z","title":"Stress test procedure for feature selection algorithms","venue":null,"work_id":"77d81744-d82f-4a57-a0f1-11e01eef355f","year":2015},"citing_paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T14:57:46.266050Z"},"links":{"citing_paper":"/paper/2508.21106"},"observation_digest":"sha256:3f408156737adf33abd8a752ffe82c764c93d83affcc73807f7da2004920f479","observation_id":"8f496f1d-2f37-423d-b3fa-d1d2bb559be0","resolution":{"observed_at":"2026-08-05T14:57:46.515857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.21106","last_updated":"2025-08-28T13:15:05Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T21:58:57.037665Z","submitted_at":"2025-08-28T13:15:05Z","title":"Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models"},"reference_resolution":{"displayed":21,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":1,"verified_fuzzy":14},"total_outbound_references":21},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2508.21106."}