{"as_of":"2026-08-05T08:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:23eb4b73db5028475ca0cc26d13dc335ce2f8956bfde470a30b9b67d11976cfe","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":9,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":9,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":9,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T21:12:51.552457Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-21T05:49:40.560450Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-08-04T21:12:51.552457Z","title":"FedNL: Making Newton-type meth- ods applicable to federated learning.arXiv preprint arXiv:2106.02969, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08195","last_updated":"2025-09-09T23:59:20Z","snapshot_observed_at":"2026-08-04T21:12:46.200789Z","submitted_at":"2025-09-09T23:59:20Z","title":"Sketched Gaussian Mechanism for Private Federated Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T21:12:51.552457Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2509.08195"},"observation_digest":"sha256:d066d788d0b2158807c6112fd1be5d179c95e8262f75689ebe5e871e21cf5463","observation_id":"bd38a1f0-30da-4202-b684-0465e3d5210e","resolution":{"observed_at":"2026-08-04T21:12:51.552457Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-07-14T20:05:26.173933Z","title":"Fednl: Making newton-type methods applicable to federated learning.arXiv preprint arXiv:2106.02969,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.28314","last_updated":"2026-03-30T11:37:03Z","snapshot_observed_at":"2026-07-16T23:19:34.048977Z","submitted_at":"2026-03-30T11:37:03Z","title":"Exclusive Hadron Observables in Neutrino Induced $2p2h$ Multinucleon Knockout","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-14T20:05:26.173933Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2603.28314"},"observation_digest":"sha256:dff5045e4db024bdcefeff3c7893f1e7905bc5adedc791bb0665c7b78336a33b","observation_id":"f8d62a70-4017-40c4-9e17-56dbb8b4013a","resolution":{"observed_at":"2026-07-14T20:05:26.173933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":"2106.02969","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2106.02969 , year=","venue":null,"work_id":"66015604-3177-43f4-b5cc-3b2007d90887","year":2021},"citing_paper":{"arxiv_id":"2605.07795","last_updated":"2026-05-08T14:32:41Z","snapshot_observed_at":"2026-07-06T23:20:06.574823Z","submitted_at":"2026-05-08T14:32:41Z","title":"Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits","version":1},"reference_index":105,"source":"arxiv_source","source_observed_at":"2026-05-11T02:52:53.588595Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2605.07795"},"observation_digest":"sha256:ebf878cba0dad13d9027d093b925ecec6b949b8ea72a6b514a95a44d1e7cbbde","observation_id":"077e4cb5-4b9e-4a44-8f25-3fb504c0bf57","resolution":{"observed_at":"2026-05-11T03:05:54.848748Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":"2106.02969","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2106.02969 , year=","venue":null,"work_id":"66015604-3177-43f4-b5cc-3b2007d90887","year":2021},"citing_paper":{"arxiv_id":"2605.08871","last_updated":"2026-05-09T10:46:59Z","snapshot_observed_at":"2026-07-31T15:53:03.039634Z","submitted_at":"2026-05-09T10:46:59Z","title":"Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction","version":1},"reference_index":188,"source":"arxiv_source","source_observed_at":"2026-05-12T01:51:20.003552Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2605.08871"},"observation_digest":"sha256:3dc5ec1bd37586e155fb7db010b2b3b837e39432560460b029952803576ca269","observation_id":"5942a421-81b8-4e9d-a6dd-b85d2be87bfb","resolution":{"observed_at":"2026-05-12T07:51:33.861237Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":"2106.02969","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2106.02969 , year=","venue":null,"work_id":"66015604-3177-43f4-b5cc-3b2007d90887","year":2021},"citing_paper":{"arxiv_id":"2605.13434","last_updated":"2026-05-13T12:27:22Z","snapshot_observed_at":"2026-07-06T23:25:01.951546Z","submitted_at":"2026-05-13T12:27:22Z","title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","version":1},"reference_index":200,"source":"arxiv_source","source_observed_at":"2026-05-14T19:31:12.149482Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2605.13434"},"observation_digest":"sha256:1f0d999c0906152491aec2e06b32e0cf08819a7f70b31ffdd5e3861b787e28f4","observation_id":"939ee9d0-f095-4b18-8bb6-4c84cf793e06","resolution":{"observed_at":"2026-05-14T19:32:52.087092Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":"2106.02969","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2106.02969 , year=","venue":null,"work_id":"66015604-3177-43f4-b5cc-3b2007d90887","year":2021},"citing_paper":{"arxiv_id":"2605.18174","last_updated":"2026-05-18T10:18:02Z","snapshot_observed_at":"2026-07-06T23:29:04.241654Z","submitted_at":"2026-05-18T10:18:02Z","title":"Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method","version":1},"reference_index":190,"source":"arxiv_source","source_observed_at":"2026-05-20T13:08:52.912250Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2605.18174"},"observation_digest":"sha256:56f58abd79ec95b852cbcf1993b6c4204000b3f1bc7d02f7071066678e2e277a","observation_id":"b3f0d701-172f-417e-8027-d92d130d3d95","resolution":{"observed_at":"2026-05-20T13:13:18.560490Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":"2106.02969","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2106.02969 , year=","venue":null,"work_id":"66015604-3177-43f4-b5cc-3b2007d90887","year":2021},"citing_paper":{"arxiv_id":"2605.20866","last_updated":"2026-05-20T08:01:45Z","snapshot_observed_at":"2026-08-02T02:54:50.828651Z","submitted_at":"2026-05-20T08:01:45Z","title":"LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging","version":1},"reference_index":191,"source":"arxiv_source","source_observed_at":"2026-05-21T05:49:28.713982Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2605.20866"},"observation_digest":"sha256:efd5b053775ffe8f1529b43b2e09e8aad57efd4b2f8077bd5dfd79103f946f25","observation_id":"bce7632a-9c6b-4ad4-a071-64eac23e09be","resolution":{"observed_at":"2026-05-21T05:49:40.562301Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":"2106.02969","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2106.02969 , year=","venue":null,"work_id":"66015604-3177-43f4-b5cc-3b2007d90887","year":2021},"citing_paper":{"arxiv_id":"2605.21169","last_updated":"2026-05-21T14:14:37Z","snapshot_observed_at":"2026-07-06T23:31:37.061253Z","submitted_at":"2026-05-20T13:41:29Z","title":"Decentralized Inexact Cubic Newton Method with Consensus Procedure","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-21T03:32:25.678618Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2605.21169"},"observation_digest":"sha256:0209f819e6c3a980edc72f25f19e77c6b7b3606e4b8b43cb2cde508a144c1dab","observation_id":"4ac7e8ca-187c-4ec2-a7b1-e3c880cdf0c1","resolution":{"observed_at":"2026-05-21T03:33:56.505234Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.02969","snapshot_observed_at":"2026-07-12T00:07:55.485589Z","title":"arXiv preprint arXiv:2106.02969 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03763","last_updated":"2026-07-04T08:31:49Z","snapshot_observed_at":"2026-07-12T00:07:51.408954Z","submitted_at":"2026-07-04T08:31:49Z","title":"FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-07-12T00:07:55.485589Z"},"links":{"cited_paper":"/paper/2106.02969","citing_paper":"/paper/2607.03763"},"observation_digest":"sha256:8f4bea1581c5cf3e17030b9099a8cf4075dc90eb96011086c8fb9963c00db658","observation_id":"40404671-bca7-47c9-9bdd-e5851af18910","resolution":{"observed_at":"2026-07-12T00:07:55.485589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2106.02969/citation-record","integrity":"/paper/2106.02969/integrity","json":"/paper/2106.02969/citation-record.json","paper":"/paper/2106.02969"},"outbound":[],"paper":{"arxiv_id":"2106.02969","last_updated":"2022-05-22T16:18:49Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T11:16:16.773116Z","submitted_at":"2021-06-05T21:30:11Z","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 9 inbound Pith citation observations for arXiv:2106.02969."}